From 9d39407500f5c5df37ca32fcbed574a2cdc454b9 Mon Sep 17 00:00:00 2001 From: Steve Reinhardt Date: Mon, 4 Dec 2006 19:07:00 -0500 Subject: Update SPEC CPU2000 tests with actual benchmark output. tests/long/00.gzip/ref/alpha/linux/o3-timing/config.ini: tests/long/00.gzip/ref/alpha/linux/o3-timing/config.out: tests/long/00.gzip/ref/alpha/linux/o3-timing/m5stats.txt: tests/long/00.gzip/ref/alpha/linux/o3-timing/stderr: tests/long/00.gzip/ref/alpha/linux/o3-timing/stdout: tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.ini: tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.out: tests/long/00.gzip/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/00.gzip/ref/alpha/linux/simple-atomic/stderr: tests/long/00.gzip/ref/alpha/linux/simple-atomic/stdout: tests/long/00.gzip/ref/alpha/linux/simple-timing/config.ini: tests/long/00.gzip/ref/alpha/linux/simple-timing/config.out: tests/long/00.gzip/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/00.gzip/ref/alpha/linux/simple-timing/stderr: tests/long/00.gzip/ref/alpha/linux/simple-timing/stdout: tests/long/30.eon/ref/alpha/linux/simple-atomic/config.ini: tests/long/30.eon/ref/alpha/linux/simple-atomic/config.out: tests/long/30.eon/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/30.eon/ref/alpha/linux/simple-atomic/stderr: tests/long/30.eon/ref/alpha/linux/simple-atomic/stdout: tests/long/30.eon/ref/alpha/linux/simple-timing/config.ini: tests/long/30.eon/ref/alpha/linux/simple-timing/config.out: tests/long/30.eon/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/30.eon/ref/alpha/linux/simple-timing/stderr: tests/long/30.eon/ref/alpha/linux/simple-timing/stdout: tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.ini: tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.out: tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stderr: tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stdout: tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.ini: tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.out: tests/long/40.perlbmk/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stderr: tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stdout: tests/long/50.vortex/ref/alpha/linux/o3-timing/config.ini: tests/long/50.vortex/ref/alpha/linux/o3-timing/config.out: tests/long/50.vortex/ref/alpha/linux/o3-timing/m5stats.txt: tests/long/50.vortex/ref/alpha/linux/o3-timing/stderr: tests/long/50.vortex/ref/alpha/linux/o3-timing/stdout: tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.ini: tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.out: tests/long/50.vortex/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/50.vortex/ref/alpha/linux/simple-atomic/stderr: tests/long/50.vortex/ref/alpha/linux/simple-atomic/stdout: tests/long/50.vortex/ref/alpha/linux/simple-timing/config.ini: tests/long/50.vortex/ref/alpha/linux/simple-timing/config.out: tests/long/50.vortex/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/50.vortex/ref/alpha/linux/simple-timing/stderr: tests/long/50.vortex/ref/alpha/linux/simple-timing/stdout: tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.ini: tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.out: tests/long/60.bzip2/ref/alpha/linux/o3-timing/m5stats.txt: tests/long/60.bzip2/ref/alpha/linux/o3-timing/stderr: tests/long/60.bzip2/ref/alpha/linux/o3-timing/stdout: tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.ini: tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.out: tests/long/60.bzip2/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stderr: tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stdout: tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.ini: tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.out: tests/long/60.bzip2/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/60.bzip2/ref/alpha/linux/simple-timing/stderr: tests/long/60.bzip2/ref/alpha/linux/simple-timing/stdout: tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini: tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out: tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt: tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr: tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout: tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini: tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out: tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt: tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr: tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout: tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini: tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out: tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt: tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr: tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout: Update with actual benchmark output. --HG-- extra : convert_revision : 12e8de58172dd717d9cc8c5c27dd926a7257153c --- .../70.twolf/ref/alpha/linux/o3-timing/config.ini | 28 +- .../70.twolf/ref/alpha/linux/o3-timing/config.out | 105 +- .../70.twolf/ref/alpha/linux/o3-timing/m5stats.txt | 2167 +++----------------- .../long/70.twolf/ref/alpha/linux/o3-timing/stderr | 2 - .../long/70.twolf/ref/alpha/linux/o3-timing/stdout | 25 +- .../ref/alpha/linux/simple-atomic/config.ini | 352 +--- .../ref/alpha/linux/simple-atomic/config.out | 346 +--- .../ref/alpha/linux/simple-atomic/m5stats.txt | 1982 +----------------- .../70.twolf/ref/alpha/linux/simple-atomic/stderr | 2 - .../70.twolf/ref/alpha/linux/simple-atomic/stdout | 25 +- .../ref/alpha/linux/simple-timing/config.ini | 225 +- .../ref/alpha/linux/simple-timing/config.out | 265 +-- .../ref/alpha/linux/simple-timing/m5stats.txt | 2036 ++---------------- .../70.twolf/ref/alpha/linux/simple-timing/stderr | 2 - .../70.twolf/ref/alpha/linux/simple-timing/stdout | 25 +- 15 files changed, 688 insertions(+), 6899 deletions(-) (limited to 'tests/long/70.twolf/ref/alpha') diff --git a/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini b/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini index c3a59fbce..fb3d24c55 100644 --- a/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini +++ b/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini @@ -7,11 +7,9 @@ max_tick=0 output_file=cout progress_interval=0 -[debug] -break_cycles= - [exetrace] intel_format=false +legion_lockstep=false pc_symbol=true print_cpseq=false print_cycle=true @@ -102,14 +100,15 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 -mem=system.cpu.dcache numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 numROBEntries=192 numRobs=1 numThreads=1 +phase=0 predType=tournament +progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 renameToIEWDelay=2 @@ -131,7 +130,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -308,7 +306,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -348,7 +345,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -384,20 +380,33 @@ mem_side=system.membus.port[1] [system.cpu.toL2Bus] type=Bus bus_id=0 +clock=1000 +responder_set=false +width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side [system.cpu.workload] type=LiveProcess -cmd=hello +cmd=twolf smred +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/o3-timing +egid=100 env= -executable=tests/test-progs/hello/bin/alpha/linux/hello +euid=100 +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus bus_id=0 +clock=1000 +responder_set=false +width=64 port=system.physmem.port system.cpu.l2cache.mem_side [system.physmem] @@ -409,6 +418,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out b/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out index f491a3081..e4ed95acf 100644 --- a/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out +++ b/tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out @@ -19,54 +19,25 @@ mem_mode=atomic [system.membus] type=Bus bus_id=0 +clock=1000 +width=64 +responder_set=false [system.cpu.workload] type=LiveProcess -cmd=hello -executable=tests/test-progs/hello/bin/alpha/linux/hello +cmd=twolf smred +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf input=cin output=cout env= +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/o3-timing system=system - -[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 +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu.fuPool.FUList0.opList0] type=OpDesc @@ -199,15 +170,16 @@ FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUL [system.cpu] type=DerivO3CPU clock=1 +phase=0 numThreads=1 activity=0 workload=system.cpu.workload -mem=system.cpu.dcache checker=null 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 @@ -283,7 +255,44 @@ 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.dcache] +type=BaseCache +size=262144 +assoc=2 +block_size=64 +latency=1 +mshrs=10 +tgts_per_mshr=5 +write_buffers=8 +prioritizeRequests=false protocol=null trace_addr=0 hash_delay=1 @@ -322,7 +331,6 @@ mshrs=10 tgts_per_mshr=5 write_buffers=8 prioritizeRequests=false -do_copy=false protocol=null trace_addr=0 hash_delay=1 @@ -354,10 +362,14 @@ hit_latency=1 [system.cpu.toL2Bus] type=Bus bus_id=0 +clock=1000 +width=64 +responder_set=false [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -396,8 +408,9 @@ print_cpseq=false print_reg_delta=false pc_symbol=true intel_format=false +legion_lockstep=false trace_system=client -[debug] -break_cycles= +[statsreset] +reset_cycle=0 diff --git a/tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt b/tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt index 5d4f9235a..dfa1fbe0b 100644 --- a/tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt @@ -1,112 +1,112 @@ ---------- 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.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.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) -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.insertedStores 1221 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 11837684 # Number of BTB hits +global.BPredUnit.BTBLookups 15197122 # Number of BTB lookups +global.BPredUnit.RASInCorrect 1217 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1998573 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 12917224 # Number of conditional branches predicted +global.BPredUnit.lookups 17533197 # Number of BP lookups +global.BPredUnit.usedRAS 1687018 # Number of times the RAS was used to get a target. +host_inst_rate 57997 # Simulator instruction rate (inst/s) +host_mem_usage 178748 # Number of bytes of host memory used +host_seconds 1423.90 # Real time elapsed on the host +host_tick_rate 73521 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 10104667 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 3292311 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 29530804 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 9370879 # 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 -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 +sim_insts 82582323 # Number of instructions simulated +sim_seconds 0.000105 # Number of seconds simulated +sim_ticks 104686099 # Number of ticks simulated +system.cpu.commit.COM:branches 10071057 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 3175901 # 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 65490840 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 32034998 4891.52% + 1 13785472 2104.95% + 2 8057025 1230.25% + 3 3669149 560.25% + 4 1988059 303.56% + 5 1377349 210.31% + 6 785420 119.93% + 7 617467 94.28% + 8 3175901 484.94% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist -system.cpu.commit.COM:count 5640 # Number of instructions committed -system.cpu.commit.COM:loads 979 # Number of loads committed +system.cpu.commit.COM:count 90187947 # Number of instructions committed +system.cpu.commit.COM:loads 19613586 # Number of loads committed system.cpu.commit.COM:membars 0 # Number of memory barriers committed -system.cpu.commit.COM:refs 1791 # Number of memory references committed +system.cpu.commit.COM:refs 25981086 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -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.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.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_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_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_misses 71 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs # 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.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.commit.branchMispredicts 1985168 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 90187947 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 387 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 40679620 # The number of squashed insts skipped by commit +system.cpu.committedInsts 82582323 # Number of Instructions Simulated +system.cpu.committedInsts_total 82582323 # Number of Instructions Simulated +system.cpu.cpi 1.267657 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.267657 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 22673452 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 5439.841232 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4838.693712 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 22672608 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 4591226 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000037 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 844 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 351 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 2385476 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000022 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 493 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 6365908 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 5074.130393 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 4849.051425 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 6360739 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 26228180 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.000812 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 5169 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 3555 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 7826369 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.000254 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 1614 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 2811.600000 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 3114.692857 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 13779.471761 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 10 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 700 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 28116 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 2180285 # 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 29039360 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 5125.462498 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 4846.627907 # average overall mshr miss latency +system.cpu.dcache.demand_hits 29033347 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 30819406 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000207 # miss rate for demand accesses +system.cpu.dcache.demand_misses 6013 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 3906 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 10211845 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.000073 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 2107 # 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 29039360 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 5125.462498 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 4846.627907 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency # 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 29033347 # number of overall hits +system.cpu.dcache.overall_miss_latency 30819406 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000207 # miss rate for overall accesses +system.cpu.dcache.overall_misses 6013 # number of overall misses +system.cpu.dcache.overall_mshr_hits 3906 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 10211845 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.000073 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 2107 # 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 @@ -118,92 +118,92 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 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.sampled_refs 178 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 104 # number of replacements +system.cpu.dcache.sampled_refs 2107 # 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 1404.053454 # Cycle average of tags in use +system.cpu.dcache.total_refs 29033347 # 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:RunCycles 2158 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 754 # 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.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.IcacheSquashes 148 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 13707 # 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.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.dcache.writebacks 75 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 2221252 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 13564 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 2815361 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 145659694 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 36080141 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 27108364 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 6243203 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 50032 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 81084 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 17533197 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 17509399 # Number of cache lines fetched +system.cpu.fetch.Cycles 45531133 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 484323 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 150299775 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 2040341 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.244419 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 17509399 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 13524702 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.095236 # 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 71734044 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 43713095 6093.77% + 1 2792314 389.26% + 2 2129360 296.84% + 3 3194083 445.27% + 4 4028588 561.60% + 5 1363321 190.05% + 6 1870461 260.75% + 7 1629807 227.20% + 8 11013015 1535.26% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 1582 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 2.960245 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 1.996885 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1255 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 968 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.206700 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 327 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 6 # number of ReadReq MSHR hits -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_refs 3.909657 # Average number of references to valid blocks. +system.cpu.icache.ReadReq_accesses 17509399 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 3388.211547 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 2494.269154 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 17495889 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 45774738 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000772 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 13510 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 3486 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 25002554 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000572 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 10024 # number of ReadReq MSHR misses +system.cpu.icache.avg_blocked_cycles_no_mshrs # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles_no_targets 3400.454545 # average number of cycles each access was blocked +system.cpu.icache.avg_refs 1745.399940 # 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_no_targets 22 # 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.blocked_cycles_no_targets 74810 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 1582 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency -system.cpu.icache.demand_hits 1255 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 968 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.206700 # miss rate for demand accesses -system.cpu.icache.demand_misses 327 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 6 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 641 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.202908 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 321 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 17509399 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 3388.211547 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 2494.269154 # average overall mshr miss latency +system.cpu.icache.demand_hits 17495889 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 45774738 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000772 # miss rate for demand accesses +system.cpu.icache.demand_misses 13510 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 3486 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 25002554 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000572 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 10024 # 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.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.icache.overall_accesses 1582 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency +system.cpu.icache.overall_accesses 17509399 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 3388.211547 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 2494.269154 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 1255 # number of overall hits -system.cpu.icache.overall_miss_latency 968 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.206700 # miss rate for overall accesses -system.cpu.icache.overall_misses 327 # number of overall misses -system.cpu.icache.overall_mshr_hits 6 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 641 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.202908 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 321 # number of overall MSHR misses +system.cpu.icache.overall_hits 17495889 # number of overall hits +system.cpu.icache.overall_miss_latency 45774738 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000772 # miss rate for overall accesses +system.cpu.icache.overall_misses 13510 # number of overall misses +system.cpu.icache.overall_mshr_hits 3486 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 25002554 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000572 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 10024 # 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_misses 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 @@ -215,1726 +215,162 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 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 0 # number of replacements -system.cpu.icache.sampled_refs 321 # Sample count of references to valid blocks. +system.cpu.icache.replacements 8115 # number of replacements +system.cpu.icache.sampled_refs 10024 # 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.total_refs 1255 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1481.631027 # Cycle average of tags in use +system.cpu.icache.total_refs 17495889 # 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.idleCycles 32952056 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 12456785 # Number of branches executed +system.cpu.iew.EXEC:nop 11559797 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.365191 # Inst execution rate +system.cpu.iew.EXEC:refs 30958353 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 7006627 # 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 86914579 # num instructions consuming a value +system.cpu.iew.WB:count 96291361 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.729319 # 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.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.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.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 63388475 # num instructions producing a value +system.cpu.iew.WB:rate 1.342338 # insts written-back per cycle +system.cpu.iew.WB:sent 96947832 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 2153450 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 156060 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 29530804 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 437 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 2057217 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 9370879 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 130866464 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 23951726 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2095770 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 97930658 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 43929 # 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.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 -system.cpu.iew.lsq.thread.0.forwLoads 55 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 5 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 720 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 6243203 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 62133 # Number of cycles IEW is unblocking +system.cpu.iew.lsq.thread.0.blockedLoads 9874 # Number of blocked loads due to partial load-store forwarding +system.cpu.iew.lsq.thread.0.cacheBlocked 40553 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 855538 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 3321 # 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.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.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.iew.lsq.thread.0.memOrderViolation 18493 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 9874 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 9917218 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 3003379 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 18493 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 1143572 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 1009878 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.788857 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.788857 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 100026428 # 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 - IntMult 1 0.01% # Type of FU issued + (null) 7 0.00% # Type of FU issued + IntAlu 61666427 61.65% # Type of FU issued + IntMult 468908 0.47% # 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 1757 20.95% # Type of FU issued - MemWrite 1032 12.30% # Type of FU issued + FloatAdd 2704055 2.70% # Type of FU issued + FloatCmp 112834 0.11% # Type of FU issued + FloatCvt 2307257 2.31% # Type of FU issued + FloatMult 295394 0.30% # Type of FU issued + FloatDiv 735688 0.74% # Type of FU issued + FloatSqrt 122 0.00% # Type of FU issued + MemRead 24586382 24.58% # Type of FU issued + MemWrite 7149354 7.15% # 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_cnt 1620744 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.016203 # 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 + IntAlu 195067 12.04% # 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 - FloatCmp 0 0.00% # attempts to use FU when none available - FloatCvt 0 0.00% # attempts to use FU when none available - FloatMult 0 0.00% # attempts to use FU when none available - FloatDiv 0 0.00% # attempts to use FU when none available + FloatAdd 1678 0.10% # attempts to use FU when none available + FloatCmp 197 0.01% # attempts to use FU when none available + FloatCvt 4552 0.28% # attempts to use FU when none available + FloatMult 2392 0.15% # attempts to use FU when none available + FloatDiv 951463 58.71% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 76 66.09% # attempts to use FU when none available - MemWrite 38 33.04% # attempts to use FU when none available + MemRead 401417 24.77% # attempts to use FU when none available + MemWrite 63978 3.95% # 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 6871 +system.cpu.iq.ISSUE:issued_per_cycle.samples 71734044 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 28631398 3991.33% + 1 15448994 2153.65% + 2 12333631 1719.36% + 3 7046540 982.31% + 4 4503539 627.81% + 5 2295007 319.93% + 6 1113179 155.18% + 7 291761 40.67% + 8 69995 9.76% 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.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.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.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.iq.ISSUE:rate 1.394407 # Inst issue rate +system.cpu.iq.iqInstsAdded 119306230 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 100026428 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 437 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 35838359 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 150449 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 50 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 30462150 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 12131 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 3919.717352 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2067.943230 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 7146 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 19539791 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.410931 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 4985 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 10308697 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.410931 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 4985 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReqNoAck|Writeback_accesses 75 # number of WriteReqNoAck|Writeback accesses(hits+misses) +system.cpu.l2cache.WriteReqNoAck|Writeback_hits 75 # number of WriteReqNoAck|Writeback hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets # 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 1.448546 # 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_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_accesses 12131 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 3919.717352 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2067.943230 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 7146 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 19539791 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.410931 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 4985 # 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 10308697 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.410931 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 4985 # 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_avg_mshr_miss_latency 1 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 12206 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 3919.717352 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2067.943230 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency # 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 7221 # number of overall hits +system.cpu.l2cache.overall_miss_latency 19539791 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.408406 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 4985 # 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 10308697 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.408406 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 4985 # 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 @@ -1947,28 +383,31 @@ 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 4985 # 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 3244.539242 # Cycle average of tags in use +system.cpu.l2cache.total_refs 7221 # 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.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: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: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 -system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 408 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 21 # count of temporary serializing insts renamed -system.cpu.workload.PROG:num_syscalls 17 # Number of system calls +system.cpu.numCycles 71734044 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 969328 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 67122956 # Number of HB maps that are committed +system.cpu.rename.RENAME:IQFullEvents 411688 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 37058676 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 742595 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 109 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 181728449 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 141044897 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 103457127 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 26196123 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 6243203 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 1187915 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 36334171 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 78799 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 513 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 2731208 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 502 # count of temporary serializing insts renamed +system.cpu.timesIdled 10186 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.workload.PROG:num_syscalls 387 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr b/tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr index 8893caac8..87866a2a5 100644 --- a/tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr +++ b/tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr @@ -1,3 +1 @@ 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 diff --git a/tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout b/tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout index fbb329a2f..f32f0a972 100644 --- a/tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout +++ b/tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout @@ -1,13 +1,14 @@ -Hello world! -M5 Simulator System -Copyright (c) 2001-2006 -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 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() +TimberWolfSC version:v4.3a date:Mon Jan 25 18:50:36 EST 1988 +Standard Cell Placement and Global Routing Program +Authors: Carl Sechen, Bill Swartz + Yale University + 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 + 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 + 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 + 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 + 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 + 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 +106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 +122 123 124 \ No newline at end of file diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini index c3a59fbce..fbf8dd865 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini +++ b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini @@ -7,11 +7,9 @@ max_tick=0 output_file=cout progress_interval=0 -[debug] -break_cycles= - [exetrace] intel_format=false +legion_lockstep=false pc_symbol=true print_cpseq=false print_cycle=true @@ -53,352 +51,49 @@ mem_mode=atomic physmem=system.physmem [system.cpu] -type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload -BTBEntries=4096 -BTBTagSize=16 -LFSTSize=1024 -LQEntries=32 -RASSize=16 -SQEntries=32 -SSITSize=1024 -activity=0 -backComSize=5 -choiceCtrBits=2 -choicePredictorSize=8192 +type=AtomicSimpleCPU +children=workload clock=1 -commitToDecodeDelay=1 -commitToFetchDelay=1 -commitToIEWDelay=1 -commitToRenameDelay=1 -commitWidth=8 -decodeToFetchDelay=1 -decodeToRenameDelay=1 -decodeWidth=8 +cpu_id=0 defer_registration=false -dispatchWidth=8 -fetchToDecodeDelay=1 -fetchTrapLatency=1 -fetchWidth=8 -forwardComSize=5 -fuPool=system.cpu.fuPool function_trace=false function_trace_start=0 -globalCtrBits=2 -globalHistoryBits=13 -globalPredictorSize=8192 -iewToCommitDelay=1 -iewToDecodeDelay=1 -iewToFetchDelay=1 -iewToRenameDelay=1 -instShiftAmt=2 -issueToExecuteDelay=1 -issueWidth=8 -localCtrBits=2 -localHistoryBits=11 -localHistoryTableSize=2048 -localPredictorSize=2048 max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 -mem=system.cpu.dcache -numIQEntries=64 -numPhysFloatRegs=256 -numPhysIntRegs=256 -numROBEntries=192 -numRobs=1 -numThreads=1 -predType=tournament -renameToDecodeDelay=1 -renameToFetchDelay=1 -renameToIEWDelay=2 -renameToROBDelay=1 -renameWidth=8 -squashWidth=8 +phase=0 +progress_interval=0 +simulate_stalls=false system=system -trapLatency=13 -wbDepth=1 -wbWidth=8 +width=1 workload=system.cpu.workload -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 -children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 -FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 - -[system.cpu.fuPool.FUList0] -type=FUDesc -children=opList0 -count=6 -opList=system.cpu.fuPool.FUList0.opList0 - -[system.cpu.fuPool.FUList0.opList0] -type=OpDesc -issueLat=1 -opClass=IntAlu -opLat=1 - -[system.cpu.fuPool.FUList1] -type=FUDesc -children=opList0 opList1 -count=2 -opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 - -[system.cpu.fuPool.FUList1.opList0] -type=OpDesc -issueLat=1 -opClass=IntMult -opLat=3 - -[system.cpu.fuPool.FUList1.opList1] -type=OpDesc -issueLat=19 -opClass=IntDiv -opLat=20 - -[system.cpu.fuPool.FUList2] -type=FUDesc -children=opList0 opList1 opList2 -count=4 -opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 - -[system.cpu.fuPool.FUList2.opList0] -type=OpDesc -issueLat=1 -opClass=FloatAdd -opLat=2 - -[system.cpu.fuPool.FUList2.opList1] -type=OpDesc -issueLat=1 -opClass=FloatCmp -opLat=2 - -[system.cpu.fuPool.FUList2.opList2] -type=OpDesc -issueLat=1 -opClass=FloatCvt -opLat=2 - -[system.cpu.fuPool.FUList3] -type=FUDesc -children=opList0 opList1 opList2 -count=2 -opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 - -[system.cpu.fuPool.FUList3.opList0] -type=OpDesc -issueLat=1 -opClass=FloatMult -opLat=4 - -[system.cpu.fuPool.FUList3.opList1] -type=OpDesc -issueLat=12 -opClass=FloatDiv -opLat=12 - -[system.cpu.fuPool.FUList3.opList2] -type=OpDesc -issueLat=24 -opClass=FloatSqrt -opLat=24 - -[system.cpu.fuPool.FUList4] -type=FUDesc -children=opList0 -count=0 -opList=system.cpu.fuPool.FUList4.opList0 - -[system.cpu.fuPool.FUList4.opList0] -type=OpDesc -issueLat=1 -opClass=MemRead -opLat=1 - -[system.cpu.fuPool.FUList5] -type=FUDesc -children=opList0 -count=0 -opList=system.cpu.fuPool.FUList5.opList0 - -[system.cpu.fuPool.FUList5.opList0] -type=OpDesc -issueLat=1 -opClass=MemWrite -opLat=1 - -[system.cpu.fuPool.FUList6] -type=FUDesc -children=opList0 opList1 -count=4 -opList=system.cpu.fuPool.FUList6.opList0 system.cpu.fuPool.FUList6.opList1 - -[system.cpu.fuPool.FUList6.opList0] -type=OpDesc -issueLat=1 -opClass=MemRead -opLat=1 - -[system.cpu.fuPool.FUList6.opList1] -type=OpDesc -issueLat=1 -opClass=MemWrite -opLat=1 - -[system.cpu.fuPool.FUList7] -type=FUDesc -children=opList0 -count=1 -opList=system.cpu.fuPool.FUList7.opList0 - -[system.cpu.fuPool.FUList7.opList0] -type=OpDesc -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 +dcache_port=system.membus.port[2] +icache_port=system.membus.port[1] [system.cpu.workload] type=LiveProcess -cmd=hello +cmd=twolf smred +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/simple-atomic +egid=100 env= -executable=tests/test-progs/hello/bin/alpha/linux/hello +euid=100 +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus bus_id=0 -port=system.physmem.port system.cpu.l2cache.mem_side +clock=1000 +responder_set=false +width=64 +port=system.physmem.port system.cpu.icache_port system.cpu.dcache_port [system.physmem] type=PhysicalMemory @@ -409,6 +104,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out index f491a3081..5375d2a8f 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out +++ b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out @@ -19,345 +19,48 @@ mem_mode=atomic [system.membus] type=Bus bus_id=0 +clock=1000 +width=64 +responder_set=false [system.cpu.workload] type=LiveProcess -cmd=hello -executable=tests/test-progs/hello/bin/alpha/linux/hello +cmd=twolf smred +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf input=cin output=cout env= +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/simple-atomic system=system - -[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 -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList0] -type=FUDesc -opList=system.cpu.fuPool.FUList0.opList0 -count=6 - -[system.cpu.fuPool.FUList1.opList0] -type=OpDesc -opClass=IntMult -opLat=3 -issueLat=1 - -[system.cpu.fuPool.FUList1.opList1] -type=OpDesc -opClass=IntDiv -opLat=20 -issueLat=19 - -[system.cpu.fuPool.FUList1] -type=FUDesc -opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 -count=2 - -[system.cpu.fuPool.FUList2.opList0] -type=OpDesc -opClass=FloatAdd -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2.opList1] -type=OpDesc -opClass=FloatCmp -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2.opList2] -type=OpDesc -opClass=FloatCvt -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2] -type=FUDesc -opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 -count=4 - -[system.cpu.fuPool.FUList3.opList0] -type=OpDesc -opClass=FloatMult -opLat=4 -issueLat=1 - -[system.cpu.fuPool.FUList3.opList1] -type=OpDesc -opClass=FloatDiv -opLat=12 -issueLat=12 - -[system.cpu.fuPool.FUList3.opList2] -type=OpDesc -opClass=FloatSqrt -opLat=24 -issueLat=24 - -[system.cpu.fuPool.FUList3] -type=FUDesc -opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 -count=2 - -[system.cpu.fuPool.FUList4.opList0] -type=OpDesc -opClass=MemRead -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList4] -type=FUDesc -opList=system.cpu.fuPool.FUList4.opList0 -count=0 - -[system.cpu.fuPool.FUList5.opList0] -type=OpDesc -opClass=MemWrite -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList5] -type=FUDesc -opList=system.cpu.fuPool.FUList5.opList0 -count=0 - -[system.cpu.fuPool.FUList6.opList0] -type=OpDesc -opClass=MemRead -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList6.opList1] -type=OpDesc -opClass=MemWrite -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList6] -type=FUDesc -opList=system.cpu.fuPool.FUList6.opList0 system.cpu.fuPool.FUList6.opList1 -count=4 - -[system.cpu.fuPool.FUList7.opList0] -type=OpDesc -opClass=IprAccess -opLat=3 -issueLat=3 - -[system.cpu.fuPool.FUList7] -type=FUDesc -opList=system.cpu.fuPool.FUList7.opList0 -count=1 - -[system.cpu.fuPool] -type=FUPool -FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 [system.cpu] -type=DerivO3CPU -clock=1 -numThreads=1 -activity=0 -workload=system.cpu.workload -mem=system.cpu.dcache -checker=null +type=AtomicSimpleCPU max_insts_any_thread=0 max_insts_all_threads=0 max_loads_any_thread=0 max_loads_all_threads=0 -cachePorts=200 -decodeToFetchDelay=1 -renameToFetchDelay=1 -iewToFetchDelay=1 -commitToFetchDelay=1 -fetchWidth=8 -renameToDecodeDelay=1 -iewToDecodeDelay=1 -commitToDecodeDelay=1 -fetchToDecodeDelay=1 -decodeWidth=8 -iewToRenameDelay=1 -commitToRenameDelay=1 -decodeToRenameDelay=1 -renameWidth=8 -commitToIEWDelay=1 -renameToIEWDelay=2 -issueToExecuteDelay=1 -dispatchWidth=8 -issueWidth=8 -wbWidth=8 -wbDepth=1 -fuPool=system.cpu.fuPool -iewToCommitDelay=1 -renameToROBDelay=1 -commitWidth=8 -squashWidth=8 -trapLatency=13 -backComSize=5 -forwardComSize=5 -predType=tournament -localPredictorSize=2048 -localCtrBits=2 -localHistoryTableSize=2048 -localHistoryBits=11 -globalPredictorSize=8192 -globalCtrBits=2 -globalHistoryBits=13 -choicePredictorSize=8192 -choiceCtrBits=2 -BTBEntries=4096 -BTBTagSize=16 -RASSize=16 -LQEntries=32 -SQEntries=32 -LFSTSize=1024 -SSITSize=1024 -numPhysIntRegs=256 -numPhysFloatRegs=256 -numIQEntries=64 -numROBEntries=192 -smtNumFetchingThreads=1 -smtFetchPolicy=SingleThread -smtLSQPolicy=Partitioned -smtLSQThreshold=100 -smtIQPolicy=Partitioned -smtIQThreshold=100 -smtROBPolicy=Partitioned -smtROBThreshold=100 -smtCommitPolicy=RoundRobin -instShiftAmt=2 +progress_interval=0 +system=system +cpu_id=0 +workload=system.cpu.workload +clock=1 +phase=0 defer_registration=false +width=1 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 +simulate_stalls=false [trace] flags= start=0 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -396,8 +99,9 @@ print_cpseq=false print_reg_delta=false pc_symbol=true intel_format=false +legion_lockstep=false trace_system=client -[debug] -break_cycles= +[statsreset] +reset_cycle=0 diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt index 5d4f9235a..e5e0a4991 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt @@ -1,1974 +1,18 @@ ---------- 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.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.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) -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.insertedStores 1221 # Number of stores inserted to the mem dependence unit. +host_inst_rate 827042 # Simulator instruction rate (inst/s) +host_mem_usage 146736 # Number of bytes of host memory used +host_seconds 111.12 # Real time elapsed on the host +host_tick_rate 827039 # Simulator tick rate (ticks/s) 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 -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.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% -system.cpu.commit.COM:committed_per_cycle.max_value 8 -system.cpu.commit.COM:committed_per_cycle.end_dist - -system.cpu.commit.COM:count 5640 # Number of instructions committed -system.cpu.commit.COM:loads 979 # Number of loads committed -system.cpu.commit.COM:membars 0 # Number of memory barriers committed -system.cpu.commit.COM:refs 1791 # Number of memory references committed -system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -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.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.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_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_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_misses 71 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs # 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.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.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_avg_mshr_uncacheable_latency # 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_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 -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.sampled_refs 178 # 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.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:RunCycles 2158 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 754 # 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.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.IcacheSquashes 148 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 13707 # 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.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.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 6871 -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% -system.cpu.fetch.rateDist.max_value 8 -system.cpu.fetch.rateDist.end_dist - -system.cpu.icache.ReadReq_accesses 1582 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 2.960245 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 1.996885 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1255 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 968 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.206700 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 327 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 6 # number of ReadReq MSHR hits -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_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 -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 1582 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency -system.cpu.icache.demand_hits 1255 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 968 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.206700 # miss rate for demand accesses -system.cpu.icache.demand_misses 327 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 6 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 641 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.202908 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 321 # 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.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.icache.overall_accesses 1582 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_uncacheable_latency # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 1255 # number of overall hits -system.cpu.icache.overall_miss_latency 968 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.206700 # miss rate for overall accesses -system.cpu.icache.overall_misses 327 # number of overall misses -system.cpu.icache.overall_mshr_hits 6 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 641 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.202908 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 321 # 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_misses 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 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.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: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: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.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.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.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.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 -system.cpu.iew.lsq.thread.0.forwLoads 55 # Number of loads that had data forwarded from stores -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.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.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.iq.ISSUE:FU_type_0.start_dist - (null) 2 0.02% # Type of FU issued - IntAlu 5594 66.69% # 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 1757 20.95% # Type of FU issued - MemWrite 1032 12.30% # 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_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 - 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 - FloatCmp 0 0.00% # attempts to use FU when none available - FloatCvt 0 0.00% # attempts to use FU when none available - 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 76 66.09% # attempts to use FU when none available - MemWrite 38 33.04% # 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 6871 -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% -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.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.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.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.avg_blocked_cycles_no_mshrs # average number of cycles each access was blocked -system.cpu.l2cache.avg_blocked_cycles_no_targets # 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.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_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_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.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_avg_mshr_miss_latency 1 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_uncacheable_latency # 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_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_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 -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.sampled_refs 497 # 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.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.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: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: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 -system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 408 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 21 # count of temporary serializing insts renamed -system.cpu.workload.PROG:num_syscalls 17 # Number of system calls +sim_insts 91900700 # Number of instructions simulated +sim_seconds 0.000092 # Number of seconds simulated +sim_ticks 91900699 # Number of ticks simulated +system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles +system.cpu.numCycles 91900700 # number of cpu cycles simulated +system.cpu.num_insts 91900700 # Number of instructions executed +system.cpu.num_refs 26536244 # Number of memory references +system.cpu.workload.PROG:num_syscalls 387 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr index 8893caac8..87866a2a5 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr +++ b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr @@ -1,3 +1 @@ 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 diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout index fbb329a2f..f32f0a972 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout +++ b/tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout @@ -1,13 +1,14 @@ -Hello world! -M5 Simulator System -Copyright (c) 2001-2006 -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 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() +TimberWolfSC version:v4.3a date:Mon Jan 25 18:50:36 EST 1988 +Standard Cell Placement and Global Routing Program +Authors: Carl Sechen, Bill Swartz + Yale University + 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 + 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 + 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 + 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 + 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 + 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 +106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 +122 123 124 \ No newline at end of file diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini b/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini index c3a59fbce..9f6151e4d 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini +++ b/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini @@ -7,11 +7,9 @@ max_tick=0 output_file=cout progress_interval=0 -[debug] -break_cycles= - [exetrace] intel_format=false +legion_lockstep=false pc_symbol=true print_cpseq=false print_cycle=true @@ -53,73 +51,20 @@ mem_mode=atomic physmem=system.physmem [system.cpu] -type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload -BTBEntries=4096 -BTBTagSize=16 -LFSTSize=1024 -LQEntries=32 -RASSize=16 -SQEntries=32 -SSITSize=1024 -activity=0 -backComSize=5 -choiceCtrBits=2 -choicePredictorSize=8192 +type=TimingSimpleCPU +children=dcache icache l2cache toL2Bus workload clock=1 -commitToDecodeDelay=1 -commitToFetchDelay=1 -commitToIEWDelay=1 -commitToRenameDelay=1 -commitWidth=8 -decodeToFetchDelay=1 -decodeToRenameDelay=1 -decodeWidth=8 +cpu_id=0 defer_registration=false -dispatchWidth=8 -fetchToDecodeDelay=1 -fetchTrapLatency=1 -fetchWidth=8 -forwardComSize=5 -fuPool=system.cpu.fuPool function_trace=false function_trace_start=0 -globalCtrBits=2 -globalHistoryBits=13 -globalPredictorSize=8192 -iewToCommitDelay=1 -iewToDecodeDelay=1 -iewToFetchDelay=1 -iewToRenameDelay=1 -instShiftAmt=2 -issueToExecuteDelay=1 -issueWidth=8 -localCtrBits=2 -localHistoryBits=11 -localHistoryTableSize=2048 -localPredictorSize=2048 max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 -mem=system.cpu.dcache -numIQEntries=64 -numPhysFloatRegs=256 -numPhysIntRegs=256 -numROBEntries=192 -numRobs=1 -numThreads=1 -predType=tournament -renameToDecodeDelay=1 -renameToFetchDelay=1 -renameToIEWDelay=2 -renameToROBDelay=1 -renameWidth=8 -squashWidth=8 +phase=0 +progress_interval=0 system=system -trapLatency=13 -wbDepth=1 -wbWidth=8 workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side icache_port=system.cpu.icache.cpu_side @@ -131,7 +76,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -164,143 +108,6 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] -[system.cpu.fuPool] -type=FUPool -children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 -FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 - -[system.cpu.fuPool.FUList0] -type=FUDesc -children=opList0 -count=6 -opList=system.cpu.fuPool.FUList0.opList0 - -[system.cpu.fuPool.FUList0.opList0] -type=OpDesc -issueLat=1 -opClass=IntAlu -opLat=1 - -[system.cpu.fuPool.FUList1] -type=FUDesc -children=opList0 opList1 -count=2 -opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 - -[system.cpu.fuPool.FUList1.opList0] -type=OpDesc -issueLat=1 -opClass=IntMult -opLat=3 - -[system.cpu.fuPool.FUList1.opList1] -type=OpDesc -issueLat=19 -opClass=IntDiv -opLat=20 - -[system.cpu.fuPool.FUList2] -type=FUDesc -children=opList0 opList1 opList2 -count=4 -opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 - -[system.cpu.fuPool.FUList2.opList0] -type=OpDesc -issueLat=1 -opClass=FloatAdd -opLat=2 - -[system.cpu.fuPool.FUList2.opList1] -type=OpDesc -issueLat=1 -opClass=FloatCmp -opLat=2 - -[system.cpu.fuPool.FUList2.opList2] -type=OpDesc -issueLat=1 -opClass=FloatCvt -opLat=2 - -[system.cpu.fuPool.FUList3] -type=FUDesc -children=opList0 opList1 opList2 -count=2 -opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 - -[system.cpu.fuPool.FUList3.opList0] -type=OpDesc -issueLat=1 -opClass=FloatMult -opLat=4 - -[system.cpu.fuPool.FUList3.opList1] -type=OpDesc -issueLat=12 -opClass=FloatDiv -opLat=12 - -[system.cpu.fuPool.FUList3.opList2] -type=OpDesc -issueLat=24 -opClass=FloatSqrt -opLat=24 - -[system.cpu.fuPool.FUList4] -type=FUDesc -children=opList0 -count=0 -opList=system.cpu.fuPool.FUList4.opList0 - -[system.cpu.fuPool.FUList4.opList0] -type=OpDesc -issueLat=1 -opClass=MemRead -opLat=1 - -[system.cpu.fuPool.FUList5] -type=FUDesc -children=opList0 -count=0 -opList=system.cpu.fuPool.FUList5.opList0 - -[system.cpu.fuPool.FUList5.opList0] -type=OpDesc -issueLat=1 -opClass=MemWrite -opLat=1 - -[system.cpu.fuPool.FUList6] -type=FUDesc -children=opList0 opList1 -count=4 -opList=system.cpu.fuPool.FUList6.opList0 system.cpu.fuPool.FUList6.opList1 - -[system.cpu.fuPool.FUList6.opList0] -type=OpDesc -issueLat=1 -opClass=MemRead -opLat=1 - -[system.cpu.fuPool.FUList6.opList1] -type=OpDesc -issueLat=1 -opClass=MemWrite -opLat=1 - -[system.cpu.fuPool.FUList7] -type=FUDesc -children=opList0 -count=1 -opList=system.cpu.fuPool.FUList7.opList0 - -[system.cpu.fuPool.FUList7.opList0] -type=OpDesc -issueLat=3 -opClass=IprAccess -opLat=3 - [system.cpu.icache] type=BaseCache adaptive_compression=false @@ -308,7 +115,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -348,7 +154,6 @@ assoc=2 block_size=64 compressed_bus=false compression_latency=0 -do_copy=false hash_delay=1 hit_latency=1 latency=1 @@ -384,20 +189,33 @@ mem_side=system.membus.port[1] [system.cpu.toL2Bus] type=Bus bus_id=0 +clock=1000 +responder_set=false +width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side [system.cpu.workload] type=LiveProcess -cmd=hello +cmd=twolf smred +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/simple-timing +egid=100 env= -executable=tests/test-progs/hello/bin/alpha/linux/hello +euid=100 +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf +gid=100 input=cin output=cout +pid=100 +ppid=99 system=system +uid=100 [system.membus] type=Bus bus_id=0 +clock=1000 +responder_set=false +width=64 port=system.physmem.port system.cpu.l2cache.mem_side [system.physmem] @@ -409,6 +227,7 @@ port=system.membus.port[0] [trace] bufsize=0 +cycle=0 dump_on_exit=false file=cout flags= diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out b/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out index f491a3081..c27975bcb 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out +++ b/tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out @@ -19,19 +19,54 @@ mem_mode=atomic [system.membus] type=Bus bus_id=0 +clock=1000 +width=64 +responder_set=false [system.cpu.workload] type=LiveProcess -cmd=hello -executable=tests/test-progs/hello/bin/alpha/linux/hello +cmd=twolf smred +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf input=cin output=cout env= +cwd=build/ALPHA_SE/tests/opt/long/70.twolf/alpha/linux/simple-timing system=system +uid=100 +euid=100 +gid=100 +egid=100 +pid=100 +ppid=99 -[system.cpu.dcache] +[system.cpu] +type=TimingSimpleCPU +max_insts_any_thread=0 +max_insts_all_threads=0 +max_loads_any_thread=0 +max_loads_all_threads=0 +progress_interval=0 +system=system +cpu_id=0 +workload=system.cpu.workload +clock=1 +phase=0 +defer_registration=false +// width not specified +function_trace=false +function_trace_start=0 +// simulate_stalls not specified + +[system.cpu.toL2Bus] +type=Bus +bus_id=0 +clock=1000 +width=64 +responder_set=false + +[system.cpu.icache] type=BaseCache -size=262144 +size=131072 assoc=2 block_size=64 latency=1 @@ -39,7 +74,6 @@ mshrs=10 tgts_per_mshr=5 write_buffers=8 prioritizeRequests=false -do_copy=false protocol=null trace_addr=0 hash_delay=1 @@ -68,214 +102,9 @@ prefetch_use_cpu_id=true prefetch_data_accesses_only=false hit_latency=1 -[system.cpu.fuPool.FUList0.opList0] -type=OpDesc -opClass=IntAlu -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList0] -type=FUDesc -opList=system.cpu.fuPool.FUList0.opList0 -count=6 - -[system.cpu.fuPool.FUList1.opList0] -type=OpDesc -opClass=IntMult -opLat=3 -issueLat=1 - -[system.cpu.fuPool.FUList1.opList1] -type=OpDesc -opClass=IntDiv -opLat=20 -issueLat=19 - -[system.cpu.fuPool.FUList1] -type=FUDesc -opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 -count=2 - -[system.cpu.fuPool.FUList2.opList0] -type=OpDesc -opClass=FloatAdd -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2.opList1] -type=OpDesc -opClass=FloatCmp -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2.opList2] -type=OpDesc -opClass=FloatCvt -opLat=2 -issueLat=1 - -[system.cpu.fuPool.FUList2] -type=FUDesc -opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 -count=4 - -[system.cpu.fuPool.FUList3.opList0] -type=OpDesc -opClass=FloatMult -opLat=4 -issueLat=1 - -[system.cpu.fuPool.FUList3.opList1] -type=OpDesc -opClass=FloatDiv -opLat=12 -issueLat=12 - -[system.cpu.fuPool.FUList3.opList2] -type=OpDesc -opClass=FloatSqrt -opLat=24 -issueLat=24 - -[system.cpu.fuPool.FUList3] -type=FUDesc -opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 -count=2 - -[system.cpu.fuPool.FUList4.opList0] -type=OpDesc -opClass=MemRead -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList4] -type=FUDesc -opList=system.cpu.fuPool.FUList4.opList0 -count=0 - -[system.cpu.fuPool.FUList5.opList0] -type=OpDesc -opClass=MemWrite -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList5] -type=FUDesc -opList=system.cpu.fuPool.FUList5.opList0 -count=0 - -[system.cpu.fuPool.FUList6.opList0] -type=OpDesc -opClass=MemRead -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList6.opList1] -type=OpDesc -opClass=MemWrite -opLat=1 -issueLat=1 - -[system.cpu.fuPool.FUList6] -type=FUDesc -opList=system.cpu.fuPool.FUList6.opList0 system.cpu.fuPool.FUList6.opList1 -count=4 - -[system.cpu.fuPool.FUList7.opList0] -type=OpDesc -opClass=IprAccess -opLat=3 -issueLat=3 - -[system.cpu.fuPool.FUList7] -type=FUDesc -opList=system.cpu.fuPool.FUList7.opList0 -count=1 - -[system.cpu.fuPool] -type=FUPool -FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 - -[system.cpu] -type=DerivO3CPU -clock=1 -numThreads=1 -activity=0 -workload=system.cpu.workload -mem=system.cpu.dcache -checker=null -max_insts_any_thread=0 -max_insts_all_threads=0 -max_loads_any_thread=0 -max_loads_all_threads=0 -cachePorts=200 -decodeToFetchDelay=1 -renameToFetchDelay=1 -iewToFetchDelay=1 -commitToFetchDelay=1 -fetchWidth=8 -renameToDecodeDelay=1 -iewToDecodeDelay=1 -commitToDecodeDelay=1 -fetchToDecodeDelay=1 -decodeWidth=8 -iewToRenameDelay=1 -commitToRenameDelay=1 -decodeToRenameDelay=1 -renameWidth=8 -commitToIEWDelay=1 -renameToIEWDelay=2 -issueToExecuteDelay=1 -dispatchWidth=8 -issueWidth=8 -wbWidth=8 -wbDepth=1 -fuPool=system.cpu.fuPool -iewToCommitDelay=1 -renameToROBDelay=1 -commitWidth=8 -squashWidth=8 -trapLatency=13 -backComSize=5 -forwardComSize=5 -predType=tournament -localPredictorSize=2048 -localCtrBits=2 -localHistoryTableSize=2048 -localHistoryBits=11 -globalPredictorSize=8192 -globalCtrBits=2 -globalHistoryBits=13 -choicePredictorSize=8192 -choiceCtrBits=2 -BTBEntries=4096 -BTBTagSize=16 -RASSize=16 -LQEntries=32 -SQEntries=32 -LFSTSize=1024 -SSITSize=1024 -numPhysIntRegs=256 -numPhysFloatRegs=256 -numIQEntries=64 -numROBEntries=192 -smtNumFetchingThreads=1 -smtFetchPolicy=SingleThread -smtLSQPolicy=Partitioned -smtLSQThreshold=100 -smtIQPolicy=Partitioned -smtIQThreshold=100 -smtROBPolicy=Partitioned -smtROBThreshold=100 -smtCommitPolicy=RoundRobin -instShiftAmt=2 -defer_registration=false -function_trace=false -function_trace_start=0 - -[system.cpu.icache] +[system.cpu.dcache] type=BaseCache -size=131072 +size=262144 assoc=2 block_size=64 latency=1 @@ -283,7 +112,6 @@ mshrs=10 tgts_per_mshr=5 write_buffers=8 prioritizeRequests=false -do_copy=false protocol=null trace_addr=0 hash_delay=1 @@ -322,7 +150,6 @@ mshrs=10 tgts_per_mshr=5 write_buffers=8 prioritizeRequests=false -do_copy=false protocol=null trace_addr=0 hash_delay=1 @@ -351,13 +178,10 @@ 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 +cycle=0 bufsize=0 file=cout dump_on_exit=false @@ -396,8 +220,9 @@ print_cpseq=false print_reg_delta=false pc_symbol=true intel_format=false +legion_lockstep=false trace_system=client -[debug] -break_cycles= +[statsreset] +reset_cycle=0 diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt b/tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt index 5d4f9235a..3926b2de9 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt @@ -1,112 +1,67 @@ ---------- 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.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.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) -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.insertedStores 1221 # Number of stores inserted to the mem dependence unit. +host_inst_rate 460435 # Simulator instruction rate (inst/s) +host_mem_usage 178124 # Number of bytes of host memory used +host_seconds 199.60 # Real time elapsed on the host +host_tick_rate 765898 # Simulator tick rate (ticks/s) 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 -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.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% -system.cpu.commit.COM:committed_per_cycle.max_value 8 -system.cpu.commit.COM:committed_per_cycle.end_dist - -system.cpu.commit.COM:count 5640 # Number of instructions committed -system.cpu.commit.COM:loads 979 # Number of loads committed -system.cpu.commit.COM:membars 0 # Number of memory barriers committed -system.cpu.commit.COM:refs 1791 # Number of memory references committed -system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -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.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.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_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_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_misses 71 # number of WriteReq MSHR misses +sim_insts 91900700 # Number of instructions simulated +sim_seconds 0.000153 # Number of seconds simulated +sim_ticks 152870012 # Number of ticks simulated +system.cpu.dcache.ReadReq_accesses 19995627 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 3765.212314 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2765.212314 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 19995156 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 1773415 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000024 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 471 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_miss_latency 1302415 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000024 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 471 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 6500813 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 3867.178372 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2867.178372 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 6499204 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 6222290 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.000248 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 1609 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_miss_latency 4613290 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.000248 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 1609 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs # 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_blocked_cycles_no_targets # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 12737.673077 # 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_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 4 # 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 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 26496440 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 3844.088942 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 2844.088942 # average overall mshr miss latency +system.cpu.dcache.demand_hits 26494360 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 7995705 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000079 # miss rate for demand accesses +system.cpu.dcache.demand_misses 2080 # 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 5915705 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.000079 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 2080 # 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 26496440 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 3844.088942 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 2844.088942 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency # 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 26494360 # number of overall hits +system.cpu.dcache.overall_miss_latency 7995705 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000079 # miss rate for overall accesses +system.cpu.dcache.overall_misses 2080 # number of overall misses +system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 5915705 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.000079 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 2080 # 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 @@ -118,92 +73,57 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 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.sampled_refs 178 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 103 # number of replacements +system.cpu.dcache.sampled_refs 2080 # 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 1399.324024 # Cycle average of tags in use +system.cpu.dcache.total_refs 26494360 # 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:RunCycles 2158 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 754 # 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.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.IcacheSquashes 148 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 13707 # 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.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.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 6871 -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% -system.cpu.fetch.rateDist.max_value 8 -system.cpu.fetch.rateDist.end_dist - -system.cpu.icache.ReadReq_accesses 1582 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 2.960245 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 1.996885 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1255 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 968 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.206700 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 327 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 6 # number of ReadReq MSHR hits -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_refs 3.909657 # Average number of references to valid blocks. +system.cpu.dcache.writebacks 74 # number of writebacks +system.cpu.icache.ReadReq_accesses 91900701 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 3116.205529 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 2116.205529 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 91892201 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 26487747 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000092 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 8500 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_miss_latency 17987747 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000092 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 8500 # number of ReadReq MSHR misses +system.cpu.icache.avg_blocked_cycles_no_mshrs # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles_no_targets # average number of cycles each access was blocked +system.cpu.icache.avg_refs 10810.847176 # 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 1582 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency -system.cpu.icache.demand_hits 1255 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 968 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.206700 # miss rate for demand accesses -system.cpu.icache.demand_misses 327 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 6 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 641 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.202908 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 321 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 91900701 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 3116.205529 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 2116.205529 # average overall mshr miss latency +system.cpu.icache.demand_hits 91892201 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 26487747 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000092 # miss rate for demand accesses +system.cpu.icache.demand_misses 8500 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 17987747 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000092 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 8500 # 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.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.icache.overall_accesses 1582 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 2.960245 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 1.996885 # average overall mshr miss latency +system.cpu.icache.overall_accesses 91900701 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 3116.205529 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 2116.205529 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 1255 # number of overall hits -system.cpu.icache.overall_miss_latency 968 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.206700 # miss rate for overall accesses -system.cpu.icache.overall_misses 327 # number of overall misses -system.cpu.icache.overall_mshr_hits 6 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 641 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.202908 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 321 # number of overall MSHR misses +system.cpu.icache.overall_hits 91892201 # number of overall hits +system.cpu.icache.overall_miss_latency 26487747 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000092 # miss rate for overall accesses +system.cpu.icache.overall_misses 8500 # number of overall misses +system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 17987747 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000092 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 8500 # 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_misses 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 @@ -215,1726 +135,60 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 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 0 # number of replacements -system.cpu.icache.sampled_refs 321 # Sample count of references to valid blocks. +system.cpu.icache.replacements 6677 # number of replacements +system.cpu.icache.sampled_refs 8500 # 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.total_refs 1255 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1370.015418 # Cycle average of tags in use +system.cpu.icache.total_refs 91892201 # 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: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: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.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.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.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.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 -system.cpu.iew.lsq.thread.0.forwLoads 55 # Number of loads that had data forwarded from stores -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.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.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.iq.ISSUE:FU_type_0.start_dist - (null) 2 0.02% # Type of FU issued - IntAlu 5594 66.69% # 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 1757 20.95% # Type of FU issued - MemWrite 1032 12.30% # 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_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 - 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 - FloatCmp 0 0.00% # attempts to use FU when none available - FloatCvt 0 0.00% # attempts to use FU when none available - 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 76 66.09% # attempts to use FU when none available - MemWrite 38 33.04% # 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 6871 -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% -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.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.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.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.idle_fraction 0 # Percentage of idle cycles +system.cpu.l2cache.ReadReq_accesses 10580 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 2883.751500 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 1878.799057 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 5912 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 13461352 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.441210 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 4668 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 8770234 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.441210 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 4668 # number of ReadReq MSHR misses +system.cpu.l2cache.WriteReqNoAck|Writeback_accesses 74 # number of WriteReqNoAck|Writeback accesses(hits+misses) +system.cpu.l2cache.WriteReqNoAck|Writeback_hits 74 # number of WriteReqNoAck|Writeback hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets # 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 1.282348 # 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_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_accesses 10580 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 2883.751500 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 1878.799057 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 5912 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 13461352 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.441210 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 4668 # 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 8770234 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.441210 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 4668 # 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_avg_mshr_miss_latency 1 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 10654 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 2883.751500 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 1878.799057 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency # 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 5986 # number of overall hits +system.cpu.l2cache.overall_miss_latency 13461352 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.438145 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 4668 # 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 8770234 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.438145 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 4668 # 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 @@ -1947,28 +201,16 @@ 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 4668 # 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 3056.777484 # Cycle average of tags in use +system.cpu.l2cache.total_refs 5986 # 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.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: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: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 -system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 408 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 21 # count of temporary serializing insts renamed -system.cpu.workload.PROG:num_syscalls 17 # Number of system calls +system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles +system.cpu.numCycles 152870012 # number of cpu cycles simulated +system.cpu.num_insts 91900700 # Number of instructions executed +system.cpu.num_refs 26536244 # Number of memory references +system.cpu.workload.PROG:num_syscalls 387 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr b/tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr index 8893caac8..87866a2a5 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr +++ b/tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr @@ -1,3 +1 @@ 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 diff --git a/tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout b/tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout index fbb329a2f..f32f0a972 100644 --- a/tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout +++ b/tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout @@ -1,13 +1,14 @@ -Hello world! -M5 Simulator System -Copyright (c) 2001-2006 -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 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() +TimberWolfSC version:v4.3a date:Mon Jan 25 18:50:36 EST 1988 +Standard Cell Placement and Global Routing Program +Authors: Carl Sechen, Bill Swartz + Yale University + 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 + 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 + 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 + 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 + 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 + 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 +106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 +122 123 124 \ No newline at end of file -- cgit v1.2.3