diff options
51 files changed, 1904 insertions, 3898 deletions
diff --git a/src/mem/bus.cc b/src/mem/bus.cc index cf9e54e62..3c5283a77 100644 --- a/src/mem/bus.cc +++ b/src/mem/bus.cc @@ -252,6 +252,7 @@ Bus::recvFunctional(Packet *pkt) DPRINTF(Bus, "recvFunctional: packet src %d dest %d addr 0x%x cmd %s\n", pkt->getSrc(), pkt->getDest(), pkt->getAddr(), pkt->cmdString()); assert(pkt->getDest() == Packet::Broadcast); + atomicSnoop(pkt); findPort(pkt->getAddr(), pkt->getSrc())->sendFunctional(pkt); } diff --git a/src/mem/cache/base_cache.cc b/src/mem/cache/base_cache.cc index a172847df..d7ccca8c0 100644 --- a/src/mem/cache/base_cache.cc +++ b/src/mem/cache/base_cache.cc @@ -96,6 +96,15 @@ void BaseCache::CachePort::recvRetry() { Packet *pkt; + if (!drainList.empty()) { + //We have some responses to drain first + bool result = true; + while (result && !drainList.empty()) { + result = sendTiming(drainList.front()); + if (result) + drainList.pop_front(); + } + } if (!isCpuSide) { @@ -199,8 +208,17 @@ BaseCache::CacheEvent::process() return; } //Response - //Know the packet to send, no need to mark in service (must succed) - assert(cachePort->sendTiming(pkt)); + //Know the packet to send + pkt->result = Packet::Success; + pkt->makeTimingResponse(); + if (!cachePort->drainList.empty()) { + //Already blocked waiting for bus, just append + cachePort->drainList.push_back(pkt); + } + else if (!cachePort->sendTiming(pkt)) { + //It failed, save it to list of drain events + cachePort->drainList.push_back(pkt); + } } const char * diff --git a/src/mem/cache/base_cache.hh b/src/mem/cache/base_cache.hh index 069dbab58..c69fb7fd5 100644 --- a/src/mem/cache/base_cache.hh +++ b/src/mem/cache/base_cache.hh @@ -110,6 +110,8 @@ class BaseCache : public MemObject bool mustSendRetry; bool isCpuSide; + + std::list<Packet *> drainList; }; struct CacheEvent : public Event @@ -127,6 +129,8 @@ class BaseCache : public MemObject CachePort *cpuSidePort; CachePort *memSidePort; + bool snoopRangesSent; + public: virtual Port *getPort(const std::string &if_name, int idx = -1); @@ -149,17 +153,22 @@ class BaseCache : public MemObject void recvStatusChange(Port::Status status, bool isCpuSide) { - if (status == Port::RangeChange) - { - if (!isCpuSide) - { + if (status == Port::RangeChange){ + if (!isCpuSide) { cpuSidePort->sendStatusChange(Port::RangeChange); + if (topLevelCache && !snoopRangesSent) { + snoopRangesSent = true; + memSidePort->sendStatusChange(Port::RangeChange); + } } - else - { + else { memSidePort->sendStatusChange(Port::RangeChange); } } + else if (status == Port::SnoopSquash) { + assert(snoopPhase2); + snoopPhase2 = false; + } } virtual Packet *getPacket() @@ -205,6 +214,10 @@ class BaseCache : public MemObject /** True if this cache is connected to the CPU. */ bool topLevelCache; + + /** True if we are now in phase 2 of the snoop process. */ + bool snoopPhase2; + /** Stores time the cache blocked for statistics. */ Tick blockedCycle; @@ -332,6 +345,7 @@ class BaseCache : public MemObject //Start ports at null if more than one is created we should panic cpuSidePort = NULL; memSidePort = NULL; + snoopRangesSent = false; } virtual void init(); @@ -382,9 +396,12 @@ class BaseCache : public MemObject blocked_causes[cause]++; blockedCycle = curTick; } - blocked |= flag; - DPRINTF(Cache,"Blocking for cause %s\n", cause); - cpuSidePort->setBlocked(); + if (!(blocked & flag)) { + //Wasn't already blocked for this cause + blocked |= flag; + DPRINTF(Cache,"Blocking for cause %s\n", cause); + cpuSidePort->setBlocked(); + } } /** @@ -395,8 +412,11 @@ class BaseCache : public MemObject void setBlockedForSnoop(BlockedCause cause) { uint8_t flag = 1 << cause; - blockedSnoop |= flag; - memSidePort->setBlocked(); + if (!(blocked & flag)) { + //Wasn't already blocked for this cause + blockedSnoop |= flag; + memSidePort->setBlocked(); + } } /** @@ -503,8 +523,6 @@ class BaseCache : public MemObject */ void respond(Packet *pkt, Tick time) { - pkt->makeTimingResponse(); - pkt->result = Packet::Success; CacheEvent *reqCpu = new CacheEvent(cpuSidePort, pkt); reqCpu->schedule(time); } @@ -517,10 +535,8 @@ class BaseCache : public MemObject void respondToMiss(Packet *pkt, Tick time) { if (!pkt->req->isUncacheable()) { - missLatency[pkt->cmdToIndex()][pkt->req->getThreadNum()] += time - pkt->time; + missLatency[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/] += time - pkt->time; } - pkt->makeTimingResponse(); - pkt->result = Packet::Success; CacheEvent *reqCpu = new CacheEvent(cpuSidePort, pkt); reqCpu->schedule(time); } @@ -529,10 +545,12 @@ class BaseCache : public MemObject * Suppliess the data if cache to cache transfers are enabled. * @param pkt The bus transaction to fulfill. */ - void respondToSnoop(Packet *pkt) + void respondToSnoop(Packet *pkt, Tick time) { - assert("Implement\n" && 0); +// assert("Implement\n" && 0); // mi->respond(pkt,curTick + hitLatency); + CacheEvent *reqMem = new CacheEvent(memSidePort, pkt); + reqMem->schedule(time); } /** @@ -551,6 +569,16 @@ class BaseCache : public MemObject else { //This is where snoops get updated + AddrRangeList dummy; + if (!topLevelCache) + { + cpuSidePort->getPeerAddressRanges(dummy, snoop); + } + else + { + snoop.push_back(RangeSize(0,-1)); + } + return; } } diff --git a/src/mem/cache/cache.hh b/src/mem/cache/cache.hh index 989b8743e..4b8870c95 100644 --- a/src/mem/cache/cache.hh +++ b/src/mem/cache/cache.hh @@ -251,7 +251,7 @@ class Cache : public BaseCache * request. * @return The estimated completion time. */ - Tick probe(Packet * &pkt, bool update); + Tick probe(Packet * &pkt, bool update, CachePort * otherSidePort); /** * Snoop for the provided request in the cache and return the estimated @@ -262,7 +262,7 @@ class Cache : public BaseCache * request. * @return The estimated completion time. */ - Tick snoopProbe(Packet * &pkt, bool update); + Tick snoopProbe(Packet * &pkt); }; #endif // __CACHE_HH__ diff --git a/src/mem/cache/cache_impl.hh b/src/mem/cache/cache_impl.hh index 593dbecf3..46f4b0ebe 100644 --- a/src/mem/cache/cache_impl.hh +++ b/src/mem/cache/cache_impl.hh @@ -63,14 +63,26 @@ doTimingAccess(Packet *pkt, CachePort *cachePort, bool isCpuSide) if (pkt->isWrite() && (pkt->req->getFlags() & LOCKED)) { pkt->req->setScResult(1); } - access(pkt); + if (!(pkt->flags & SATISFIED)) { + access(pkt); + } } else { if (pkt->isResponse()) handleResponse(pkt); - else - snoop(pkt); + else { + //Check if we are in phase1 + if (!snoopPhase2) { + snoopPhase2 = true; + } + else { + //Check if we should do the snoop + if (pkt->flags && SNOOP_COMMIT) + snoop(pkt); + snoopPhase2 = false; + } + } } return true; } @@ -87,7 +99,7 @@ doAtomicAccess(Packet *pkt, bool isCpuSide) pkt->req->setScResult(1); } - probe(pkt, true); + probe(pkt, true, NULL); //TEMP ALWAYS SUCCES FOR NOW pkt->result = Packet::Success; } @@ -96,7 +108,7 @@ doAtomicAccess(Packet *pkt, bool isCpuSide) if (pkt->isResponse()) handleResponse(pkt); else - snoopProbe(pkt, true); + snoopProbe(pkt); } //Fix this timing info return hitLatency; @@ -117,16 +129,13 @@ doFunctionalAccess(Packet *pkt, bool isCpuSide) assert("Can't handle LL/SC on functional path\n"); } - probe(pkt, true); + probe(pkt, false, memSidePort); //TEMP ALWAYS SUCCESFUL FOR NOW pkt->result = Packet::Success; } else { - if (pkt->isResponse()) - handleResponse(pkt); - else - snoopProbe(pkt, true); + probe(pkt, false, cpuSidePort); } } @@ -239,7 +248,7 @@ Cache<TagStore,Buffering,Coherence>::access(PacketPtr &pkt) pkt->getAddr() & ~((Addr)blkSize - 1), pkt->req->getPC()); if (blk) { // Hit - hits[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + hits[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; // clear dirty bit if write through if (pkt->needsResponse()) respond(pkt, curTick+lat); @@ -249,7 +258,7 @@ Cache<TagStore,Buffering,Coherence>::access(PacketPtr &pkt) // Miss if (!pkt->req->isUncacheable()) { - misses[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + misses[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; /** @todo Move miss count code into BaseCache */ if (missCount) { --missCount; @@ -270,7 +279,7 @@ Cache<TagStore,Buffering,Coherence>::getPacket() Packet * pkt = missQueue->getPacket(); if (pkt) { if (!pkt->req->isUncacheable()) { - if (pkt->cmd == Packet::HardPFReq) misses[Packet::HardPFReq][pkt->req->getThreadNum()]++; + if (pkt->cmd == Packet::HardPFReq) misses[Packet::HardPFReq][0/*pkt->req->getThreadNum()*/]++; BlkType *blk = tags->findBlock(pkt); Packet::Command cmd = coherence->getBusCmd(pkt->cmd, (blk)? blk->status : 0); @@ -314,9 +323,10 @@ Cache<TagStore,Buffering,Coherence>::handleResponse(Packet * &pkt) PacketList writebacks; blk = tags->handleFill(blk, (MSHR*)pkt->senderState, coherence->getNewState(pkt,old_state), - writebacks); + writebacks, pkt); while (!writebacks.empty()) { missQueue->doWriteback(writebacks.front()); + writebacks.pop_front(); } } missQueue->handleResponse(pkt, curTick + hitLatency); @@ -372,7 +382,6 @@ template<class TagStore, class Buffering, class Coherence> void Cache<TagStore,Buffering,Coherence>::snoop(Packet * &pkt) { - Addr blk_addr = pkt->getAddr() & ~(Addr(blkSize-1)); BlkType *blk = tags->findBlock(pkt); MSHR *mshr = missQueue->findMSHR(blk_addr); @@ -385,7 +394,10 @@ Cache<TagStore,Buffering,Coherence>::snoop(Packet * &pkt) //If the outstanding request was an invalidate (upgrade,readex,..) //Then we need to ACK the request until we get the data //Also NACK if the outstanding request is not a cachefill (writeback) + pkt->flags |= SATISFIED; pkt->flags |= NACKED_LINE; + assert("Don't detect these on the other side yet\n"); + respondToSnoop(pkt, curTick + hitLatency); return; } else { @@ -398,6 +410,7 @@ Cache<TagStore,Buffering,Coherence>::snoop(Packet * &pkt) //@todo Make it so that a read to a pending read can't be exclusive now. //Set the address so find match works + assert("Don't have invalidates yet\n"); invalidatePkt->addrOverride(pkt->getAddr()); //Append the invalidate on @@ -433,7 +446,7 @@ Cache<TagStore,Buffering,Coherence>::snoop(Packet * &pkt) assert(offset + pkt->getSize() <=blkSize); memcpy(pkt->getPtr<uint8_t>(), mshr->pkt->getPtr<uint8_t>() + offset, pkt->getSize()); - respondToSnoop(pkt); + respondToSnoop(pkt, curTick + hitLatency); } if (pkt->isInvalidate()) { @@ -449,7 +462,7 @@ Cache<TagStore,Buffering,Coherence>::snoop(Packet * &pkt) bool satisfy = coherence->handleBusRequest(pkt,blk,mshr, new_state); if (satisfy) { tags->handleSnoop(blk, new_state, pkt); - respondToSnoop(pkt); + respondToSnoop(pkt, curTick + hitLatency); return; } tags->handleSnoop(blk, new_state); @@ -486,7 +499,7 @@ Cache<TagStore,Buffering,Coherence>::invalidateBlk(Addr addr) */ template<class TagStore, class Buffering, class Coherence> Tick -Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update) +Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update, CachePort* otherSidePort) { // MemDebug::cacheProbe(pkt); if (!pkt->req->isUncacheable()) { @@ -517,7 +530,8 @@ Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update) missQueue->findWrites(blk_addr, writes); if (!update) { - memSidePort->sendFunctional(pkt); + otherSidePort->sendFunctional(pkt); + // Check for data in MSHR and writebuffer. if (mshr) { warn("Found outstanding miss on an non-update probe"); @@ -612,12 +626,15 @@ Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update) lat = memSidePort->sendAtomic(busPkt); + //Be sure to flip the response to a request for coherence + busPkt->makeAtomicResponse(); + /* if (!(busPkt->flags & SATISFIED)) { // blocked at a higher level, just return return 0; } -*/ misses[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; +*/ misses[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; CacheBlk::State old_state = (blk) ? blk->status : 0; tags->handleFill(blk, busPkt, @@ -642,10 +659,10 @@ Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update) } if (update) { - hits[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + hits[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; } else if (pkt->isWrite()) { // Still need to change data in all locations. - return memSidePort->sendAtomic(pkt); + return otherSidePort->sendAtomic(pkt); } return curTick + lat; } @@ -655,18 +672,18 @@ Cache<TagStore,Buffering,Coherence>::probe(Packet * &pkt, bool update) template<class TagStore, class Buffering, class Coherence> Tick -Cache<TagStore,Buffering,Coherence>::snoopProbe(PacketPtr &pkt, bool update) +Cache<TagStore,Buffering,Coherence>::snoopProbe(PacketPtr &pkt) { - Addr blk_addr = pkt->getAddr() & ~(Addr(blkSize-1)); - BlkType *blk = tags->findBlock(pkt); - MSHR *mshr = missQueue->findMSHR(blk_addr); - CacheBlk::State new_state = 0; - bool satisfy = coherence->handleBusRequest(pkt,blk,mshr, new_state); - if (satisfy) { - tags->handleSnoop(blk, new_state, pkt); - return hitLatency; - } - tags->handleSnoop(blk, new_state); - return 0; + Addr blk_addr = pkt->getAddr() & ~(Addr(blkSize-1)); + BlkType *blk = tags->findBlock(pkt); + MSHR *mshr = missQueue->findMSHR(blk_addr); + CacheBlk::State new_state = 0; + bool satisfy = coherence->handleBusRequest(pkt,blk,mshr, new_state); + if (satisfy) { + tags->handleSnoop(blk, new_state, pkt); + return hitLatency; + } + tags->handleSnoop(blk, new_state); + return 0; } diff --git a/src/mem/cache/miss/blocking_buffer.cc b/src/mem/cache/miss/blocking_buffer.cc index 67fc7ae56..7a6ea9133 100644 --- a/src/mem/cache/miss/blocking_buffer.cc +++ b/src/mem/cache/miss/blocking_buffer.cc @@ -189,7 +189,7 @@ BlockingBuffer::squash(int threadNum) if (miss.threadNum == threadNum) { Packet * target = miss.getTarget(); miss.popTarget(); - assert(target->req->getThreadNum() == threadNum); + assert(0/*target->req->getThreadNum()*/ == threadNum); target = NULL; assert(!miss.hasTargets()); miss.ntargets=0; @@ -218,7 +218,7 @@ BlockingBuffer::doWriteback(Addr addr, } ///All writebacks charged to same thread @todo figure this out - writebacks[pkt->req->getThreadNum()]++; + writebacks[0/*pkt->req->getThreadNum()*/]++; wb.allocateAsBuffer(pkt); cache->setMasterRequest(Request_WB, curTick); @@ -230,7 +230,7 @@ BlockingBuffer::doWriteback(Addr addr, void BlockingBuffer::doWriteback(Packet * &pkt) { - writebacks[pkt->req->getThreadNum()]++; + writebacks[0/*pkt->req->getThreadNum()*/]++; wb.allocateAsBuffer(pkt); diff --git a/src/mem/cache/miss/miss_queue.cc b/src/mem/cache/miss/miss_queue.cc index 76fb25716..273b6587f 100644 --- a/src/mem/cache/miss/miss_queue.cc +++ b/src/mem/cache/miss/miss_queue.cc @@ -413,8 +413,8 @@ MissQueue::handleMiss(Packet * &pkt, int blkSize, Tick time) mshr = mq.findMatch(blkAddr); if (mshr) { //@todo remove hw_pf here - mshr_hits[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; - if (mshr->threadNum != pkt->req->getThreadNum()) { + mshr_hits[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; + if (mshr->threadNum != 0/*pkt->req->getThreadNum()*/) { mshr->threadNum = -1; } mq.allocateTarget(mshr, pkt); @@ -434,11 +434,11 @@ MissQueue::handleMiss(Packet * &pkt, int blkSize, Tick time) mshr_no_allocate_misses++; } else { - mshr_misses[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + mshr_misses[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; } } else { //Count uncacheable accesses - mshr_uncacheable[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + mshr_uncacheable[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; size = pkt->getSize(); } if (pkt->isWrite() && (pkt->req->isUncacheable() || !writeAllocate || @@ -499,7 +499,7 @@ MissQueue::getPacket() pkt = prefetcher->getPacket(); if (pkt) { //Update statistic on number of prefetches issued (hwpf_mshr_misses) - mshr_misses[pkt->cmdToIndex()][pkt->req->getThreadNum()]++; + mshr_misses[pkt->cmdToIndex()][0/*pkt->req->getThreadNum()*/]++; //It will request the bus for the future, but should clear that immedieatley allocateMiss(pkt, pkt->getSize(), curTick); pkt = mq.getReq(); @@ -592,7 +592,7 @@ MissQueue::handleResponse(Packet * &pkt, Tick time) BlockedCause cause = NUM_BLOCKED_CAUSES; if (pkt->isCacheFill() && !pkt->isNoAllocate()) { - mshr_miss_latency[mshr->originalCmd][pkt->req->getThreadNum()] += + mshr_miss_latency[mshr->originalCmd][0/*pkt->req->getThreadNum()*/] += curTick - pkt->time; // targets were handled in the cache tags if (mshr == noTargetMSHR) { @@ -619,7 +619,7 @@ MissQueue::handleResponse(Packet * &pkt, Tick time) } } else { if (pkt->req->isUncacheable()) { - mshr_uncacheable_lat[pkt->cmd][pkt->req->getThreadNum()] += + mshr_uncacheable_lat[pkt->cmd][0/*pkt->req->getThreadNum()*/] += curTick - pkt->time; } if (mshr->hasTargets() && pkt->req->isUncacheable()) { @@ -725,7 +725,7 @@ MissQueue::doWriteback(Addr addr, } ///All writebacks charged to same thread @todo figure this out - writebacks[pkt->req->getThreadNum()]++; + writebacks[0/*pkt->req->getThreadNum()*/]++; allocateWrite(pkt, 0, curTick); } @@ -734,7 +734,7 @@ MissQueue::doWriteback(Addr addr, void MissQueue::doWriteback(Packet * &pkt) { - writebacks[pkt->req->getThreadNum()]++; + writebacks[0/*pkt->req->getThreadNum()*/]++; allocateWrite(pkt, 0, curTick); } diff --git a/src/mem/cache/miss/mshr.cc b/src/mem/cache/miss/mshr.cc index 519ec5ebd..f36032672 100644 --- a/src/mem/cache/miss/mshr.cc +++ b/src/mem/cache/miss/mshr.cc @@ -88,7 +88,7 @@ void MSHR::allocateAsBuffer(Packet * &target) { addr = target->getAddr(); - threadNum = target->req->getThreadNum(); + threadNum = 0/*target->req->getThreadNum()*/; pkt = new Packet(target->req, target->cmd, -1); pkt->allocate(); pkt->senderState = (Packet::SenderState*)this; diff --git a/src/mem/cache/miss/mshr_queue.cc b/src/mem/cache/miss/mshr_queue.cc index 97a56119f..bd9667529 100644 --- a/src/mem/cache/miss/mshr_queue.cc +++ b/src/mem/cache/miss/mshr_queue.cc @@ -128,6 +128,7 @@ MSHR* MSHRQueue::allocate(Packet * &pkt, int size) { Addr aligned_addr = pkt->getAddr() & ~((Addr)size - 1); + assert(!freeList.empty()); MSHR *mshr = freeList.front(); assert(mshr->getNumTargets() == 0); freeList.pop_front(); @@ -251,7 +252,7 @@ MSHRQueue::squash(int threadNum) Packet * target = mshr->getTarget(); mshr->popTarget(); - assert(target->req->getThreadNum() == threadNum); + assert(0/*target->req->getThreadNum()*/ == threadNum); target = NULL; } assert(!mshr->hasTargets()); diff --git a/src/mem/packet.hh b/src/mem/packet.hh index c7d28010c..be9bf5f57 100644 --- a/src/mem/packet.hh +++ b/src/mem/packet.hh @@ -312,7 +312,7 @@ class Packet * for returning as a response to that request. Used for timing * accesses only. For atomic and functional accesses, the * request packet is always implicitly passed back *without* - * modifying the command or destination fields, so this function + * modifying the destination fields, so this function * should not be called. */ void makeTimingResponse() { assert(needsResponse()); @@ -325,6 +325,18 @@ class Packet srcValid = false; } + /** Take a request packet and modify it in place to be suitable + * for returning as a response to that request. + */ + void makeAtomicResponse() { + assert(needsResponse()); + assert(isRequest()); + int icmd = (int)cmd; + icmd &= ~(IsRequest); + icmd |= IsResponse; + cmd = (Command)icmd; + } + /** Take a request packet that has been returned as NACKED and modify it so * that it can be sent out again. Only packets that need a response can be * NACKED, so verify that that is true. */ diff --git a/tests/configs/o3-timing-mp.py b/tests/configs/o3-timing-mp.py new file mode 100644 index 000000000..881c23156 --- /dev/null +++ b/tests/configs/o3-timing-mp.py @@ -0,0 +1,90 @@ +# Copyright (c) 2006 The Regents of The University of Michigan +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are +# met: redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer; +# redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution; +# neither the name of the copyright holders nor the names of its +# contributors may be used to endorse or promote products derived from +# this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +# +# Authors: Ron Dreslinski + +import m5 +from m5.objects import * +m5.AddToPath('../configs/common') +from FullO3Config import * + +# -------------------- +# Base L1 Cache +# ==================== + +class L1(BaseCache): + latency = 1 + block_size = 64 + mshrs = 4 + tgts_per_mshr = 8 + protocol = CoherenceProtocol(protocol='moesi') + +# ---------------------- +# Base L2 Cache +# ---------------------- + +class L2(BaseCache): + block_size = 64 + latency = 100 + mshrs = 92 + tgts_per_mshr = 16 + write_buffers = 8 + +nb_cores = 4 +cpus = [ DetailedO3CPU() for i in xrange(nb_cores) ] + +# system simulated +system = System(cpu = cpus, physmem = PhysicalMemory(), membus = +Bus()) + +# l2cache & bus +system.toL2Bus = Bus() +system.l2c = L2(size='4MB', assoc=8) +system.l2c.cpu_side = system.toL2Bus.port + +# connect l2c to membus +system.l2c.mem_side = system.membus.port + +# add L1 caches +for cpu in cpus: + cpu.addPrivateSplitL1Caches(L1(size = '32kB', assoc = 1), + L1(size = '32kB', assoc = 4)) + cpu.mem = cpu.dcache + # connect cpu level-1 caches to shared level-2 cache + cpu.connectMemPorts(system.toL2Bus) + +# connect memory to membus +system.physmem.port = system.membus.port + + +# ----------------------- +# run simulation +# ----------------------- + +root = Root( system = system ) +root.system.mem_mode = 'timing' +root.trace.flags="Bus Cache" +#root.trace.flags = "BusAddrRanges" diff --git a/tests/configs/simple-atomic-mp.py b/tests/configs/simple-atomic-mp.py new file mode 100644 index 000000000..cc1a36dda --- /dev/null +++ b/tests/configs/simple-atomic-mp.py @@ -0,0 +1,86 @@ +# Copyright (c) 2006 The Regents of The University of Michigan +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are +# met: redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer; +# redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution; +# neither the name of the copyright holders nor the names of its +# contributors may be used to endorse or promote products derived from +# this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +# +# Authors: Ron Dreslinski + +import m5 +from m5.objects import * + +# -------------------- +# Base L1 Cache +# ==================== + +class L1(BaseCache): + latency = 1 + block_size = 64 + mshrs = 4 + tgts_per_mshr = 8 + protocol = CoherenceProtocol(protocol='moesi') + +# ---------------------- +# Base L2 Cache +# ---------------------- + +class L2(BaseCache): + block_size = 64 + latency = 100 + mshrs = 92 + tgts_per_mshr = 16 + write_buffers = 8 + +nb_cores = 4 +cpus = [ AtomicSimpleCPU() for i in xrange(nb_cores) ] + +# system simulated +system = System(cpu = cpus, physmem = PhysicalMemory(), membus = +Bus()) + +# l2cache & bus +system.toL2Bus = Bus() +system.l2c = L2(size='4MB', assoc=8) +system.l2c.cpu_side = system.toL2Bus.port + +# connect l2c to membus +system.l2c.mem_side = system.membus.port + +# add L1 caches +for cpu in cpus: + cpu.addPrivateSplitL1Caches(L1(size = '32kB', assoc = 1), + L1(size = '32kB', assoc = 4)) + cpu.mem = cpu.dcache + # connect cpu level-1 caches to shared level-2 cache + cpu.connectMemPorts(system.toL2Bus) + +# connect memory to membus +system.physmem.port = system.membus.port + + +# ----------------------- +# run simulation +# ----------------------- + +root = Root( system = system ) +root.system.mem_mode = 'atomic' diff --git a/tests/configs/simple-timing-mp.py b/tests/configs/simple-timing-mp.py new file mode 100644 index 000000000..9fc5f3874 --- /dev/null +++ b/tests/configs/simple-timing-mp.py @@ -0,0 +1,86 @@ +# Copyright (c) 2006 The Regents of The University of Michigan +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions are +# met: redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer; +# redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution; +# neither the name of the copyright holders nor the names of its +# contributors may be used to endorse or promote products derived from +# this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +# +# Authors: Ron Dreslinski + +import m5 +from m5.objects import * + +# -------------------- +# Base L1 Cache +# ==================== + +class L1(BaseCache): + latency = 1 + block_size = 64 + mshrs = 4 + tgts_per_mshr = 8 + protocol = CoherenceProtocol(protocol='moesi') + +# ---------------------- +# Base L2 Cache +# ---------------------- + +class L2(BaseCache): + block_size = 64 + latency = 100 + mshrs = 92 + tgts_per_mshr = 16 + write_buffers = 8 + +nb_cores = 4 +cpus = [ TimingSimpleCPU() for i in xrange(nb_cores) ] + +# system simulated +system = System(cpu = cpus, physmem = PhysicalMemory(), membus = +Bus()) + +# l2cache & bus +system.toL2Bus = Bus() +system.l2c = L2(size='4MB', assoc=8) +system.l2c.cpu_side = system.toL2Bus.port + +# connect l2c to membus +system.l2c.mem_side = system.membus.port + +# add L1 caches +for cpu in cpus: + cpu.addPrivateSplitL1Caches(L1(size = '32kB', assoc = 1), + L1(size = '32kB', assoc = 4)) + cpu.mem = cpu.dcache + # connect cpu level-1 caches to shared level-2 cache + cpu.connectMemPorts(system.toL2Bus) + +# connect memory to membus +system.physmem.port = system.membus.port + + +# ----------------------- +# run simulation +# ----------------------- + +root = Root( system = system ) +root.system.mem_mode = 'timing' diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini index c3a59fbce..903794729 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini @@ -110,6 +110,7 @@ numROBEntries=192 numRobs=1 numThreads=1 predType=tournament +progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 renameToIEWDelay=2 @@ -389,11 +390,17 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/linux/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -409,6 +416,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.out b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.out index f491a3081..2a9a97255 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.out +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.out @@ -28,6 +28,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu.dcache] type=BaseCache @@ -208,6 +214,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 cachePorts=200 decodeToFetchDelay=1 renameToFetchDelay=1 @@ -358,6 +365,7 @@ bus_id=0 [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -401,3 +409,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt index 5d4f9235a..c2c9affca 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt @@ -2,39 +2,39 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. global.BPredUnit.BTBHits 542 # Number of BTB hits -global.BPredUnit.BTBLookups 1938 # Number of BTB lookups +global.BPredUnit.BTBLookups 1936 # Number of BTB lookups global.BPredUnit.RASInCorrect 48 # Number of incorrect RAS predictions. global.BPredUnit.condIncorrect 420 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 1304 # Number of conditional branches predicted -global.BPredUnit.lookups 2256 # Number of BP lookups +global.BPredUnit.condPredicted 1302 # Number of conditional branches predicted +global.BPredUnit.lookups 2254 # Number of BP lookups global.BPredUnit.usedRAS 291 # Number of times the RAS was used to get a target. -host_inst_rate 41797 # Simulator instruction rate (inst/s) -host_mem_usage 160344 # Number of bytes of host memory used -host_seconds 0.13 # Real time elapsed on the host -host_tick_rate 50948 # Simulator tick rate (ticks/s) +host_inst_rate 47059 # Simulator instruction rate (inst/s) +host_mem_usage 160380 # Number of bytes of host memory used +host_seconds 0.12 # Real time elapsed on the host +host_tick_rate 57322 # Simulator tick rate (ticks/s) memdepunit.memDep.conflictingLoads 12 # Number of conflicting loads. memdepunit.memDep.conflictingStores 259 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 2050 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 2049 # Number of loads inserted to the mem dependence unit. memdepunit.memDep.insertedStores 1221 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5623 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated -sim_ticks 6870 # Number of ticks simulated +sim_ticks 6868 # Number of ticks simulated system.cpu.commit.COM:branches 862 # Number of branches committed system.cpu.commit.COM:bw_lim_events 74 # number cycles where commit BW limit reached system.cpu.commit.COM:bw_limited 0 # number of insts not committed due to BW limits system.cpu.commit.COM:committed_per_cycle.start_dist # Number of insts commited each cycle -system.cpu.commit.COM:committed_per_cycle.samples 6116 +system.cpu.commit.COM:committed_per_cycle.samples 6115 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 3908 6389.80% - 1 1064 1739.70% - 2 389 636.04% - 3 210 343.36% - 4 153 250.16% - 5 93 152.06% - 6 76 124.26% - 7 149 243.62% - 8 74 120.99% + 0 3908 6390.84% + 1 1063 1738.35% + 2 389 636.14% + 3 210 343.42% + 4 152 248.57% + 5 94 153.72% + 6 76 124.28% + 7 149 243.66% + 8 74 121.01% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -46,67 +46,67 @@ system.cpu.commit.COM:swp_count 0 # Nu system.cpu.commit.branchMispredicts 337 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 5640 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 17 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 4350 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 4342 # The number of squashed insts skipped by commit system.cpu.committedInsts 5623 # Number of Instructions Simulated system.cpu.committedInsts_total 5623 # Number of Instructions Simulated -system.cpu.cpi 1.221768 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.221768 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 1538 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 3.072000 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2.240000 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 1413 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 384 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.081274 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 125 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 25 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 224 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.065020 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 100 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 821 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 2.467742 # average WriteReq miss latency +system.cpu.cpi 1.221412 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.221412 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 1536 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 3.038760 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2.235294 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 1407 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 392 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.083984 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 129 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 27 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 228 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.066406 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 102 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 812 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 2.564246 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2.140845 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 635 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits 633 # number of WriteReq hits system.cpu.dcache.WriteReq_miss_latency 459 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.226553 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 186 # number of WriteReq misses +system.cpu.dcache.WriteReq_miss_rate 0.220443 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 179 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_hits 108 # number of WriteReq MSHR hits system.cpu.dcache.WriteReq_mshr_miss_latency 152 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.086480 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.087438 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 71 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets 0.800000 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 11.505618 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 11.791908 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 5 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 4 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 2359 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 2.710611 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 2.198830 # average overall mshr miss latency -system.cpu.dcache.demand_hits 2048 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 843 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.131836 # miss rate for demand accesses -system.cpu.dcache.demand_misses 311 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 133 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 376 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.072488 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 171 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 2348 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 2.762987 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 2.196532 # average overall mshr miss latency +system.cpu.dcache.demand_hits 2040 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 851 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.131175 # miss rate for demand accesses +system.cpu.dcache.demand_misses 308 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 135 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 380 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.073680 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 173 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 2359 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 2.710611 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 2.198830 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 2348 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 2.762987 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 2.196532 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 2048 # number of overall hits -system.cpu.dcache.overall_miss_latency 843 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.131836 # miss rate for overall accesses -system.cpu.dcache.overall_misses 311 # number of overall misses -system.cpu.dcache.overall_mshr_hits 133 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 376 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.072488 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 171 # number of overall MSHR misses +system.cpu.dcache.overall_hits 2040 # number of overall hits +system.cpu.dcache.overall_miss_latency 851 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.131175 # miss rate for overall accesses +system.cpu.dcache.overall_misses 308 # number of overall misses +system.cpu.dcache.overall_mshr_hits 135 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 380 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.073680 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 173 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -119,43 +119,43 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.dcache.replacements 0 # number of replacements -system.cpu.dcache.sampled_refs 178 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 173 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 119.831029 # Cycle average of tags in use -system.cpu.dcache.total_refs 2048 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 114.960547 # Cycle average of tags in use +system.cpu.dcache.total_refs 2040 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.decode.DECODE:BlockedCycles 387 # Number of cycles decode is blocked system.cpu.decode.DECODE:BranchMispred 93 # Number of times decode detected a branch misprediction system.cpu.decode.DECODE:BranchResolved 185 # Number of times decode resolved a branch system.cpu.decode.DECODE:DecodedInsts 12349 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 3542 # Number of cycles decode is idle +system.cpu.decode.DECODE:IdleCycles 3541 # Number of cycles decode is idle system.cpu.decode.DECODE:RunCycles 2158 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 754 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashCycles 753 # Number of cycles decode is squashing system.cpu.decode.DECODE:SquashedInsts 286 # Number of squashed instructions handled by decode system.cpu.decode.DECODE:UnblockCycles 30 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 2256 # Number of branches that fetch encountered +system.cpu.fetch.Branches 2254 # Number of branches that fetch encountered system.cpu.fetch.CacheLines 1582 # Number of cache lines fetched -system.cpu.fetch.Cycles 3905 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.Cycles 3904 # Number of cycles fetch has run and was not squashing or blocked system.cpu.fetch.IcacheSquashes 148 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 13707 # Number of instructions fetch has processed +system.cpu.fetch.Insts 13699 # Number of instructions fetch has processed system.cpu.fetch.SquashCycles 456 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.328336 # Number of branch fetches per cycle +system.cpu.fetch.branchRate 0.328141 # Number of branch fetches per cycle system.cpu.fetch.icacheStallCycles 1582 # Number of cycles fetch is stalled on an Icache miss system.cpu.fetch.predictedBranches 833 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.994906 # Number of inst fetches per cycle +system.cpu.fetch.rate 1.994322 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 6871 +system.cpu.fetch.rateDist.samples 6869 system.cpu.fetch.rateDist.min_value 0 - 0 4549 6620.58% - 1 174 253.24% - 2 186 270.70% - 3 157 228.50% - 4 211 307.09% - 5 153 222.68% - 6 171 248.87% - 7 105 152.82% - 8 1165 1695.53% + 0 4548 6621.05% + 1 174 253.31% + 2 186 270.78% + 3 157 228.56% + 4 211 307.18% + 5 153 222.74% + 6 171 248.94% + 7 105 152.86% + 8 1164 1694.57% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist @@ -170,8 +170,8 @@ system.cpu.icache.ReadReq_mshr_hits 6 # nu system.cpu.icache.ReadReq_mshr_miss_latency 641 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.202908 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 321 # number of ReadReq MSHR misses -system.cpu.icache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked -system.cpu.icache.avg_blocked_cycles_no_targets no value # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_refs 3.909657 # Average number of references to valid blocks. system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked @@ -218,38 +218,38 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 321 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 176.393247 # Cycle average of tags in use +system.cpu.icache.tagsinuse 176.439074 # Cycle average of tags in use system.cpu.icache.total_refs 1255 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.iew.EXEC:branches 1206 # Number of branches executed -system.cpu.iew.EXEC:insts 7969 # Number of executed instructions -system.cpu.iew.EXEC:loads 1610 # Number of load instructions executed system.cpu.iew.EXEC:nop 37 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.159802 # Inst execution rate -system.cpu.iew.EXEC:refs 2599 # number of memory reference insts executed -system.cpu.iew.EXEC:squashedInsts 419 # Number of squashed instructions skipped in execute -system.cpu.iew.EXEC:stores 989 # Number of stores executed +system.cpu.iew.EXEC:rate 1.157374 # Inst execution rate +system.cpu.iew.EXEC:refs 2595 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 985 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 5438 # num instructions consuming a value -system.cpu.iew.WB:count 7722 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.744575 # average fanout of values written-back +system.cpu.iew.WB:consumers 5409 # num instructions consuming a value +system.cpu.iew.WB:count 7670 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.744130 # average fanout of values written-back system.cpu.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.iew.WB:producers 4049 # num instructions producing a value -system.cpu.iew.WB:rate 1.123854 # insts written-back per cycle -system.cpu.iew.WB:sent 7762 # cumulative count of insts sent to commit +system.cpu.iew.WB:producers 4025 # num instructions producing a value +system.cpu.iew.WB:rate 1.116611 # insts written-back per cycle +system.cpu.iew.WB:sent 7743 # cumulative count of insts sent to commit system.cpu.iew.branchMispredicts 393 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 4 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 2050 # Number of dispatched load instructions +system.cpu.iew.iewDispLoadInsts 2049 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 21 # Number of dispatched non-speculative instructions system.cpu.iew.iewDispSquashedInsts 272 # Number of squashed instructions skipped by dispatch system.cpu.iew.iewDispStoreInsts 1221 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 9990 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispatchedInsts 9982 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 1610 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 409 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 7950 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 754 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 753 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking system.cpu.iew.lsq.thread.0.blockedLoads 1 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread.0.cacheBlocked 5 # Number of times an access to memory failed due to the cache being blocked @@ -257,1586 +257,19 @@ system.cpu.iew.lsq.thread.0.forwLoads 55 # Nu system.cpu.iew.lsq.thread.0.ignoredResponses 5 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu.iew.lsq.thread.0.memOrderViolation 41 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 1 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 1071 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedLoads 1070 # Number of loads squashed system.cpu.iew.lsq.thread.0.squashedStores 409 # Number of stores squashed system.cpu.iew.memOrderViolationEvents 41 # Number of memory order violations system.cpu.iew.predictedNotTakenIncorrect 296 # Number of branches that were predicted not taken incorrectly system.cpu.iew.predictedTakenIncorrect 97 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.818486 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.818486 # IPC: Total IPC of All Threads -system.cpu.iq.IQ:residence:(null).start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:(null).samples 0 -system.cpu.iq.IQ:residence:(null).min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:(null).max_value 0 -system.cpu.iq.IQ:residence:(null).end_dist - -system.cpu.iq.IQ:residence:IntAlu.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntAlu.samples 0 -system.cpu.iq.IQ:residence:IntAlu.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntAlu.max_value 0 -system.cpu.iq.IQ:residence:IntAlu.end_dist - -system.cpu.iq.IQ:residence:IntMult.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntMult.samples 0 -system.cpu.iq.IQ:residence:IntMult.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntMult.max_value 0 -system.cpu.iq.IQ:residence:IntMult.end_dist - -system.cpu.iq.IQ:residence:IntDiv.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntDiv.samples 0 -system.cpu.iq.IQ:residence:IntDiv.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntDiv.max_value 0 -system.cpu.iq.IQ:residence:IntDiv.end_dist - -system.cpu.iq.IQ:residence:FloatAdd.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatAdd.samples 0 -system.cpu.iq.IQ:residence:FloatAdd.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatAdd.max_value 0 -system.cpu.iq.IQ:residence:FloatAdd.end_dist - -system.cpu.iq.IQ:residence:FloatCmp.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatCmp.samples 0 -system.cpu.iq.IQ:residence:FloatCmp.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatCmp.max_value 0 -system.cpu.iq.IQ:residence:FloatCmp.end_dist - -system.cpu.iq.IQ:residence:FloatCvt.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatCvt.samples 0 -system.cpu.iq.IQ:residence:FloatCvt.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatCvt.max_value 0 -system.cpu.iq.IQ:residence:FloatCvt.end_dist - -system.cpu.iq.IQ:residence:FloatMult.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatMult.samples 0 -system.cpu.iq.IQ:residence:FloatMult.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatMult.max_value 0 -system.cpu.iq.IQ:residence:FloatMult.end_dist - -system.cpu.iq.IQ:residence:FloatDiv.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatDiv.samples 0 -system.cpu.iq.IQ:residence:FloatDiv.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatDiv.max_value 0 -system.cpu.iq.IQ:residence:FloatDiv.end_dist - -system.cpu.iq.IQ:residence:FloatSqrt.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatSqrt.samples 0 -system.cpu.iq.IQ:residence:FloatSqrt.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatSqrt.max_value 0 -system.cpu.iq.IQ:residence:FloatSqrt.end_dist - -system.cpu.iq.IQ:residence:MemRead.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:MemRead.samples 0 -system.cpu.iq.IQ:residence:MemRead.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:MemRead.max_value 0 -system.cpu.iq.IQ:residence:MemRead.end_dist - -system.cpu.iq.IQ:residence:MemWrite.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:MemWrite.samples 0 -system.cpu.iq.IQ:residence:MemWrite.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:MemWrite.max_value 0 -system.cpu.iq.IQ:residence:MemWrite.end_dist - -system.cpu.iq.IQ:residence:IprAccess.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IprAccess.samples 0 -system.cpu.iq.IQ:residence:IprAccess.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IprAccess.max_value 0 -system.cpu.iq.IQ:residence:IprAccess.end_dist - -system.cpu.iq.IQ:residence:InstPrefetch.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:InstPrefetch.samples 0 -system.cpu.iq.IQ:residence:InstPrefetch.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:InstPrefetch.max_value 0 -system.cpu.iq.IQ:residence:InstPrefetch.end_dist - -system.cpu.iq.ISSUE:(null)_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:(null)_delay.samples 0 -system.cpu.iq.ISSUE:(null)_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:(null)_delay.max_value 0 -system.cpu.iq.ISSUE:(null)_delay.end_dist - -system.cpu.iq.ISSUE:IntAlu_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntAlu_delay.samples 0 -system.cpu.iq.ISSUE:IntAlu_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntAlu_delay.max_value 0 -system.cpu.iq.ISSUE:IntAlu_delay.end_dist - -system.cpu.iq.ISSUE:IntMult_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntMult_delay.samples 0 -system.cpu.iq.ISSUE:IntMult_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntMult_delay.max_value 0 -system.cpu.iq.ISSUE:IntMult_delay.end_dist - -system.cpu.iq.ISSUE:IntDiv_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntDiv_delay.samples 0 -system.cpu.iq.ISSUE:IntDiv_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntDiv_delay.max_value 0 -system.cpu.iq.ISSUE:IntDiv_delay.end_dist - -system.cpu.iq.ISSUE:FloatAdd_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatAdd_delay.samples 0 -system.cpu.iq.ISSUE:FloatAdd_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatAdd_delay.max_value 0 -system.cpu.iq.ISSUE:FloatAdd_delay.end_dist - -system.cpu.iq.ISSUE:FloatCmp_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatCmp_delay.samples 0 -system.cpu.iq.ISSUE:FloatCmp_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatCmp_delay.max_value 0 -system.cpu.iq.ISSUE:FloatCmp_delay.end_dist - -system.cpu.iq.ISSUE:FloatCvt_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatCvt_delay.samples 0 -system.cpu.iq.ISSUE:FloatCvt_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatCvt_delay.max_value 0 -system.cpu.iq.ISSUE:FloatCvt_delay.end_dist - -system.cpu.iq.ISSUE:FloatMult_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatMult_delay.samples 0 -system.cpu.iq.ISSUE:FloatMult_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatMult_delay.max_value 0 -system.cpu.iq.ISSUE:FloatMult_delay.end_dist - -system.cpu.iq.ISSUE:FloatDiv_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatDiv_delay.samples 0 -system.cpu.iq.ISSUE:FloatDiv_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatDiv_delay.max_value 0 -system.cpu.iq.ISSUE:FloatDiv_delay.end_dist - -system.cpu.iq.ISSUE:FloatSqrt_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatSqrt_delay.samples 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.max_value 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.end_dist - -system.cpu.iq.ISSUE:MemRead_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:MemRead_delay.samples 0 -system.cpu.iq.ISSUE:MemRead_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:MemRead_delay.max_value 0 -system.cpu.iq.ISSUE:MemRead_delay.end_dist - -system.cpu.iq.ISSUE:MemWrite_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:MemWrite_delay.samples 0 -system.cpu.iq.ISSUE:MemWrite_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:MemWrite_delay.max_value 0 -system.cpu.iq.ISSUE:MemWrite_delay.end_dist - -system.cpu.iq.ISSUE:IprAccess_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IprAccess_delay.samples 0 -system.cpu.iq.ISSUE:IprAccess_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IprAccess_delay.max_value 0 -system.cpu.iq.ISSUE:IprAccess_delay.end_dist - -system.cpu.iq.ISSUE:InstPrefetch_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:InstPrefetch_delay.samples 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.max_value 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.end_dist - -system.cpu.iq.ISSUE:FU_type_0 8388 # Type of FU issued +system.cpu.ipc 0.818725 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.818725 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8359 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 2 0.02% # Type of FU issued - IntAlu 5594 66.69% # Type of FU issued + IntAlu 5573 66.67% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 2 0.02% # Type of FU issued @@ -1845,13 +278,13 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 1757 20.95% # Type of FU issued - MemWrite 1032 12.30% # Type of FU issued + MemRead 1757 21.02% # Type of FU issued + MemWrite 1024 12.25% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.end_dist system.cpu.iq.ISSUE:fu_busy_cnt 115 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.013710 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate 0.013758 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available IntAlu 1 0.87% # attempts to use FU when none available @@ -1869,72 +302,74 @@ system.cpu.iq.ISSUE:fu_full.start_dist InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 6871 +system.cpu.iq.ISSUE:issued_per_cycle.samples 6869 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 3753 5462.09% - 1 894 1301.12% - 2 723 1052.25% - 3 614 893.61% - 4 451 656.38% - 5 279 406.05% - 6 104 151.36% - 7 41 59.67% - 8 12 17.46% + 0 3761 5475.32% + 1 891 1297.13% + 2 720 1048.19% + 3 617 898.24% + 4 445 647.84% + 5 278 404.72% + 6 104 151.40% + 7 41 59.69% + 8 12 17.47% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.220783 # Inst issue rate -system.cpu.iq.iqInstsAdded 9932 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 8388 # Number of instructions issued +system.cpu.iq.ISSUE:rate 1.216917 # Inst issue rate +system.cpu.iq.iqInstsAdded 9924 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 8359 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 21 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 3990 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsExamined 3985 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedInstsIssued 21 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 4 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 2486 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 499 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 2.042254 # average ReadReq miss latency +system.cpu.iq.iqSquashedOperandsExamined 2568 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 494 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2.071138 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency system.cpu.l2cache.ReadReq_hits 2 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 1015 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.995992 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 497 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 490 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.981964 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 490 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_miss_latency 1019 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.995951 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 492 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 492 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.995951 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 492 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReq_accesses 2 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_hits 2 # number of WriteReq hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.004024 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.008130 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 499 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 2.042254 # average overall miss latency +system.cpu.l2cache.demand_accesses 496 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2.071138 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 2 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 1015 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.995992 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 497 # number of demand (read+write) misses +system.cpu.l2cache.demand_hits 4 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1019 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.991935 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 492 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 490 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.981964 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 490 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 492 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.991935 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 492 # number of demand (read+write) MSHR misses system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.overall_accesses 499 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 2.042254 # average overall miss latency +system.cpu.l2cache.overall_accesses 496 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2.071138 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 1 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 2 # number of overall hits -system.cpu.l2cache.overall_miss_latency 1015 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.995992 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 497 # number of overall misses +system.cpu.l2cache.overall_hits 4 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1019 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.991935 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 492 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 490 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.981964 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 490 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 492 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.991935 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 492 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -1947,22 +382,22 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 497 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 492 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 295.773395 # Cycle average of tags in use -system.cpu.l2cache.total_refs 2 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 290.948901 # Cycle average of tags in use +system.cpu.l2cache.total_refs 4 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks -system.cpu.numCycles 6871 # number of cpu cycles simulated +system.cpu.numCycles 6869 # number of cpu cycles simulated system.cpu.rename.RENAME:BlockCycles 4 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 4051 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 3758 # Number of cycles rename is idle +system.cpu.rename.RENAME:IdleCycles 3757 # Number of cycles rename is idle system.cpu.rename.RENAME:LSQFullEvents 62 # Number of times rename has blocked due to LSQ full system.cpu.rename.RENAME:RenameLookups 14786 # Number of register rename lookups that rename has made system.cpu.rename.RENAME:RenamedInsts 11555 # Number of instructions processed by rename system.cpu.rename.RENAME:RenamedOperands 8634 # Number of destination operands rename has renamed system.cpu.rename.RENAME:RunCycles 1975 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 754 # Number of cycles rename is squashing +system.cpu.rename.RENAME:SquashCycles 753 # Number of cycles rename is squashing system.cpu.rename.RENAME:UnblockCycles 111 # Number of cycles rename is unblocking system.cpu.rename.RENAME:UndoneMaps 4583 # Number of HB maps that are undone due to squashing system.cpu.rename.RENAME:serializeStallCycles 269 # count of cycles rename stalled for serializing inst diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout index fbb329a2f..14ef519e9 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:12 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:34 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/linux/o3-timing tests/run.py quick/00.hello/alpha/linux/o3-timing -Exiting @ tick 6870 because target called exit() +Exiting @ tick 6868 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini index f84372165..f7e73950d 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.physmem +progress_interval=0 simulate_stalls=false system=system width=1 @@ -74,11 +75,17 @@ icache_port=system.membus.port[1] [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/linux/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -94,6 +101,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.out b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.out index a3621a08a..198d7df5e 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.out +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.out @@ -28,6 +28,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu] type=AtomicSimpleCPU @@ -35,6 +41,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.physmem system=system workload=system.cpu.workload @@ -48,6 +55,7 @@ simulate_stalls=false [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -91,3 +99,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout index 17eea9aed..e26480539 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:14 2006 +M5 compiled Oct 7 2006 11:12:49 +M5 started Sat Oct 7 11:13:02 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/linux/simple-atomic tests/run.py quick/00.hello/alpha/linux/simple-atomic Exiting @ tick 5641 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini index 80d2a27e1..cefcf7f11 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.cpu.dcache +progress_interval=0 system=system workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side @@ -197,11 +198,17 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/linux/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -217,6 +224,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.out b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.out index 09d8f0c22..1ed18ff71 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.out +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.out @@ -67,6 +67,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu] type=TimingSimpleCPU @@ -74,6 +80,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.cpu.dcache system=system workload=system.cpu.workload @@ -169,6 +176,7 @@ hit_latency=1 [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -212,3 +220,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt index fe2cd43a5..97d39456e 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt @@ -1,67 +1,67 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 113478 # Simulator instruction rate (inst/s) -host_mem_usage 159608 # Number of bytes of host memory used -host_seconds 0.05 # Real time elapsed on the host -host_tick_rate 165749 # Simulator tick rate (ticks/s) +host_inst_rate 286207 # Simulator instruction rate (inst/s) +host_mem_usage 159648 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 413300 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5642 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated -sim_ticks 8312 # Number of ticks simulated -system.cpu.dcache.ReadReq_accesses 981 # number of ReadReq accesses(hits+misses) +sim_ticks 8316 # Number of ticks simulated +system.cpu.dcache.ReadReq_accesses 979 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 3 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 891 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 270 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.091743 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 90 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_miss_latency 180 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.091743 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 90 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 821 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 2.737500 # average WriteReq miss latency +system.cpu.dcache.ReadReq_hits 887 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 276 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.093973 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 92 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_miss_latency 184 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.093973 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 92 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 812 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 3 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 741 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits 739 # number of WriteReq hits system.cpu.dcache.WriteReq_miss_latency 219 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.097442 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 80 # number of WriteReq misses +system.cpu.dcache.WriteReq_miss_rate 0.089901 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 73 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_miss_latency 146 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.088916 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.089901 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 73 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 9.600000 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 9.854545 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 1802 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 2.876471 # average overall miss latency +system.cpu.dcache.demand_accesses 1791 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 2 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1632 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 489 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.094340 # miss rate for demand accesses -system.cpu.dcache.demand_misses 170 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 1626 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 495 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.092127 # miss rate for demand accesses +system.cpu.dcache.demand_misses 165 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 326 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.090455 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 163 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 330 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.092127 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 165 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 1802 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 2.876471 # average overall miss latency +system.cpu.dcache.overall_accesses 1791 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 2 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 1632 # number of overall hits -system.cpu.dcache.overall_miss_latency 489 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.094340 # miss rate for overall accesses -system.cpu.dcache.overall_misses 170 # number of overall misses +system.cpu.dcache.overall_hits 1626 # number of overall hits +system.cpu.dcache.overall_miss_latency 495 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.092127 # miss rate for overall accesses +system.cpu.dcache.overall_misses 165 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 326 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.090455 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 163 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 330 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.092127 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 165 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -74,10 +74,10 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.dcache.replacements 0 # number of replacements -system.cpu.dcache.sampled_refs 170 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 165 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 112.055094 # Cycle average of tags in use -system.cpu.dcache.total_refs 1632 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 107.125526 # Cycle average of tags in use +system.cpu.dcache.total_refs 1626 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 5643 # number of ReadReq accesses(hits+misses) @@ -138,55 +138,57 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 277 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 133.267292 # Cycle average of tags in use +system.cpu.icache.tagsinuse 133.213539 # Cycle average of tags in use system.cpu.icache.total_refs 5366 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 447 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 1.968610 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_accesses 442 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency system.cpu.l2cache.ReadReq_hits 1 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 878 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.997763 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 446 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 439 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.982103 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 439 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_miss_latency 882 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.997738 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 441 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 441 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.997738 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 441 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReq_accesses 2 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_hits 2 # number of WriteReq hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.002242 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.006803 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 447 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 1.968610 # average overall miss latency +system.cpu.l2cache.demand_accesses 444 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 1 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 878 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.997763 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 446 # number of demand (read+write) misses +system.cpu.l2cache.demand_hits 3 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 882 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.993243 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 441 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 439 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.982103 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 439 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 441 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.993243 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 441 # number of demand (read+write) MSHR misses system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.overall_accesses 447 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 1.968610 # average overall miss latency +system.cpu.l2cache.overall_accesses 444 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no value # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 1 # number of overall hits -system.cpu.l2cache.overall_miss_latency 878 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.997763 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 446 # number of overall misses +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu.l2cache.overall_hits 3 # number of overall hits +system.cpu.l2cache.overall_miss_latency 882 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.993243 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 441 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 439 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.982103 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 439 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 441 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.993243 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 441 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -199,10 +201,10 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 446 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 441 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 245.259112 # Cycle average of tags in use -system.cpu.l2cache.total_refs 1 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 240.276061 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout index 7104aa0ce..a9c37a14d 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:15 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:38 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/linux/simple-timing tests/run.py quick/00.hello/alpha/linux/simple-timing -Exiting @ tick 8312 because target called exit() +Exiting @ tick 8316 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini index 790ae6ab3..45904ca08 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini @@ -110,6 +110,7 @@ numROBEntries=192 numRobs=1 numThreads=1 predType=tournament +progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 renameToIEWDelay=2 @@ -389,11 +390,17 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/tru64/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -409,6 +416,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.out b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.out index 474ea3523..c5cec4f22 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.out +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.out @@ -28,6 +28,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu.dcache] type=BaseCache @@ -208,6 +214,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 cachePorts=200 decodeToFetchDelay=1 renameToFetchDelay=1 @@ -358,6 +365,7 @@ bus_id=0 [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -401,3 +409,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt index db582e731..53d94a43f 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt @@ -8,10 +8,10 @@ global.BPredUnit.condIncorrect 222 # Nu global.BPredUnit.condPredicted 441 # Number of conditional branches predicted global.BPredUnit.lookups 888 # Number of BP lookups global.BPredUnit.usedRAS 160 # Number of times the RAS was used to get a target. -host_inst_rate 26468 # Simulator instruction rate (inst/s) -host_mem_usage 159864 # Number of bytes of host memory used -host_seconds 0.09 # Real time elapsed on the host -host_tick_rate 31894 # Simulator tick rate (ticks/s) +host_inst_rate 45832 # Simulator instruction rate (inst/s) +host_mem_usage 159900 # Number of bytes of host memory used +host_seconds 0.05 # Real time elapsed on the host +host_tick_rate 55090 # Simulator tick rate (ticks/s) memdepunit.memDep.conflictingLoads 9 # Number of conflicting loads. memdepunit.memDep.conflictingStores 7 # Number of conflicting stores. memdepunit.memDep.insertedLoads 675 # Number of loads inserted to the mem dependence unit. @@ -51,16 +51,16 @@ system.cpu.committedInsts 2387 # Nu system.cpu.committedInsts_total 2387 # Number of Instructions Simulated system.cpu.cpi 1.209049 # CPI: Cycles Per Instruction system.cpu.cpi_total 1.209049 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 535 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses 534 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 3 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 470 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits 469 # number of ReadReq hits system.cpu.dcache.ReadReq_miss_latency 195 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.121495 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_miss_rate 0.121723 # miss rate for ReadReq accesses system.cpu.dcache.ReadReq_misses 65 # number of ReadReq misses system.cpu.dcache.ReadReq_mshr_hits 4 # number of ReadReq MSHR hits system.cpu.dcache.ReadReq_mshr_miss_latency 122 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.114019 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate 0.114232 # mshr miss rate for ReadReq accesses system.cpu.dcache.ReadReq_mshr_misses 61 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 294 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 3.017241 # average WriteReq miss latency @@ -75,37 +75,37 @@ system.cpu.dcache.WriteReq_mshr_miss_rate 0.081633 # m system.cpu.dcache.WriteReq_mshr_misses 24 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets 1.500000 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 8.305882 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 8.294118 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 2 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 3 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 829 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses 828 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency 3.008130 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 2.058824 # average overall mshr miss latency -system.cpu.dcache.demand_hits 706 # number of demand (read+write) hits +system.cpu.dcache.demand_hits 705 # number of demand (read+write) hits system.cpu.dcache.demand_miss_latency 370 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.148372 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate 0.148551 # miss rate for demand accesses system.cpu.dcache.demand_misses 123 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 38 # number of demand (read+write) MSHR hits system.cpu.dcache.demand_mshr_miss_latency 175 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.102533 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate 0.102657 # mshr miss rate for demand accesses system.cpu.dcache.demand_mshr_misses 85 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 829 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses 828 # number of overall (read+write) accesses system.cpu.dcache.overall_avg_miss_latency 3.008130 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 2.058824 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 706 # number of overall hits +system.cpu.dcache.overall_hits 705 # number of overall hits system.cpu.dcache.overall_miss_latency 370 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.148372 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate 0.148551 # miss rate for overall accesses system.cpu.dcache.overall_misses 123 # number of overall misses system.cpu.dcache.overall_mshr_hits 38 # number of overall MSHR hits system.cpu.dcache.overall_mshr_miss_latency 175 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.102533 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate 0.102657 # mshr miss rate for overall accesses system.cpu.dcache.overall_mshr_misses 85 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -122,7 +122,7 @@ system.cpu.dcache.replacements 0 # nu system.cpu.dcache.sampled_refs 85 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.tagsinuse 54.161413 # Cycle average of tags in use -system.cpu.dcache.total_refs 706 # Total number of references to valid blocks. +system.cpu.dcache.total_refs 705 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.decode.DECODE:BlockedCycles 82 # Number of cycles decode is blocked @@ -222,30 +222,30 @@ system.cpu.icache.tagsinuse 115.538968 # Cy system.cpu.icache.total_refs 550 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.iew.EXEC:branches 533 # Number of branches executed -system.cpu.iew.EXEC:insts 3123 # Number of executed instructions -system.cpu.iew.EXEC:loads 578 # Number of load instructions executed +system.cpu.iew.EXEC:branches 532 # Number of branches executed system.cpu.iew.EXEC:nop 247 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.081746 # Inst execution rate -system.cpu.iew.EXEC:refs 914 # number of memory reference insts executed -system.cpu.iew.EXEC:squashedInsts 148 # Number of squashed instructions skipped in execute +system.cpu.iew.EXEC:rate 1.078628 # Inst execution rate +system.cpu.iew.EXEC:refs 910 # number of memory reference insts executed system.cpu.iew.EXEC:stores 336 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1801 # num instructions consuming a value -system.cpu.iew.WB:count 3070 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.791227 # average fanout of values written-back +system.cpu.iew.WB:consumers 1788 # num instructions consuming a value +system.cpu.iew.WB:count 3053 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.790828 # average fanout of values written-back system.cpu.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.iew.WB:producers 1425 # num instructions producing a value -system.cpu.iew.WB:rate 1.063388 # insts written-back per cycle -system.cpu.iew.WB:sent 3076 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 159 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 1414 # num instructions producing a value +system.cpu.iew.WB:rate 1.057499 # insts written-back per cycle +system.cpu.iew.WB:sent 3067 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 158 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 0 # Number of cycles IEW is blocking system.cpu.iew.iewDispLoadInsts 675 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 7 # Number of dispatched non-speculative instructions system.cpu.iew.iewDispSquashedInsts 127 # Number of squashed instructions skipped by dispatch system.cpu.iew.iewDispStoreInsts 369 # Number of dispatched store instructions system.cpu.iew.iewDispatchedInsts 3835 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 574 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 143 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 3114 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall @@ -257,1586 +257,19 @@ system.cpu.iew.lsq.thread.0.forwLoads 30 # Nu system.cpu.iew.lsq.thread.0.ignoredResponses 3 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu.iew.lsq.thread.0.memOrderViolation 11 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled system.cpu.iew.lsq.thread.0.squashedLoads 260 # Number of loads squashed system.cpu.iew.lsq.thread.0.squashedStores 75 # Number of stores squashed system.cpu.iew.memOrderViolationEvents 11 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 106 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 105 # Number of branches that were predicted not taken incorrectly system.cpu.iew.predictedTakenIncorrect 53 # Number of branches that were predicted taken incorrectly system.cpu.ipc 0.827096 # IPC: Instructions Per Cycle system.cpu.ipc_total 0.827096 # IPC: Total IPC of All Threads -system.cpu.iq.IQ:residence:(null).start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:(null).samples 0 -system.cpu.iq.IQ:residence:(null).min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:(null).max_value 0 -system.cpu.iq.IQ:residence:(null).end_dist - -system.cpu.iq.IQ:residence:IntAlu.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntAlu.samples 0 -system.cpu.iq.IQ:residence:IntAlu.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntAlu.max_value 0 -system.cpu.iq.IQ:residence:IntAlu.end_dist - -system.cpu.iq.IQ:residence:IntMult.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntMult.samples 0 -system.cpu.iq.IQ:residence:IntMult.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntMult.max_value 0 -system.cpu.iq.IQ:residence:IntMult.end_dist - -system.cpu.iq.IQ:residence:IntDiv.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IntDiv.samples 0 -system.cpu.iq.IQ:residence:IntDiv.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IntDiv.max_value 0 -system.cpu.iq.IQ:residence:IntDiv.end_dist - -system.cpu.iq.IQ:residence:FloatAdd.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatAdd.samples 0 -system.cpu.iq.IQ:residence:FloatAdd.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatAdd.max_value 0 -system.cpu.iq.IQ:residence:FloatAdd.end_dist - -system.cpu.iq.IQ:residence:FloatCmp.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatCmp.samples 0 -system.cpu.iq.IQ:residence:FloatCmp.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatCmp.max_value 0 -system.cpu.iq.IQ:residence:FloatCmp.end_dist - -system.cpu.iq.IQ:residence:FloatCvt.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatCvt.samples 0 -system.cpu.iq.IQ:residence:FloatCvt.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatCvt.max_value 0 -system.cpu.iq.IQ:residence:FloatCvt.end_dist - -system.cpu.iq.IQ:residence:FloatMult.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatMult.samples 0 -system.cpu.iq.IQ:residence:FloatMult.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatMult.max_value 0 -system.cpu.iq.IQ:residence:FloatMult.end_dist - -system.cpu.iq.IQ:residence:FloatDiv.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatDiv.samples 0 -system.cpu.iq.IQ:residence:FloatDiv.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatDiv.max_value 0 -system.cpu.iq.IQ:residence:FloatDiv.end_dist - -system.cpu.iq.IQ:residence:FloatSqrt.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:FloatSqrt.samples 0 -system.cpu.iq.IQ:residence:FloatSqrt.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:FloatSqrt.max_value 0 -system.cpu.iq.IQ:residence:FloatSqrt.end_dist - -system.cpu.iq.IQ:residence:MemRead.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:MemRead.samples 0 -system.cpu.iq.IQ:residence:MemRead.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:MemRead.max_value 0 -system.cpu.iq.IQ:residence:MemRead.end_dist - -system.cpu.iq.IQ:residence:MemWrite.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:MemWrite.samples 0 -system.cpu.iq.IQ:residence:MemWrite.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:MemWrite.max_value 0 -system.cpu.iq.IQ:residence:MemWrite.end_dist - -system.cpu.iq.IQ:residence:IprAccess.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:IprAccess.samples 0 -system.cpu.iq.IQ:residence:IprAccess.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:IprAccess.max_value 0 -system.cpu.iq.IQ:residence:IprAccess.end_dist - -system.cpu.iq.IQ:residence:InstPrefetch.start_dist # cycles from dispatch to issue -system.cpu.iq.IQ:residence:InstPrefetch.samples 0 -system.cpu.iq.IQ:residence:InstPrefetch.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.IQ:residence:InstPrefetch.max_value 0 -system.cpu.iq.IQ:residence:InstPrefetch.end_dist - -system.cpu.iq.ISSUE:(null)_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:(null)_delay.samples 0 -system.cpu.iq.ISSUE:(null)_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:(null)_delay.max_value 0 -system.cpu.iq.ISSUE:(null)_delay.end_dist - -system.cpu.iq.ISSUE:IntAlu_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntAlu_delay.samples 0 -system.cpu.iq.ISSUE:IntAlu_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntAlu_delay.max_value 0 -system.cpu.iq.ISSUE:IntAlu_delay.end_dist - -system.cpu.iq.ISSUE:IntMult_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntMult_delay.samples 0 -system.cpu.iq.ISSUE:IntMult_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntMult_delay.max_value 0 -system.cpu.iq.ISSUE:IntMult_delay.end_dist - -system.cpu.iq.ISSUE:IntDiv_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IntDiv_delay.samples 0 -system.cpu.iq.ISSUE:IntDiv_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IntDiv_delay.max_value 0 -system.cpu.iq.ISSUE:IntDiv_delay.end_dist - -system.cpu.iq.ISSUE:FloatAdd_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatAdd_delay.samples 0 -system.cpu.iq.ISSUE:FloatAdd_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatAdd_delay.max_value 0 -system.cpu.iq.ISSUE:FloatAdd_delay.end_dist - -system.cpu.iq.ISSUE:FloatCmp_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatCmp_delay.samples 0 -system.cpu.iq.ISSUE:FloatCmp_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatCmp_delay.max_value 0 -system.cpu.iq.ISSUE:FloatCmp_delay.end_dist - -system.cpu.iq.ISSUE:FloatCvt_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatCvt_delay.samples 0 -system.cpu.iq.ISSUE:FloatCvt_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatCvt_delay.max_value 0 -system.cpu.iq.ISSUE:FloatCvt_delay.end_dist - -system.cpu.iq.ISSUE:FloatMult_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatMult_delay.samples 0 -system.cpu.iq.ISSUE:FloatMult_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatMult_delay.max_value 0 -system.cpu.iq.ISSUE:FloatMult_delay.end_dist - -system.cpu.iq.ISSUE:FloatDiv_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatDiv_delay.samples 0 -system.cpu.iq.ISSUE:FloatDiv_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatDiv_delay.max_value 0 -system.cpu.iq.ISSUE:FloatDiv_delay.end_dist - -system.cpu.iq.ISSUE:FloatSqrt_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:FloatSqrt_delay.samples 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.max_value 0 -system.cpu.iq.ISSUE:FloatSqrt_delay.end_dist - -system.cpu.iq.ISSUE:MemRead_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:MemRead_delay.samples 0 -system.cpu.iq.ISSUE:MemRead_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:MemRead_delay.max_value 0 -system.cpu.iq.ISSUE:MemRead_delay.end_dist - -system.cpu.iq.ISSUE:MemWrite_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:MemWrite_delay.samples 0 -system.cpu.iq.ISSUE:MemWrite_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:MemWrite_delay.max_value 0 -system.cpu.iq.ISSUE:MemWrite_delay.end_dist - -system.cpu.iq.ISSUE:IprAccess_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:IprAccess_delay.samples 0 -system.cpu.iq.ISSUE:IprAccess_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:IprAccess_delay.max_value 0 -system.cpu.iq.ISSUE:IprAccess_delay.end_dist - -system.cpu.iq.ISSUE:InstPrefetch_delay.start_dist # cycles from operands ready to issue -system.cpu.iq.ISSUE:InstPrefetch_delay.samples 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.min_value 0 - 0 0 - 2 0 - 4 0 - 6 0 - 8 0 - 10 0 - 12 0 - 14 0 - 16 0 - 18 0 - 20 0 - 22 0 - 24 0 - 26 0 - 28 0 - 30 0 - 32 0 - 34 0 - 36 0 - 38 0 - 40 0 - 42 0 - 44 0 - 46 0 - 48 0 - 50 0 - 52 0 - 54 0 - 56 0 - 58 0 - 60 0 - 62 0 - 64 0 - 66 0 - 68 0 - 70 0 - 72 0 - 74 0 - 76 0 - 78 0 - 80 0 - 82 0 - 84 0 - 86 0 - 88 0 - 90 0 - 92 0 - 94 0 - 96 0 - 98 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.max_value 0 -system.cpu.iq.ISSUE:InstPrefetch_delay.end_dist - -system.cpu.iq.ISSUE:FU_type_0 3271 # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0 3257 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 0 0.00% # Type of FU issued - IntAlu 2317 70.83% # Type of FU issued + IntAlu 2308 70.86% # Type of FU issued IntMult 1 0.03% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 0 0.00% # Type of FU issued @@ -1845,13 +278,13 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 609 18.62% # Type of FU issued - MemWrite 344 10.52% # Type of FU issued + MemRead 605 18.58% # Type of FU issued + MemWrite 343 10.53% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.end_dist system.cpu.iq.ISSUE:fu_busy_cnt 40 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.012229 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate 0.012281 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available IntAlu 5 12.50% # attempts to use FU when none available @@ -1871,11 +304,11 @@ system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle system.cpu.iq.ISSUE:issued_per_cycle.samples 2887 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 1603 5552.48% - 1 434 1503.29% - 2 301 1042.60% - 3 220 762.04% - 4 167 578.46% + 0 1607 5566.33% + 1 435 1506.75% + 2 298 1032.21% + 3 221 765.50% + 4 164 568.06% 5 94 325.60% 6 46 159.33% 7 15 51.96% @@ -1883,14 +316,14 @@ system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.133010 # Inst issue rate +system.cpu.iq.ISSUE:rate 1.128161 # Inst issue rate system.cpu.iq.iqInstsAdded 3581 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 3271 # Number of instructions issued +system.cpu.iq.iqInstsIssued 3257 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 7 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 1067 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsExamined 1088 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedInstsIssued 1 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 3 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 477 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedOperandsExamined 503 # Number of squashed operands that are examined and possibly removed from graph system.cpu.l2cache.ReadReq_accesses 274 # number of ReadReq accesses(hits+misses) system.cpu.l2cache.ReadReq_avg_miss_latency 2.018248 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout index 708b9587a..fa94f7eb9 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:16 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:40 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/tru64/o3-timing tests/run.py quick/00.hello/alpha/tru64/o3-timing Exiting @ tick 2886 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini index 1ec052afb..34f5c0b32 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.physmem +progress_interval=0 simulate_stalls=false system=system width=1 @@ -74,11 +75,17 @@ icache_port=system.membus.port[1] [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/tru64/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -94,6 +101,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.out b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.out index ae24ae2a8..a474765ae 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.out +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.out @@ -28,6 +28,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu] type=AtomicSimpleCPU @@ -35,6 +41,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.physmem system=system workload=system.cpu.workload @@ -48,6 +55,7 @@ simulate_stalls=false [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -91,3 +99,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt index b4747f1f4..b120e12b9 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,9 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 46556 # Simulator instruction rate (inst/s) -host_mem_usage 147672 # Number of bytes of host memory used -host_seconds 0.06 # Real time elapsed on the host -host_tick_rate 46204 # Simulator tick rate (ticks/s) +host_inst_rate 548861 # Simulator instruction rate (inst/s) +host_mem_usage 147820 # Number of bytes of host memory used +host_seconds 0.01 # Real time elapsed on the host +host_tick_rate 504404 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2578 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout index 438e330f5..0c9b00960 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:18 2006 +M5 compiled Oct 7 2006 11:12:49 +M5 started Sat Oct 7 11:13:09 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/tru64/simple-atomic tests/run.py quick/00.hello/alpha/tru64/simple-atomic Exiting @ tick 2577 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini index e833d841e..0d7d34e64 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.cpu.dcache +progress_interval=0 system=system workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side @@ -197,11 +198,17 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=hello +egid=100 env= +euid=100 executable=tests/test-progs/hello/bin/alpha/tru64/hello +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus @@ -217,6 +224,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.out b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.out index 1914b47e7..9b44f8ddd 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.out +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.out @@ -67,6 +67,12 @@ input=cin output=cout env= system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu] type=TimingSimpleCPU @@ -74,6 +80,7 @@ max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.cpu.dcache system=system workload=system.cpu.workload @@ -169,6 +176,7 @@ hit_latency=1 [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -212,3 +220,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt index 47bcc1b3c..916f9dad8 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,22 +1,22 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 73626 # Simulator instruction rate (inst/s) -host_mem_usage 159128 # Number of bytes of host memory used -host_seconds 0.04 # Real time elapsed on the host -host_tick_rate 106590 # Simulator tick rate (ticks/s) +host_inst_rate 196989 # Simulator instruction rate (inst/s) +host_mem_usage 159172 # Number of bytes of host memory used +host_seconds 0.01 # Real time elapsed on the host +host_tick_rate 279840 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2578 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated sim_ticks 3777 # Number of ticks simulated -system.cpu.dcache.ReadReq_accesses 416 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses 415 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 3 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 361 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits 360 # number of ReadReq hits system.cpu.dcache.ReadReq_miss_latency 165 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.132212 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_miss_rate 0.132530 # miss rate for ReadReq accesses system.cpu.dcache.ReadReq_misses 55 # number of ReadReq misses system.cpu.dcache.ReadReq_mshr_miss_latency 110 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.132212 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate 0.132530 # mshr miss rate for ReadReq accesses system.cpu.dcache.ReadReq_mshr_misses 55 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 294 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 3 # average WriteReq miss latency @@ -30,37 +30,37 @@ system.cpu.dcache.WriteReq_mshr_miss_rate 0.091837 # m system.cpu.dcache.WriteReq_mshr_misses 27 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 7.658537 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 7.646341 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 710 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses 709 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 2 # average overall mshr miss latency -system.cpu.dcache.demand_hits 628 # number of demand (read+write) hits +system.cpu.dcache.demand_hits 627 # number of demand (read+write) hits system.cpu.dcache.demand_miss_latency 246 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.115493 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate 0.115656 # miss rate for demand accesses system.cpu.dcache.demand_misses 82 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.dcache.demand_mshr_miss_latency 164 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.115493 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate 0.115656 # mshr miss rate for demand accesses system.cpu.dcache.demand_mshr_misses 82 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 710 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses 709 # number of overall (read+write) accesses system.cpu.dcache.overall_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 2 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 628 # number of overall hits +system.cpu.dcache.overall_hits 627 # number of overall hits system.cpu.dcache.overall_miss_latency 246 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.115493 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate 0.115656 # miss rate for overall accesses system.cpu.dcache.overall_misses 82 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.dcache.overall_mshr_miss_latency 164 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.115493 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate 0.115656 # mshr miss rate for overall accesses system.cpu.dcache.overall_mshr_misses 82 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -77,7 +77,7 @@ system.cpu.dcache.replacements 0 # nu system.cpu.dcache.sampled_refs 82 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.tagsinuse 53.009529 # Cycle average of tags in use -system.cpu.dcache.total_refs 628 # Total number of references to valid blocks. +system.cpu.dcache.total_refs 627 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 2579 # number of ReadReq accesses(hits+misses) diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout index 4a02e57f0..d152dc89c 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:18 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:45 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/00.hello/alpha/tru64/simple-timing tests/run.py quick/00.hello/alpha/tru64/simple-timing Exiting @ tick 3777 because target called exit() diff --git a/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt index 5d054b950..bc5ad3cca 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt @@ -1,67 +1,67 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 129834 # Simulator instruction rate (inst/s) -host_mem_usage 158964 # Number of bytes of host memory used -host_seconds 0.04 # Real time elapsed on the host -host_tick_rate 194881 # Simulator tick rate (ticks/s) +host_inst_rate 273933 # Simulator instruction rate (inst/s) +host_mem_usage 159012 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 403699 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5657 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated -sim_ticks 8573 # Number of ticks simulated -system.cpu.dcache.ReadReq_accesses 1131 # number of ReadReq accesses(hits+misses) +sim_ticks 8579 # Number of ticks simulated +system.cpu.dcache.ReadReq_accesses 1130 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 3 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 1052 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 237 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.069850 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 79 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_miss_latency 158 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.069850 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 79 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 933 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 2.586207 # average WriteReq miss latency +system.cpu.dcache.ReadReq_hits 1048 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 246 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.072566 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 82 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_miss_latency 164 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.072566 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 82 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 924 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 3 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 875 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits 874 # number of WriteReq hits system.cpu.dcache.WriteReq_miss_latency 150 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.062165 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 58 # number of WriteReq misses +system.cpu.dcache.WriteReq_miss_rate 0.054113 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 50 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_miss_latency 100 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.053591 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.054113 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 50 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 14.065693 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 14.560606 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 2064 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 2.824818 # average overall miss latency +system.cpu.dcache.demand_accesses 2054 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 2 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1927 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 387 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.066376 # miss rate for demand accesses -system.cpu.dcache.demand_misses 137 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 1922 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 396 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.064265 # miss rate for demand accesses +system.cpu.dcache.demand_misses 132 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 258 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.062500 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 129 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 264 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.064265 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 132 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 2064 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 2.824818 # average overall miss latency +system.cpu.dcache.overall_accesses 2054 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 2 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 1927 # number of overall hits -system.cpu.dcache.overall_miss_latency 387 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.066376 # miss rate for overall accesses -system.cpu.dcache.overall_misses 137 # number of overall misses +system.cpu.dcache.overall_hits 1922 # number of overall hits +system.cpu.dcache.overall_miss_latency 396 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.064265 # miss rate for overall accesses +system.cpu.dcache.overall_misses 132 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 258 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.062500 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 129 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 264 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.064265 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 132 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -74,10 +74,10 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.dcache.replacements 0 # number of replacements -system.cpu.dcache.sampled_refs 137 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 132 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 91.822487 # Cycle average of tags in use -system.cpu.dcache.total_refs 1927 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 86.924009 # Cycle average of tags in use +system.cpu.dcache.total_refs 1922 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 5658 # number of ReadReq accesses(hits+misses) @@ -138,55 +138,57 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 13 # number of replacements system.cpu.icache.sampled_refs 303 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 138.188010 # Cycle average of tags in use +system.cpu.icache.tagsinuse 138.192774 # Cycle average of tags in use system.cpu.icache.total_refs 5355 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 440 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 1.963470 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_accesses 435 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency system.cpu.l2cache.ReadReq_hits 2 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 860 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.995455 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 438 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 430 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.977273 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 430 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_miss_latency 866 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.995402 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 433 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 433 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.995402 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 433 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReq_accesses 1 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_hits 1 # number of WriteReq hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.004566 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.006928 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 440 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 1.963470 # average overall miss latency +system.cpu.l2cache.demand_accesses 436 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 2 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 860 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.995455 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 438 # number of demand (read+write) misses +system.cpu.l2cache.demand_hits 3 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 866 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.993119 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 433 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 430 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.977273 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 430 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 433 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.993119 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 433 # number of demand (read+write) MSHR misses system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.overall_accesses 440 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 1.963470 # average overall miss latency +system.cpu.l2cache.overall_accesses 436 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 1 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 2 # number of overall hits -system.cpu.l2cache.overall_miss_latency 860 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.995455 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 438 # number of overall misses +system.cpu.l2cache.overall_hits 3 # number of overall hits +system.cpu.l2cache.overall_miss_latency 866 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.993119 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 433 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 430 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.977273 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 430 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 433 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.993119 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 433 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -199,10 +201,10 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 438 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 433 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 231.300093 # Cycle average of tags in use -system.cpu.l2cache.total_refs 2 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 226.406294 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles diff --git a/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout b/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout index 11009935d..954193ee0 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout +++ b/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:37:09 -M5 started Tue Sep 5 15:46:32 2006 +M5 compiled Oct 7 2006 12:52:26 +M5 started Sat Oct 7 12:52:42 2006 M5 executing on zizzer.eecs.umich.edu command line: build/MIPS_SE/m5.opt -d build/MIPS_SE/tests/opt/quick/00.hello/mips/linux/simple-timing tests/run.py quick/00.hello/mips/linux/simple-timing -Exiting @ tick 8573 because target called exit() +Exiting @ tick 8579 because target called exit() diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini index bd25cdab9..5b6a4c7ff 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini @@ -49,12 +49,12 @@ text_file=m5stats.txt [system] type=System children=cpu membus physmem -mem_mode=timing +mem_mode=atomic physmem=system.physmem [system.cpu] type=DerivO3CPU -children=fuPool workload0 workload1 +children=dcache fuPool icache l2cache toL2Bus workload0 workload1 BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -102,7 +102,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 -mem=system.physmem +mem=system.cpu.dcache numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -122,8 +122,48 @@ trapLatency=13 wbDepth=1 wbWidth=8 workload=system.cpu.workload0 system.cpu.workload1 -dcache_port=system.membus.port[2] -icache_port=system.membus.port[1] +dcache_port=system.cpu.dcache.cpu_side +icache_port=system.cpu.icache.cpu_side + +[system.cpu.dcache] +type=BaseCache +adaptive_compression=false +assoc=2 +block_size=64 +compressed_bus=false +compression_latency=0 +do_copy=false +hash_delay=1 +hit_latency=1 +latency=1 +lifo=false +max_miss_count=0 +mshrs=10 +prefetch_access=false +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10 +prefetch_miss=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +protocol=Null +repl=Null +size=262144 +split=false +split_size=0 +store_compressed=false +subblock_size=0 +tgts_per_mshr=5 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.dcache_port +mem_side=system.cpu.toL2Bus.port[1] [system.cpu.fuPool] type=FUPool @@ -262,9 +302,94 @@ issueLat=3 opClass=IprAccess opLat=3 +[system.cpu.icache] +type=BaseCache +adaptive_compression=false +assoc=2 +block_size=64 +compressed_bus=false +compression_latency=0 +do_copy=false +hash_delay=1 +hit_latency=1 +latency=1 +lifo=false +max_miss_count=0 +mshrs=10 +prefetch_access=false +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10 +prefetch_miss=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +protocol=Null +repl=Null +size=131072 +split=false +split_size=0 +store_compressed=false +subblock_size=0 +tgts_per_mshr=5 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.icache_port +mem_side=system.cpu.toL2Bus.port[0] + +[system.cpu.l2cache] +type=BaseCache +adaptive_compression=false +assoc=2 +block_size=64 +compressed_bus=false +compression_latency=0 +do_copy=false +hash_delay=1 +hit_latency=1 +latency=1 +lifo=false +max_miss_count=0 +mshrs=10 +prefetch_access=false +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10 +prefetch_miss=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +protocol=Null +repl=Null +size=2097152 +split=false +split_size=0 +store_compressed=false +subblock_size=0 +tgts_per_mshr=5 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.toL2Bus.port[2] +mem_side=system.membus.port[1] + +[system.cpu.toL2Bus] +type=Bus +bus_id=0 +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side + [system.cpu.workload0] type=LiveProcess -cmd=tests/test-progs/hello/bin/alpha/linux/hello +cmd=hello egid=100 env= euid=100 @@ -279,7 +404,7 @@ uid=100 [system.cpu.workload1] type=LiveProcess -cmd=tests/test-progs/hello/bin/alpha/linux/hello +cmd=hello egid=100 env= euid=100 @@ -295,7 +420,7 @@ uid=100 [system.membus] type=Bus bus_id=0 -port=system.physmem.port system.cpu.icache_port system.cpu.dcache_port +port=system.physmem.port system.cpu.l2cache.mem_side [system.physmem] type=PhysicalMemory diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.out b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.out index 6d68de2a1..bfdd7bcde 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.out +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.out @@ -14,7 +14,7 @@ latency=1 [system] type=System physmem=system.physmem -mem_mode=timing +mem_mode=atomic [system.membus] type=Bus @@ -22,7 +22,7 @@ bus_id=0 [system.cpu.workload0] type=LiveProcess -cmd=tests/test-progs/hello/bin/alpha/linux/hello +cmd=hello executable=tests/test-progs/hello/bin/alpha/linux/hello input=cin output=cout @@ -37,7 +37,7 @@ ppid=99 [system.cpu.workload1] type=LiveProcess -cmd=tests/test-progs/hello/bin/alpha/linux/hello +cmd=hello executable=tests/test-progs/hello/bin/alpha/linux/hello input=cin output=cout @@ -50,6 +50,45 @@ egid=100 pid=100 ppid=99 +[system.cpu.dcache] +type=BaseCache +size=262144 +assoc=2 +block_size=64 +latency=1 +mshrs=10 +tgts_per_mshr=5 +write_buffers=8 +prioritizeRequests=false +do_copy=false +protocol=null +trace_addr=0 +hash_delay=1 +repl=null +compressed_bus=false +store_compressed=false +adaptive_compression=false +compression_latency=0 +block_size=64 +max_miss_count=0 +addr_range=[0,18446744073709551615] +split=false +split_size=0 +lifo=false +two_queue=false +prefetch_miss=false +prefetch_access=false +prefetcher_size=100 +prefetch_past_page=false +prefetch_serial_squash=false +prefetch_latency=10 +prefetch_degree=1 +prefetch_policy=none +prefetch_cache_check_push=true +prefetch_use_cpu_id=true +prefetch_data_accesses_only=false +hit_latency=1 + [system.cpu.fuPool.FUList0.opList0] type=OpDesc opClass=IntAlu @@ -184,7 +223,7 @@ clock=1 numThreads=1 activity=0 workload=system.cpu.workload0 system.cpu.workload1 -mem=system.physmem +mem=system.cpu.dcache checker=null max_insts_any_thread=0 max_insts_all_threads=0 @@ -256,6 +295,88 @@ defer_registration=false function_trace=false function_trace_start=0 +[system.cpu.icache] +type=BaseCache +size=131072 +assoc=2 +block_size=64 +latency=1 +mshrs=10 +tgts_per_mshr=5 +write_buffers=8 +prioritizeRequests=false +do_copy=false +protocol=null +trace_addr=0 +hash_delay=1 +repl=null +compressed_bus=false +store_compressed=false +adaptive_compression=false +compression_latency=0 +block_size=64 +max_miss_count=0 +addr_range=[0,18446744073709551615] +split=false +split_size=0 +lifo=false +two_queue=false +prefetch_miss=false +prefetch_access=false +prefetcher_size=100 +prefetch_past_page=false +prefetch_serial_squash=false +prefetch_latency=10 +prefetch_degree=1 +prefetch_policy=none +prefetch_cache_check_push=true +prefetch_use_cpu_id=true +prefetch_data_accesses_only=false +hit_latency=1 + +[system.cpu.l2cache] +type=BaseCache +size=2097152 +assoc=2 +block_size=64 +latency=1 +mshrs=10 +tgts_per_mshr=5 +write_buffers=8 +prioritizeRequests=false +do_copy=false +protocol=null +trace_addr=0 +hash_delay=1 +repl=null +compressed_bus=false +store_compressed=false +adaptive_compression=false +compression_latency=0 +block_size=64 +max_miss_count=0 +addr_range=[0,18446744073709551615] +split=false +split_size=0 +lifo=false +two_queue=false +prefetch_miss=false +prefetch_access=false +prefetcher_size=100 +prefetch_past_page=false +prefetch_serial_squash=false +prefetch_latency=10 +prefetch_degree=1 +prefetch_policy=none +prefetch_cache_check_push=true +prefetch_use_cpu_id=true +prefetch_data_accesses_only=false +hit_latency=1 + +[system.cpu.toL2Bus] +type=Bus +bus_id=0 + [trace] flags= start=0 diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt index 4473a39f8..a249947ca 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt @@ -1,230 +1,517 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 669 # Number of BTB hits -global.BPredUnit.BTBLookups 3666 # Number of BTB lookups -global.BPredUnit.RASInCorrect 78 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 1050 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 2479 # Number of conditional branches predicted -global.BPredUnit.lookups 4216 # Number of BP lookups -global.BPredUnit.usedRAS 545 # Number of times the RAS was used to get a target. -host_inst_rate 13879 # Simulator instruction rate (inst/s) -host_mem_usage 150244 # Number of bytes of host memory used -host_seconds 0.82 # Real time elapsed on the host -host_tick_rate 9101 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 21 # Number of conflicting loads. -memdepunit.memDep.conflictingLoads 25 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 0 # Number of conflicting stores. -memdepunit.memDep.conflictingStores 214 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 1795 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedLoads 1734 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1066 # Number of stores inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1051 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 642 # Number of BTB hits +global.BPredUnit.BTBLookups 3598 # Number of BTB lookups +global.BPredUnit.RASInCorrect 99 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1081 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 2449 # Number of conditional branches predicted +global.BPredUnit.lookups 4173 # Number of BP lookups +global.BPredUnit.usedRAS 551 # Number of times the RAS was used to get a target. +host_inst_rate 50082 # Simulator instruction rate (inst/s) +host_mem_usage 161260 # Number of bytes of host memory used +host_seconds 0.22 # Real time elapsed on the host +host_tick_rate 37535 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 41 # Number of conflicting loads. +memdepunit.memDep.conflictingLoads 39 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 194 # Number of conflicting stores. +memdepunit.memDep.conflictingStores 198 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 1868 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 1833 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1109 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1108 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 11399 # Number of instructions simulated +sim_insts 11247 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated -sim_ticks 7478 # Number of ticks simulated -system.cpu.commit.COM:branches 1756 # Number of branches committed -system.cpu.commit.COM:branches_0 878 # Number of branches committed -system.cpu.commit.COM:branches_1 878 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 177 # number cycles where commit BW limit reached +sim_ticks 8441 # Number of ticks simulated +system.cpu.commit.COM:branches 1724 # Number of branches committed +system.cpu.commit.COM:branches_0 862 # Number of branches committed +system.cpu.commit.COM:branches_1 862 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 126 # number cycles where commit BW limit reached system.cpu.commit.COM:bw_limited 0 # number of insts not committed due to BW limits system.cpu.commit.COM:bw_limited_0 0 # number of insts not committed due to BW limits system.cpu.commit.COM:bw_limited_1 0 # number of insts not committed due to BW limits system.cpu.commit.COM:committed_per_cycle.start_dist # Number of insts commited each cycle -system.cpu.commit.COM:committed_per_cycle.samples 7424 +system.cpu.commit.COM:committed_per_cycle.samples 8393 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 3237 4360.18% - 1 1635 2202.32% - 2 920 1239.22% - 3 476 641.16% - 4 347 467.40% - 5 246 331.36% - 6 206 277.48% - 7 180 242.46% - 8 177 238.42% + 0 3957 4714.64% + 1 1909 2274.51% + 2 919 1094.96% + 3 516 614.80% + 4 375 446.80% + 5 235 280.00% + 6 189 225.19% + 7 167 198.98% + 8 126 150.13% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist -system.cpu.commit.COM:count 11433 # Number of instructions committed -system.cpu.commit.COM:count_0 5716 # Number of instructions committed -system.cpu.commit.COM:count_1 5717 # Number of instructions committed -system.cpu.commit.COM:loads 1976 # Number of loads committed -system.cpu.commit.COM:loads_0 988 # Number of loads committed -system.cpu.commit.COM:loads_1 988 # Number of loads committed +system.cpu.commit.COM:count 11281 # Number of instructions committed +system.cpu.commit.COM:count_0 5640 # Number of instructions committed +system.cpu.commit.COM:count_1 5641 # Number of instructions committed +system.cpu.commit.COM:loads 1958 # Number of loads committed +system.cpu.commit.COM:loads_0 979 # Number of loads committed +system.cpu.commit.COM:loads_1 979 # Number of loads committed system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:membars_0 0 # Number of memory barriers committed system.cpu.commit.COM:membars_1 0 # Number of memory barriers committed -system.cpu.commit.COM:refs 3600 # Number of memory references committed -system.cpu.commit.COM:refs_0 1800 # Number of memory references committed -system.cpu.commit.COM:refs_1 1800 # Number of memory references committed +system.cpu.commit.COM:refs 3582 # Number of memory references committed +system.cpu.commit.COM:refs_0 1791 # Number of memory references committed +system.cpu.commit.COM:refs_1 1791 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed system.cpu.commit.COM:swp_count_0 0 # Number of s/w prefetches committed system.cpu.commit.COM:swp_count_1 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 789 # The number of times a branch was mispredicted -system.cpu.commit.commitCommittedInsts 11433 # The number of committed instructions +system.cpu.commit.branchMispredicts 832 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 11281 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 34 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 6802 # The number of squashed insts skipped by commit -system.cpu.committedInsts_0 5699 # Number of Instructions Simulated -system.cpu.committedInsts_1 5700 # Number of Instructions Simulated -system.cpu.committedInsts_total 11399 # Number of Instructions Simulated -system.cpu.cpi_0 1.312160 # CPI: Cycles Per Instruction -system.cpu.cpi_1 1.311930 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.656022 # CPI: Total CPI of All Threads -system.cpu.decode.DECODE:BlockedCycles 1617 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 282 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 364 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 22220 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 8058 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 3571 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 1260 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 200 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 277 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 4216 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 2762 # Number of cache lines fetched -system.cpu.fetch.Cycles 6837 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.Insts 25142 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 1098 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.563712 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 2762 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 1214 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 3.361679 # Number of inst fetches per cycle +system.cpu.commit.commitSquashedInsts 7525 # The number of squashed insts skipped by commit +system.cpu.committedInsts_0 5623 # Number of Instructions Simulated +system.cpu.committedInsts_1 5624 # Number of Instructions Simulated +system.cpu.committedInsts_total 11247 # Number of Instructions Simulated +system.cpu.cpi_0 1.501156 # CPI: Cycles Per Instruction +system.cpu.cpi_1 1.500889 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.750511 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 2916 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses_0 2916 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 3.076923 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_miss_latency_0 3.076923 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2.231156 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency_0 2.231156 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 2682 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits_0 2682 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 720 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_latency_0 720 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.080247 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_miss_rate_0 0.080247 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 234 # number of ReadReq misses +system.cpu.dcache.ReadReq_misses_0 234 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 35 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_hits_0 35 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 444 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency_0 444 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.068244 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate_0 0.068244 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 199 # number of ReadReq MSHR misses +system.cpu.dcache.ReadReq_mshr_misses_0 199 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 1624 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_accesses_0 1624 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 2.762376 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency_0 2.762376 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2.062500 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency_0 2.062500 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 1321 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits_0 1321 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 837 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_latency_0 837 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.186576 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_miss_rate_0 0.186576 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 303 # number of WriteReq misses +system.cpu.dcache.WriteReq_misses_0 303 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 159 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits_0 159 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 297 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency_0 297 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.088670 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate_0 0.088670 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 144 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses_0 144 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 1 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 11.670554 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 7 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 7 # number of cycles access was blocked +system.cpu.dcache.cache_copies 0 # number of cache copies performed +system.cpu.dcache.demand_accesses 4540 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses_0 4540 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses_1 0 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 2.899441 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency_0 2.899441 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 2.160350 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency_0 2.160350 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.dcache.demand_hits 4003 # number of demand (read+write) hits +system.cpu.dcache.demand_hits_0 4003 # number of demand (read+write) hits +system.cpu.dcache.demand_hits_1 0 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 1557 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_latency_0 1557 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.118282 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate_0 0.118282 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate_1 <err: div-0> # miss rate for demand accesses +system.cpu.dcache.demand_misses 537 # number of demand (read+write) misses +system.cpu.dcache.demand_misses_0 537 # number of demand (read+write) misses +system.cpu.dcache.demand_misses_1 0 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 194 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_hits_0 194 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 741 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency_0 741 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.075551 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate_0 0.075551 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate_1 <err: div-0> # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 343 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses_0 343 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses_1 0 # number of demand (read+write) MSHR misses +system.cpu.dcache.fast_writes 0 # number of fast writes performed +system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.dcache.mshr_cap_events_0 0 # number of times MSHR cap was activated +system.cpu.dcache.mshr_cap_events_1 0 # number of times MSHR cap was activated +system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.dcache.overall_accesses 4540 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses_0 4540 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses_1 0 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 2.899441 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency_0 2.899441 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 2.160350 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency_0 2.160350 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu.dcache.overall_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency +system.cpu.dcache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency +system.cpu.dcache.overall_hits 4003 # number of overall hits +system.cpu.dcache.overall_hits_0 4003 # number of overall hits +system.cpu.dcache.overall_hits_1 0 # number of overall hits +system.cpu.dcache.overall_miss_latency 1557 # number of overall miss cycles +system.cpu.dcache.overall_miss_latency_0 1557 # number of overall miss cycles +system.cpu.dcache.overall_miss_latency_1 0 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.118282 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate_0 0.118282 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses +system.cpu.dcache.overall_misses 537 # number of overall misses +system.cpu.dcache.overall_misses_0 537 # number of overall misses +system.cpu.dcache.overall_misses_1 0 # number of overall misses +system.cpu.dcache.overall_mshr_hits 194 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_hits_0 194 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_hits_1 0 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 741 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency_0 741 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.075551 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate_0 0.075551 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 343 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses_0 343 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses_1 0 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.dcache.overall_mshr_uncacheable_latency_0 0 # number of overall MSHR uncacheable cycles +system.cpu.dcache.overall_mshr_uncacheable_latency_1 0 # number of overall MSHR uncacheable cycles +system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.dcache.overall_mshr_uncacheable_misses_0 0 # number of overall MSHR uncacheable misses +system.cpu.dcache.overall_mshr_uncacheable_misses_1 0 # number of overall MSHR uncacheable misses +system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache +system.cpu.dcache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr +system.cpu.dcache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue +system.cpu.dcache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left +system.cpu.dcache.prefetcher.num_hwpf_identified 0 # number of hwpf identified +system.cpu.dcache.prefetcher.num_hwpf_issued 0 # number of hwpf issued +system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated +system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page +system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time +system.cpu.dcache.replacements 0 # number of replacements +system.cpu.dcache.replacements_0 0 # number of replacements +system.cpu.dcache.replacements_1 0 # number of replacements +system.cpu.dcache.sampled_refs 343 # Sample count of references to valid blocks. +system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.dcache.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions +system.cpu.dcache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions +system.cpu.dcache.tagsinuse 226.419332 # Cycle average of tags in use +system.cpu.dcache.total_refs 4003 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 0 # number of writebacks +system.cpu.dcache.writebacks_0 0 # number of writebacks +system.cpu.dcache.writebacks_1 0 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 1682 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 270 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 368 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 22713 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 9663 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 3758 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 1395 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 233 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 106 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 4173 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 2872 # Number of cache lines fetched +system.cpu.fetch.Cycles 6967 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 203 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 25244 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 1143 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.494314 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 2872 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 1193 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.990287 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 7479 +system.cpu.fetch.rateDist.samples 8442 system.cpu.fetch.rateDist.min_value 0 - 0 3407 4555.42% - 1 266 355.66% - 2 222 296.83% - 3 265 354.33% - 4 317 423.85% - 5 275 367.70% - 6 279 373.04% - 7 264 352.99% - 8 2184 2920.18% + 0 4348 5150.44% + 1 274 324.57% + 2 232 274.82% + 3 248 293.77% + 4 311 368.40% + 5 277 328.12% + 6 296 350.63% + 7 291 344.71% + 8 2165 2564.56% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.iew.EXEC:branches 2294 # Number of branches executed -system.cpu.iew.EXEC:branches_0 1156 # Number of branches executed -system.cpu.iew.EXEC:branches_1 1138 # Number of branches executed -system.cpu.iew.EXEC:nop 59 # number of nop insts executed +system.cpu.icache.ReadReq_accesses 2872 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses_0 2872 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 2.982343 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_miss_latency_0 2.982343 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 1.995153 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency_0 1.995153 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 2249 # number of ReadReq hits +system.cpu.icache.ReadReq_hits_0 2249 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 1858 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_latency_0 1858 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.216922 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate_0 0.216922 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 623 # number of ReadReq misses +system.cpu.icache.ReadReq_misses_0 623 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 4 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_hits_0 4 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 1235 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency_0 1235 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.215529 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate_0 0.215529 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 619 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses_0 619 # number of ReadReq MSHR misses +system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu.icache.avg_refs 3.633279 # Average number of references to valid blocks. +system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu.icache.cache_copies 0 # number of cache copies performed +system.cpu.icache.demand_accesses 2872 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses_0 2872 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses_1 0 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 2.982343 # average overall miss latency +system.cpu.icache.demand_avg_miss_latency_0 2.982343 # average overall miss latency +system.cpu.icache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 1.995153 # average overall mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency_0 1.995153 # average overall mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.icache.demand_hits 2249 # number of demand (read+write) hits +system.cpu.icache.demand_hits_0 2249 # number of demand (read+write) hits +system.cpu.icache.demand_hits_1 0 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 1858 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency_0 1858 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.216922 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate_0 0.216922 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate_1 <err: div-0> # miss rate for demand accesses +system.cpu.icache.demand_misses 623 # number of demand (read+write) misses +system.cpu.icache.demand_misses_0 623 # number of demand (read+write) misses +system.cpu.icache.demand_misses_1 0 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 4 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_hits_0 4 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 1235 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency_0 1235 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.215529 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate_0 0.215529 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate_1 <err: div-0> # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 619 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses_0 619 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses_1 0 # number of demand (read+write) MSHR misses +system.cpu.icache.fast_writes 0 # number of fast writes performed +system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.icache.mshr_cap_events_0 0 # number of times MSHR cap was activated +system.cpu.icache.mshr_cap_events_1 0 # number of times MSHR cap was activated +system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.icache.overall_accesses 2872 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses_0 2872 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses_1 0 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 2.982343 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency_0 2.982343 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 1.995153 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency_0 1.995153 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu.icache.overall_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency +system.cpu.icache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency +system.cpu.icache.overall_hits 2249 # number of overall hits +system.cpu.icache.overall_hits_0 2249 # number of overall hits +system.cpu.icache.overall_hits_1 0 # number of overall hits +system.cpu.icache.overall_miss_latency 1858 # number of overall miss cycles +system.cpu.icache.overall_miss_latency_0 1858 # number of overall miss cycles +system.cpu.icache.overall_miss_latency_1 0 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.216922 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate_0 0.216922 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses +system.cpu.icache.overall_misses 623 # number of overall misses +system.cpu.icache.overall_misses_0 623 # number of overall misses +system.cpu.icache.overall_misses_1 0 # number of overall misses +system.cpu.icache.overall_mshr_hits 4 # number of overall MSHR hits +system.cpu.icache.overall_mshr_hits_0 4 # number of overall MSHR hits +system.cpu.icache.overall_mshr_hits_1 0 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 1235 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency_0 1235 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.215529 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate_0 0.215529 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 619 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses_0 619 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses_1 0 # number of overall MSHR misses +system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.icache.overall_mshr_uncacheable_latency_0 0 # number of overall MSHR uncacheable cycles +system.cpu.icache.overall_mshr_uncacheable_latency_1 0 # number of overall MSHR uncacheable cycles +system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.icache.overall_mshr_uncacheable_misses_0 0 # number of overall MSHR uncacheable misses +system.cpu.icache.overall_mshr_uncacheable_misses_1 0 # number of overall MSHR uncacheable misses +system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache +system.cpu.icache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr +system.cpu.icache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue +system.cpu.icache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left +system.cpu.icache.prefetcher.num_hwpf_identified 0 # number of hwpf identified +system.cpu.icache.prefetcher.num_hwpf_issued 0 # number of hwpf issued +system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated +system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page +system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time +system.cpu.icache.replacements 9 # number of replacements +system.cpu.icache.replacements_0 9 # number of replacements +system.cpu.icache.replacements_1 0 # number of replacements +system.cpu.icache.sampled_refs 619 # Sample count of references to valid blocks. +system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.icache.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions +system.cpu.icache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions +system.cpu.icache.tagsinuse 332.429874 # Cycle average of tags in use +system.cpu.icache.total_refs 2249 # Total number of references to valid blocks. +system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.icache.writebacks 0 # number of writebacks +system.cpu.icache.writebacks_0 0 # number of writebacks +system.cpu.icache.writebacks_1 0 # number of writebacks +system.cpu.iew.EXEC:branches 2318 # Number of branches executed +system.cpu.iew.EXEC:branches_0 1160 # Number of branches executed +system.cpu.iew.EXEC:branches_1 1158 # Number of branches executed +system.cpu.iew.EXEC:nop 65 # number of nop insts executed system.cpu.iew.EXEC:nop_0 31 # number of nop insts executed -system.cpu.iew.EXEC:nop_1 28 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.993582 # Inst execution rate -system.cpu.iew.EXEC:refs 4718 # number of memory reference insts executed -system.cpu.iew.EXEC:refs_0 2364 # number of memory reference insts executed -system.cpu.iew.EXEC:refs_1 2354 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 1857 # Number of stores executed -system.cpu.iew.EXEC:stores_0 924 # Number of stores executed -system.cpu.iew.EXEC:stores_1 933 # Number of stores executed +system.cpu.iew.EXEC:nop_1 34 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.814854 # Inst execution rate +system.cpu.iew.EXEC:refs 4932 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_0 2474 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_1 2458 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 1873 # Number of stores executed +system.cpu.iew.EXEC:stores_0 937 # Number of stores executed +system.cpu.iew.EXEC:stores_1 936 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed system.cpu.iew.EXEC:swp_0 0 # number of swp insts executed system.cpu.iew.EXEC:swp_1 0 # number of swp insts executed -system.cpu.iew.WB:consumers 9920 # num instructions consuming a value -system.cpu.iew.WB:consumers_0 4998 # num instructions consuming a value -system.cpu.iew.WB:consumers_1 4922 # num instructions consuming a value -system.cpu.iew.WB:count 14666 # cumulative count of insts written-back -system.cpu.iew.WB:count_0 7373 # cumulative count of insts written-back -system.cpu.iew.WB:count_1 7293 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.776915 # average fanout of values written-back -system.cpu.iew.WB:fanout_0 0.775710 # average fanout of values written-back -system.cpu.iew.WB:fanout_1 0.778139 # average fanout of values written-back +system.cpu.iew.WB:consumers 10005 # num instructions consuming a value +system.cpu.iew.WB:consumers_0 5007 # num instructions consuming a value +system.cpu.iew.WB:consumers_1 4998 # num instructions consuming a value +system.cpu.iew.WB:count 14809 # cumulative count of insts written-back +system.cpu.iew.WB:count_0 7412 # cumulative count of insts written-back +system.cpu.iew.WB:count_1 7397 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.777111 # average fanout of values written-back +system.cpu.iew.WB:fanout_0 0.776113 # average fanout of values written-back +system.cpu.iew.WB:fanout_1 0.778111 # average fanout of values written-back system.cpu.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_0 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_1 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.iew.WB:penalized_rate_0 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.iew.WB:penalized_rate_1 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.iew.WB:producers 7707 # num instructions producing a value -system.cpu.iew.WB:producers_0 3877 # num instructions producing a value -system.cpu.iew.WB:producers_1 3830 # num instructions producing a value -system.cpu.iew.WB:rate 1.960957 # insts written-back per cycle -system.cpu.iew.WB:rate_0 0.985827 # insts written-back per cycle -system.cpu.iew.WB:rate_1 0.975130 # insts written-back per cycle -system.cpu.iew.WB:sent 14753 # cumulative count of insts sent to commit -system.cpu.iew.WB:sent_0 7419 # cumulative count of insts sent to commit -system.cpu.iew.WB:sent_1 7334 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 869 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 3 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 3529 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 39 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 789 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 2117 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 18235 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 2861 # Number of load instructions executed -system.cpu.iew.iewExecLoadInsts_0 1440 # Number of load instructions executed -system.cpu.iew.iewExecLoadInsts_1 1421 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 1188 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 14910 # Number of executed instructions +system.cpu.iew.WB:producers 7775 # num instructions producing a value +system.cpu.iew.WB:producers_0 3886 # num instructions producing a value +system.cpu.iew.WB:producers_1 3889 # num instructions producing a value +system.cpu.iew.WB:rate 1.754205 # insts written-back per cycle +system.cpu.iew.WB:rate_0 0.877991 # insts written-back per cycle +system.cpu.iew.WB:rate_1 0.876214 # insts written-back per cycle +system.cpu.iew.WB:sent 14942 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_0 7477 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_1 7465 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 925 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 4 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 3701 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 40 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 606 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 2217 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 18807 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 3059 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_0 1537 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_1 1522 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 927 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 15321 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 1260 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 1395 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.blockedLoads 1 # Number of blocked loads due to partial load-store forwarding +system.cpu.iew.lsq.thread.0.cacheBlocked 4 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.lsq.thread.0.forwLoads 45 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 4 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.ignoredResponses 2 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address -system.cpu.iew.lsq.thread.0.memOrderViolation 27 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 807 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 254 # Number of stores squashed +system.cpu.iew.lsq.thread.0.memOrderViolation 32 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 1 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 889 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 297 # Number of stores squashed system.cpu.iew.lsq.thread.1.blockedLoads 1 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.1.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.1.forwLoads 43 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.1.cacheBlocked 6 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.1.forwLoads 45 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread.1.ignoredResponses 2 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.1.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.1.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address -system.cpu.iew.lsq.thread.1.memOrderViolation 29 # Number of memory ordering violations +system.cpu.iew.lsq.thread.1.memOrderViolation 35 # Number of memory ordering violations system.cpu.iew.lsq.thread.1.rescheduledLoads 1 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.1.squashedLoads 746 # Number of loads squashed -system.cpu.iew.lsq.thread.1.squashedStores 239 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 56 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 733 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 136 # Number of branches that were predicted taken incorrectly -system.cpu.ipc_0 0.762102 # IPC: Instructions Per Cycle -system.cpu.ipc_1 0.762236 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.524338 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 8140 # Type of FU issued +system.cpu.iew.lsq.thread.1.squashedLoads 854 # Number of loads squashed +system.cpu.iew.lsq.thread.1.squashedStores 296 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 67 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 764 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 161 # Number of branches that were predicted taken incorrectly +system.cpu.ipc_0 0.666153 # IPC: Instructions Per Cycle +system.cpu.ipc_1 0.666272 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.332425 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8158 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist -(null) 2 0.02% # Type of FU issued -IntAlu 5556 68.26% # Type of FU issued -IntMult 1 0.01% # Type of FU issued -IntDiv 0 0.00% # Type of FU issued -FloatAdd 2 0.02% # Type of FU issued -FloatCmp 0 0.00% # Type of FU issued -FloatCvt 0 0.00% # Type of FU issued -FloatMult 0 0.00% # Type of FU issued -FloatDiv 0 0.00% # Type of FU issued -FloatSqrt 0 0.00% # Type of FU issued -MemRead 1619 19.89% # Type of FU issued -MemWrite 960 11.79% # Type of FU issued -IprAccess 0 0.00% # Type of FU issued -InstPrefetch 0 0.00% # Type of FU issued + (null) 2 0.02% # Type of FU issued + IntAlu 5514 67.59% # Type of FU issued + IntMult 1 0.01% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 2 0.02% # Type of FU issued + FloatCmp 0 0.00% # Type of FU issued + FloatCvt 0 0.00% # Type of FU issued + FloatMult 0 0.00% # Type of FU issued + FloatDiv 0 0.00% # Type of FU issued + FloatSqrt 0 0.00% # Type of FU issued + MemRead 1662 20.37% # Type of FU issued + MemWrite 977 11.98% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.end_dist -system.cpu.iq.ISSUE:FU_type_1 7958 # Type of FU issued +system.cpu.iq.ISSUE:FU_type_1 8090 # Type of FU issued system.cpu.iq.ISSUE:FU_type_1.start_dist - (null) 2 0.03% # Type of FU issued - IntAlu 5440 68.36% # Type of FU issued + (null) 2 0.02% # Type of FU issued + IntAlu 5481 67.75% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 2 0.03% # Type of FU issued + FloatAdd 2 0.02% # Type of FU issued FloatCmp 0 0.00% # Type of FU issued FloatCvt 0 0.00% # Type of FU issued FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 1553 19.51% # Type of FU issued - MemWrite 960 12.06% # Type of FU issued + MemRead 1640 20.27% # Type of FU issued + MemWrite 964 11.92% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_1.end_dist -system.cpu.iq.ISSUE:FU_type 16098 # Type of FU issued +system.cpu.iq.ISSUE:FU_type 16248 # Type of FU issued system.cpu.iq.ISSUE:FU_type.start_dist (null) 4 0.02% # Type of FU issued - IntAlu 10996 68.31% # Type of FU issued + IntAlu 10995 67.67% # Type of FU issued IntMult 2 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 4 0.02% # Type of FU issued @@ -233,20 +520,20 @@ system.cpu.iq.ISSUE:FU_type.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 3172 19.70% # Type of FU issued - MemWrite 1920 11.93% # Type of FU issued + MemRead 3302 20.32% # Type of FU issued + MemWrite 1941 11.95% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type.end_dist -system.cpu.iq.ISSUE:fu_busy_cnt 198 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_cnt_0 101 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_cnt_1 97 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.012300 # FU busy rate (busy events/executed inst) -system.cpu.iq.ISSUE:fu_busy_rate_0 0.006274 # FU busy rate (busy events/executed inst) -system.cpu.iq.ISSUE:fu_busy_rate_1 0.006026 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 181 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_0 103 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_1 78 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.011140 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_0 0.006339 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_1 0.004801 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available - IntAlu 9 4.55% # attempts to use FU when none available + IntAlu 10 5.52% # attempts to use FU when none available IntMult 0 0.00% # attempts to use FU when none available IntDiv 0 0.00% # attempts to use FU when none available FloatAdd 0 0.00% # attempts to use FU when none available @@ -255,49 +542,183 @@ system.cpu.iq.ISSUE:fu_full.start_dist FloatMult 0 0.00% # attempts to use FU when none available FloatDiv 0 0.00% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 114 57.58% # attempts to use FU when none available - MemWrite 75 37.88% # attempts to use FU when none available + MemRead 100 55.25% # attempts to use FU when none available + MemWrite 71 39.23% # attempts to use FU when none available IprAccess 0 0.00% # attempts to use FU when none available InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 7479 +system.cpu.iq.ISSUE:issued_per_cycle.samples 8442 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 2160 2888.09% - 1 1088 1454.74% - 2 1332 1780.99% - 3 1011 1351.78% - 4 818 1093.73% - 5 568 759.46% - 6 358 478.67% - 7 99 132.37% - 8 45 60.17% + 0 2688 3184.08% + 1 1455 1723.53% + 2 1431 1695.10% + 3 1111 1316.04% + 4 762 902.63% + 5 581 688.23% + 6 288 341.15% + 7 91 107.79% + 8 35 41.46% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 2.152427 # Inst issue rate -system.cpu.iq.iqInstsAdded 18137 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 16098 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 39 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 5869 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 22 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 5 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 3337 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.numCycles 7479 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 350 # Number of cycles rename is blocking -system.cpu.rename.RENAME:CommittedMaps 8222 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 8416 # Number of cycles rename is idle +system.cpu.iq.ISSUE:rate 1.924662 # Inst issue rate +system.cpu.iq.iqInstsAdded 18702 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 16248 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 40 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 6660 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 31 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 6 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 4124 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 962 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_accesses_0 962 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2.059561 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_miss_latency_0 2.059561 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency_0 1 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 5 # number of ReadReq hits +system.cpu.l2cache.ReadReq_hits_0 5 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1971 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency_0 1971 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.994802 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_miss_rate_0 0.994802 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 957 # number of ReadReq misses +system.cpu.l2cache.ReadReq_misses_0 957 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 957 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency_0 957 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.994802 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_rate_0 0.994802 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 957 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses_0 957 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReq_accesses 4 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_accesses_0 4 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_hits 4 # number of WriteReq hits +system.cpu.l2cache.WriteReq_hits_0 4 # number of WriteReq hits +system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu.l2cache.avg_refs 0.009404 # Average number of references to valid blocks. +system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu.l2cache.cache_copies 0 # number of cache copies performed +system.cpu.l2cache.demand_accesses 966 # number of demand (read+write) accesses +system.cpu.l2cache.demand_accesses_0 966 # number of demand (read+write) accesses +system.cpu.l2cache.demand_accesses_1 0 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2.059561 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency_0 2.059561 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 1 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency_0 1 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.l2cache.demand_hits 9 # number of demand (read+write) hits +system.cpu.l2cache.demand_hits_0 9 # number of demand (read+write) hits +system.cpu.l2cache.demand_hits_1 0 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1971 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency_0 1971 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.990683 # miss rate for demand accesses +system.cpu.l2cache.demand_miss_rate_0 0.990683 # miss rate for demand accesses +system.cpu.l2cache.demand_miss_rate_1 no value # miss rate for demand accesses +system.cpu.l2cache.demand_misses 957 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses_0 957 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses_1 0 # number of demand (read+write) misses +system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits +system.cpu.l2cache.demand_mshr_hits_0 0 # number of demand (read+write) MSHR hits +system.cpu.l2cache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits +system.cpu.l2cache.demand_mshr_miss_latency 957 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency_0 957 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.990683 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_miss_rate_0 0.990683 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_miss_rate_1 no value # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 957 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses_0 957 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses_1 0 # number of demand (read+write) MSHR misses +system.cpu.l2cache.fast_writes 0 # number of fast writes performed +system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.l2cache.mshr_cap_events_0 0 # number of times MSHR cap was activated +system.cpu.l2cache.mshr_cap_events_1 0 # number of times MSHR cap was activated +system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.l2cache.overall_accesses 966 # number of overall (read+write) accesses +system.cpu.l2cache.overall_accesses_0 966 # number of overall (read+write) accesses +system.cpu.l2cache.overall_accesses_1 0 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2.059561 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency_0 2.059561 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 1 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency_0 1 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency +system.cpu.l2cache.overall_hits 9 # number of overall hits +system.cpu.l2cache.overall_hits_0 9 # number of overall hits +system.cpu.l2cache.overall_hits_1 0 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1971 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency_0 1971 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency_1 0 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.990683 # miss rate for overall accesses +system.cpu.l2cache.overall_miss_rate_0 0.990683 # miss rate for overall accesses +system.cpu.l2cache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses +system.cpu.l2cache.overall_misses 957 # number of overall misses +system.cpu.l2cache.overall_misses_0 957 # number of overall misses +system.cpu.l2cache.overall_misses_1 0 # number of overall misses +system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_hits_0 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_hits_1 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_miss_latency 957 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency_0 957 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.990683 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_miss_rate_0 0.990683 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 957 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses_0 957 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses_1 0 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.l2cache.overall_mshr_uncacheable_latency_0 0 # number of overall MSHR uncacheable cycles +system.cpu.l2cache.overall_mshr_uncacheable_latency_1 0 # number of overall MSHR uncacheable cycles +system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.l2cache.overall_mshr_uncacheable_misses_0 0 # number of overall MSHR uncacheable misses +system.cpu.l2cache.overall_mshr_uncacheable_misses_1 0 # number of overall MSHR uncacheable misses +system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache +system.cpu.l2cache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr +system.cpu.l2cache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue +system.cpu.l2cache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left +system.cpu.l2cache.prefetcher.num_hwpf_identified 0 # number of hwpf identified +system.cpu.l2cache.prefetcher.num_hwpf_issued 0 # number of hwpf issued +system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated +system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page +system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time +system.cpu.l2cache.replacements 0 # number of replacements +system.cpu.l2cache.replacements_0 0 # number of replacements +system.cpu.l2cache.replacements_1 0 # number of replacements +system.cpu.l2cache.sampled_refs 957 # Sample count of references to valid blocks. +system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.l2cache.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions +system.cpu.l2cache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions +system.cpu.l2cache.tagsinuse 558.911632 # Cycle average of tags in use +system.cpu.l2cache.total_refs 9 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 0 # number of writebacks +system.cpu.l2cache.writebacks_0 0 # number of writebacks +system.cpu.l2cache.writebacks_1 0 # number of writebacks +system.cpu.numCycles 8442 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 338 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 8102 # Number of HB maps that are committed +system.cpu.rename.RENAME:IdleCycles 9965 # Number of cycles rename is idle system.cpu.rename.RENAME:LSQFullEvents 695 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 26609 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 20867 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 15602 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 3486 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 1260 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 771 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 7380 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 500 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 49 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 2217 # count of insts added to the skid buffer +system.cpu.rename.RENAME:RenameLookups 26913 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 21123 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 15786 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 3571 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 1395 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 763 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 7684 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 572 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 48 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 1900 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 38 # count of temporary serializing insts renamed system.cpu.workload0.PROG:num_syscalls 17 # Number of system calls system.cpu.workload1.PROG:num_syscalls 17 # Number of system calls diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stderr b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stderr index a0835d526..890488cd2 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stderr +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stderr @@ -2,5 +2,3 @@ warn: Entering event queue @ 0. Starting simulation... warn: cycle 0: fault (page_table_fault) detected @ PC 0x000000 warn: Increasing stack 0x11ff92000:0x11ff9b000 to 0x11ff90000:0x11ff9b000 because of access to 0x11ff91ff0 warn: Increasing stack 0x11ff92000:0x11ff9b000 to 0x11ff90000:0x11ff9b000 because of access to 0x11ff91ff0 -warn: cycle 5368: fault (page_table_fault) detected @ PC 0x000000 -warn: cycle 5369: fault (page_table_fault) detected @ PC 0x000000 diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout index 5210b5740..be25795fb 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout @@ -7,8 +7,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Oct 6 2006 00:21:18 -M5 started Fri Oct 6 02:55:30 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:47 2006 M5 executing on zizzer.eecs.umich.edu -command line: build/ALPHA_SE/m5.debug configs/example/se.py -d --cmd=tests/test-progs/hello/bin/alpha/linux/hello;tests/test-progs/hello/bin/alpha/linux/hello -Exiting @ tick 7478 because target called exit() +command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/01.hello-2T-smt/alpha/linux/o3-timing tests/run.py quick/01.hello-2T-smt/alpha/linux/o3-timing +Exiting @ tick 8441 because target called exit() diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini index a4b103732..8722c1b67 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=500000 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.physmem +progress_interval=0 simulate_stalls=false system=system width=1 @@ -92,6 +93,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.out b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.out index 8f236d9cc..6ae80aecf 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.out +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.out @@ -33,6 +33,7 @@ max_insts_any_thread=500000 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.physmem system=system workload=system.cpu.workload @@ -46,6 +47,7 @@ simulate_stalls=false [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -89,3 +91,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt index 0132ecf1b..9fdf1d513 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt @@ -1,9 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1397534 # Simulator instruction rate (inst/s) -host_mem_usage 147632 # Number of bytes of host memory used +host_inst_rate 1393697 # Simulator instruction rate (inst/s) +host_mem_usage 147652 # Number of bytes of host memory used host_seconds 0.36 # Real time elapsed on the host -host_tick_rate 1395943 # Simulator tick rate (ticks/s) +host_tick_rate 1391995 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 500000 # Number of instructions simulated sim_seconds 0.000000 # Number of seconds simulated diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout index d3edcdc0a..207a0046c 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout @@ -7,8 +7,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:20 2006 +M5 compiled Oct 7 2006 11:12:49 +M5 started Sat Oct 7 11:13:17 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/20.eio-short/alpha/eio/simple-atomic tests/run.py quick/20.eio-short/alpha/eio/simple-atomic Exiting @ tick 499999 because a thread reached the max instruction count diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini index 27568ad50..f4bdc8171 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini @@ -64,6 +64,7 @@ max_insts_any_thread=500000 max_loads_all_threads=0 max_loads_any_thread=0 mem=system.cpu.dcache +progress_interval=0 system=system workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side @@ -215,6 +216,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out index ba6875a7b..71a6d33c4 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out @@ -72,6 +72,7 @@ max_insts_any_thread=500000 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 +progress_interval=0 mem=system.cpu.dcache system=system workload=system.cpu.workload @@ -167,6 +168,7 @@ hit_latency=1 [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -210,3 +212,6 @@ trace_system=client [debug] break_cycles= +[statsreset] +reset_cycle=0 + diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt index 6339e48b7..f8d2c4ea7 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt @@ -1,67 +1,67 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 620120 # Simulator instruction rate (inst/s) -host_mem_usage 159196 # Number of bytes of host memory used +host_inst_rate 618043 # Simulator instruction rate (inst/s) +host_mem_usage 159232 # Number of bytes of host memory used host_seconds 0.81 # Real time elapsed on the host -host_tick_rate 845850 # Simulator tick rate (ticks/s) +host_tick_rate 843177 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 500000 # Number of instructions simulated sim_seconds 0.000001 # Number of seconds simulated -sim_ticks 682354 # Number of ticks simulated -system.cpu.dcache.ReadReq_accesses 124564 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 2.987952 # average ReadReq miss latency +sim_ticks 682488 # Number of ticks simulated +system.cpu.dcache.ReadReq_accesses 124435 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 3 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 124315 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 744 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.001999 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 249 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_miss_latency 496 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.001991 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 248 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 56744 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 1.256024 # average WriteReq miss latency +system.cpu.dcache.ReadReq_hits 124120 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 945 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.002531 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 315 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_miss_latency 630 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.002531 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 315 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 56340 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 3 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 56412 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits 56201 # number of WriteReq hits system.cpu.dcache.WriteReq_miss_latency 417 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.005851 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 332 # number of WriteReq misses +system.cpu.dcache.WriteReq_miss_rate 0.002467 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 139 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_miss_latency 278 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.002450 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.002467 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 139 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 311.061962 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 397.182819 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 181308 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 1.998279 # average overall miss latency +system.cpu.dcache.demand_accesses 180775 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 2 # average overall mshr miss latency -system.cpu.dcache.demand_hits 180727 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1161 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.003204 # miss rate for demand accesses -system.cpu.dcache.demand_misses 581 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 180321 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 1362 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.002511 # miss rate for demand accesses +system.cpu.dcache.demand_misses 454 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 774 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.002134 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 387 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 908 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.002511 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 454 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 181308 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 1.998279 # average overall miss latency +system.cpu.dcache.overall_accesses 180775 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 3 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 2 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 180727 # number of overall hits -system.cpu.dcache.overall_miss_latency 1161 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.003204 # miss rate for overall accesses -system.cpu.dcache.overall_misses 581 # number of overall misses +system.cpu.dcache.overall_hits 180321 # number of overall hits +system.cpu.dcache.overall_miss_latency 1362 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.002511 # miss rate for overall accesses +system.cpu.dcache.overall_misses 454 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 774 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.002134 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 387 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 908 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.002511 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 454 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -74,10 +74,10 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.dcache.replacements 0 # number of replacements -system.cpu.dcache.sampled_refs 581 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 454 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 347.118131 # Cycle average of tags in use -system.cpu.dcache.total_refs 180727 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 291.968600 # Cycle average of tags in use +system.cpu.dcache.total_refs 180321 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 500000 # number of ReadReq accesses(hits+misses) @@ -138,54 +138,56 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 403 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 268.434590 # Cycle average of tags in use +system.cpu.icache.tagsinuse 268.423238 # Cycle average of tags in use system.cpu.icache.total_refs 499597 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 984 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 1.605691 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_accesses 857 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 1580 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency 1714 # number of ReadReq miss cycles system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 984 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 790 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.802846 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 790 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_misses 857 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 857 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 857 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReq_accesses 165 # number of WriteReq accesses(hits+misses) +system.cpu.l2cache.WriteReq_hits 165 # number of WriteReq hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.192532 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 984 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 1.605691 # average overall miss latency +system.cpu.l2cache.demand_accesses 1022 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 1580 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 984 # number of demand (read+write) misses +system.cpu.l2cache.demand_hits 165 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1714 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.838552 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 857 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 790 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.802846 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 790 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 857 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.838552 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 857 # number of demand (read+write) MSHR misses system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.overall_accesses 984 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 1.605691 # average overall miss latency +system.cpu.l2cache.overall_accesses 1022 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 1 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 1580 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 984 # number of overall misses +system.cpu.l2cache.overall_hits 165 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1714 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.838552 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 857 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 790 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.802846 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 790 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 857 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.838552 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 857 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -198,10 +200,10 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 984 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 857 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 615.553879 # Cycle average of tags in use -system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 560.393094 # Cycle average of tags in use +system.cpu.l2cache.total_refs 165 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout index 158dcfe2b..409068a91 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout @@ -7,8 +7,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Sep 5 2006 15:28:48 -M5 started Tue Sep 5 15:42:20 2006 +M5 compiled Oct 7 2006 12:38:12 +M5 started Sat Oct 7 12:38:52 2006 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.opt -d build/ALPHA_SE/tests/opt/quick/20.eio-short/alpha/eio/simple-timing tests/run.py quick/20.eio-short/alpha/eio/simple-timing -Exiting @ tick 682354 because a thread reached the max instruction count +Exiting @ tick 682488 because a thread reached the max instruction count |