diff options
author | Steve Reinhardt <steve.reinhardt@amd.com> | 2009-04-21 08:37:50 -0700 |
---|---|---|
committer | Steve Reinhardt <steve.reinhardt@amd.com> | 2009-04-21 08:37:50 -0700 |
commit | 7b2f8e6857c035f6ae1d24abaab41915070705e3 (patch) | |
tree | c9204863c91d80ccdc0c0404993b27b675d80e3d /tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp | |
parent | 03b3925e58505c7781b56888019e2f9ea0b85e56 (diff) | |
download | gem5-7b2f8e6857c035f6ae1d24abaab41915070705e3.tar.xz |
Set up m5threads tests on classic (non-ruby) memory system.
Just one test (40.m5threads-test-atomic) is set up for now.
These tests require that the m5threads SPARC binaries are present
in /dist or in test-progs.
Diffstat (limited to 'tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp')
4 files changed, 2784 insertions, 0 deletions
diff --git a/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/config.ini b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/config.ini new file mode 100644 index 000000000..b1c2caacb --- /dev/null +++ b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/config.ini @@ -0,0 +1,1300 @@ +[root] +type=Root +children=system +dummy=0 + +[system] +type=System +children=cpu0 cpu1 cpu2 cpu3 l2c membus physmem toL2Bus +mem_mode=timing +physmem=system.physmem + +[system.cpu0] +type=DerivO3CPU +children=dcache dtb fuPool icache itb tracer workload +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=0 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu0.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu0.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 +itb=system.cpu0.itb +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 +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 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu0.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu0.workload +dcache_port=system.cpu0.dcache.cpu_side +icache_port=system.cpu0.icache.cpu_side + +[system.cpu0.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=4 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu0.dcache_port +mem_side=system.toL2Bus.port[2] + +[system.cpu0.dtb] +type=SparcTLB +size=64 + +[system.cpu0.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 +FUList=system.cpu0.fuPool.FUList0 system.cpu0.fuPool.FUList1 system.cpu0.fuPool.FUList2 system.cpu0.fuPool.FUList3 system.cpu0.fuPool.FUList4 system.cpu0.fuPool.FUList5 system.cpu0.fuPool.FUList6 system.cpu0.fuPool.FUList7 + +[system.cpu0.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu0.fuPool.FUList0.opList + +[system.cpu0.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu0.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu0.fuPool.FUList1.opList0 system.cpu0.fuPool.FUList1.opList1 + +[system.cpu0.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu0.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu0.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu0.fuPool.FUList2.opList0 system.cpu0.fuPool.FUList2.opList1 system.cpu0.fuPool.FUList2.opList2 + +[system.cpu0.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu0.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu0.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu0.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu0.fuPool.FUList3.opList0 system.cpu0.fuPool.FUList3.opList1 system.cpu0.fuPool.FUList3.opList2 + +[system.cpu0.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu0.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu0.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu0.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu0.fuPool.FUList4.opList + +[system.cpu0.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu0.fuPool.FUList5] +type=FUDesc +children=opList +count=0 +opList=system.cpu0.fuPool.FUList5.opList + +[system.cpu0.fuPool.FUList5.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu0.fuPool.FUList6] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu0.fuPool.FUList6.opList0 system.cpu0.fuPool.FUList6.opList1 + +[system.cpu0.fuPool.FUList6.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu0.fuPool.FUList6.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu0.fuPool.FUList7] +type=FUDesc +children=opList +count=1 +opList=system.cpu0.fuPool.FUList7.opList + +[system.cpu0.fuPool.FUList7.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu0.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=1 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu0.icache_port +mem_side=system.toL2Bus.port[1] + +[system.cpu0.itb] +type=SparcTLB +size=64 + +[system.cpu0.tracer] +type=ExeTracer + +[system.cpu0.workload] +type=LiveProcess +cmd=test_atomic 4 +cwd= +egid=100 +env= +errout=cerr +euid=100 +executable=/dist/m5/regression/test-progs/m5threads/bin/sparc/linux/test_atomic +gid=100 +input=cin +max_stack_size=67108864 +output=cout +pid=100 +ppid=99 +simpoint=0 +system=system +uid=100 + +[system.cpu1] +type=DerivO3CPU +children=dcache dtb fuPool icache itb tracer +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=1 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu1.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu1.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 +itb=system.cpu1.itb +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 +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 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu1.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu0.workload +dcache_port=system.cpu1.dcache.cpu_side +icache_port=system.cpu1.icache.cpu_side + +[system.cpu1.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=4 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu1.dcache_port +mem_side=system.toL2Bus.port[4] + +[system.cpu1.dtb] +type=SparcTLB +size=64 + +[system.cpu1.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 +FUList=system.cpu1.fuPool.FUList0 system.cpu1.fuPool.FUList1 system.cpu1.fuPool.FUList2 system.cpu1.fuPool.FUList3 system.cpu1.fuPool.FUList4 system.cpu1.fuPool.FUList5 system.cpu1.fuPool.FUList6 system.cpu1.fuPool.FUList7 + +[system.cpu1.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu1.fuPool.FUList0.opList + +[system.cpu1.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu1.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu1.fuPool.FUList1.opList0 system.cpu1.fuPool.FUList1.opList1 + +[system.cpu1.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu1.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu1.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu1.fuPool.FUList2.opList0 system.cpu1.fuPool.FUList2.opList1 system.cpu1.fuPool.FUList2.opList2 + +[system.cpu1.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu1.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu1.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu1.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu1.fuPool.FUList3.opList0 system.cpu1.fuPool.FUList3.opList1 system.cpu1.fuPool.FUList3.opList2 + +[system.cpu1.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu1.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu1.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu1.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu1.fuPool.FUList4.opList + +[system.cpu1.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu1.fuPool.FUList5] +type=FUDesc +children=opList +count=0 +opList=system.cpu1.fuPool.FUList5.opList + +[system.cpu1.fuPool.FUList5.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu1.fuPool.FUList6] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu1.fuPool.FUList6.opList0 system.cpu1.fuPool.FUList6.opList1 + +[system.cpu1.fuPool.FUList6.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu1.fuPool.FUList6.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu1.fuPool.FUList7] +type=FUDesc +children=opList +count=1 +opList=system.cpu1.fuPool.FUList7.opList + +[system.cpu1.fuPool.FUList7.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu1.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=1 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu1.icache_port +mem_side=system.toL2Bus.port[3] + +[system.cpu1.itb] +type=SparcTLB +size=64 + +[system.cpu1.tracer] +type=ExeTracer + +[system.cpu2] +type=DerivO3CPU +children=dcache dtb fuPool icache itb tracer +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=2 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu2.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu2.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 +itb=system.cpu2.itb +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 +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 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu2.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu0.workload +dcache_port=system.cpu2.dcache.cpu_side +icache_port=system.cpu2.icache.cpu_side + +[system.cpu2.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=4 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu2.dcache_port +mem_side=system.toL2Bus.port[6] + +[system.cpu2.dtb] +type=SparcTLB +size=64 + +[system.cpu2.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 +FUList=system.cpu2.fuPool.FUList0 system.cpu2.fuPool.FUList1 system.cpu2.fuPool.FUList2 system.cpu2.fuPool.FUList3 system.cpu2.fuPool.FUList4 system.cpu2.fuPool.FUList5 system.cpu2.fuPool.FUList6 system.cpu2.fuPool.FUList7 + +[system.cpu2.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu2.fuPool.FUList0.opList + +[system.cpu2.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu2.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu2.fuPool.FUList1.opList0 system.cpu2.fuPool.FUList1.opList1 + +[system.cpu2.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu2.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu2.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu2.fuPool.FUList2.opList0 system.cpu2.fuPool.FUList2.opList1 system.cpu2.fuPool.FUList2.opList2 + +[system.cpu2.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu2.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu2.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu2.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu2.fuPool.FUList3.opList0 system.cpu2.fuPool.FUList3.opList1 system.cpu2.fuPool.FUList3.opList2 + +[system.cpu2.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu2.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu2.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu2.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu2.fuPool.FUList4.opList + +[system.cpu2.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu2.fuPool.FUList5] +type=FUDesc +children=opList +count=0 +opList=system.cpu2.fuPool.FUList5.opList + +[system.cpu2.fuPool.FUList5.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu2.fuPool.FUList6] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu2.fuPool.FUList6.opList0 system.cpu2.fuPool.FUList6.opList1 + +[system.cpu2.fuPool.FUList6.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu2.fuPool.FUList6.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu2.fuPool.FUList7] +type=FUDesc +children=opList +count=1 +opList=system.cpu2.fuPool.FUList7.opList + +[system.cpu2.fuPool.FUList7.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu2.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=1 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu2.icache_port +mem_side=system.toL2Bus.port[5] + +[system.cpu2.itb] +type=SparcTLB +size=64 + +[system.cpu2.tracer] +type=ExeTracer + +[system.cpu3] +type=DerivO3CPU +children=dcache dtb fuPool icache itb tracer +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=3 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu3.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu3.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 +itb=system.cpu3.itb +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 +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 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu3.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu0.workload +dcache_port=system.cpu3.dcache.cpu_side +icache_port=system.cpu3.icache.cpu_side + +[system.cpu3.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=4 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu3.dcache_port +mem_side=system.toL2Bus.port[8] + +[system.cpu3.dtb] +type=SparcTLB +size=64 + +[system.cpu3.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 +FUList=system.cpu3.fuPool.FUList0 system.cpu3.fuPool.FUList1 system.cpu3.fuPool.FUList2 system.cpu3.fuPool.FUList3 system.cpu3.fuPool.FUList4 system.cpu3.fuPool.FUList5 system.cpu3.fuPool.FUList6 system.cpu3.fuPool.FUList7 + +[system.cpu3.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu3.fuPool.FUList0.opList + +[system.cpu3.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu3.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu3.fuPool.FUList1.opList0 system.cpu3.fuPool.FUList1.opList1 + +[system.cpu3.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu3.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu3.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu3.fuPool.FUList2.opList0 system.cpu3.fuPool.FUList2.opList1 system.cpu3.fuPool.FUList2.opList2 + +[system.cpu3.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu3.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu3.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu3.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu3.fuPool.FUList3.opList0 system.cpu3.fuPool.FUList3.opList1 system.cpu3.fuPool.FUList3.opList2 + +[system.cpu3.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu3.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu3.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu3.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu3.fuPool.FUList4.opList + +[system.cpu3.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu3.fuPool.FUList5] +type=FUDesc +children=opList +count=0 +opList=system.cpu3.fuPool.FUList5.opList + +[system.cpu3.fuPool.FUList5.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu3.fuPool.FUList6] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu3.fuPool.FUList6.opList0 system.cpu3.fuPool.FUList6.opList1 + +[system.cpu3.fuPool.FUList6.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu3.fuPool.FUList6.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu3.fuPool.FUList7] +type=FUDesc +children=opList +count=1 +opList=system.cpu3.fuPool.FUList7.opList + +[system.cpu3.fuPool.FUList7.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu3.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=1 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=1000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=4 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=32768 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu3.icache_port +mem_side=system.toL2Bus.port[7] + +[system.cpu3.itb] +type=SparcTLB +size=64 + +[system.cpu3.tracer] +type=ExeTracer + +[system.l2c] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=8 +block_size=64 +cpu_side_filter_ranges= +hash_delay=1 +latency=10000 +max_miss_count=0 +mem_side_filter_ranges= +mshrs=92 +prefetch_cache_check_push=true +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=100000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=4194304 +subblock_size=0 +tgts_per_mshr=16 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.toL2Bus.port[0] +mem_side=system.membus.port[0] + +[system.membus] +type=Bus +block_size=64 +bus_id=0 +clock=1000 +header_cycles=1 +responder_set=false +width=64 +port=system.l2c.mem_side system.physmem.port[0] + +[system.physmem] +type=PhysicalMemory +file= +latency=30000 +latency_var=0 +null=false +range=0:134217727 +zero=false +port=system.membus.port[1] + +[system.toL2Bus] +type=Bus +block_size=64 +bus_id=0 +clock=1000 +header_cycles=1 +responder_set=false +width=64 +port=system.l2c.cpu_side system.cpu0.icache.mem_side system.cpu0.dcache.mem_side system.cpu1.icache.mem_side system.cpu1.dcache.mem_side system.cpu2.icache.mem_side system.cpu2.dcache.mem_side system.cpu3.icache.mem_side system.cpu3.dcache.mem_side + diff --git a/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simerr b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simerr new file mode 100644 index 000000000..eabe42249 --- /dev/null +++ b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simerr @@ -0,0 +1,3 @@ +warn: Sockets disabled, not accepting gdb connections +For more information see: http://www.m5sim.org/warn/d946bea6 +hack: be nice to actually delete the event here diff --git a/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simout b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simout new file mode 100644 index 000000000..fca385548 --- /dev/null +++ b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/simout @@ -0,0 +1,87 @@ +M5 Simulator System + +Copyright (c) 2001-2008 +The Regents of The University of Michigan +All Rights Reserved + + +M5 compiled Apr 17 2009 00:22:56 +M5 revision 35b1dc26772f 6041 default qtip tip m5threads-base-regressions.diff +M5 started Apr 17 2009 00:29:37 +M5 executing on zizzer +command line: build/SPARC_SE/m5.opt -d build/SPARC_SE/tests/opt/quick/40.m5threads-test-atomic/sparc/linux/o3-timing-mp -re tests/run.py build/SPARC_SE/tests/opt/quick/40.m5threads-test-atomic/sparc/linux/o3-timing-mp +Global frequency set at 1000000000000 ticks per second +info: Entering event queue @ 0. Starting simulation... +Init done +[Iteration 1, Thread 1] Got lock +[Iteration 1, Thread 1] Critical section done, previously next=0, now next=1 +[Iteration 1, Thread 2] Got lock +[Iteration 1, Thread 2] Critical section done, previously next=1, now next=2 +[Iteration 1, Thread 3] Got lock +[Iteration 1, Thread 3] Critical section done, previously next=2, now next=3 +Iteration 1 completed +[Iteration 2, Thread 3] Got lock +[Iteration 2, Thread 3] Critical section done, previously next=0, now next=3 +[Iteration 2, Thread 1] Got lock +[Iteration 2, Thread 1] Critical section done, previously next=3, now next=1 +[Iteration 2, Thread 2] Got lock +[Iteration 2, Thread 2] Critical section done, previously next=1, now next=2 +Iteration 2 completed +[Iteration 3, Thread 2] Got lock +[Iteration 3, Thread 2] Critical section done, previously next=0, now next=2 +[Iteration 3, Thread 1] Got lock +[Iteration 3, Thread 1] Critical section done, previously next=2, now next=1 +[Iteration 3, Thread 3] Got lock +[Iteration 3, Thread 3] Critical section done, previously next=1, now next=3 +Iteration 3 completed +[Iteration 4, Thread 3] Got lock +[Iteration 4, Thread 3] Critical section done, previously next=0, now next=3 +[Iteration 4, Thread 1] Got lock +[Iteration 4, Thread 1] Critical section done, previously next=3, now next=1 +[Iteration 4, Thread 2] Got lock +[Iteration 4, Thread 2] Critical section done, previously next=1, now next=2 +Iteration 4 completed +[Iteration 5, Thread 3] Got lock +[Iteration 5, Thread 3] Critical section done, previously next=0, now next=3 +[Iteration 5, Thread 2] Got lock +[Iteration 5, Thread 2] Critical section done, previously next=3, now next=2 +[Iteration 5, Thread 1] Got lock +[Iteration 5, Thread 1] Critical section done, previously next=2, now next=1 +Iteration 5 completed +[Iteration 6, Thread 1] Got lock +[Iteration 6, Thread 1] Critical section done, previously next=0, now next=1 +[Iteration 6, Thread 3] Got lock +[Iteration 6, Thread 3] Critical section done, previously next=1, now next=3 +[Iteration 6, Thread 2] Got lock +[Iteration 6, Thread 2] Critical section done, previously next=3, now next=2 +Iteration 6 completed +[Iteration 7, Thread 1] Got lock +[Iteration 7, Thread 1] Critical section done, previously next=0, now next=1 +[Iteration 7, Thread 3] Got lock +[Iteration 7, Thread 3] Critical section done, previously next=1, now next=3 +[Iteration 7, Thread 2] Got lock +[Iteration 7, Thread 2] Critical section done, previously next=3, now next=2 +Iteration 7 completed +[Iteration 8, Thread 1] Got lock +[Iteration 8, Thread 1] Critical section done, previously next=0, now next=1 +[Iteration 8, Thread 2] Got lock +[Iteration 8, Thread 2] Critical section done, previously next=1, now next=2 +[Iteration 8, Thread 3] Got lock +[Iteration 8, Thread 3] Critical section done, previously next=2, now next=3 +Iteration 8 completed +[Iteration 9, Thread 2] Got lock +[Iteration 9, Thread 2] Critical section done, previously next=0, now next=2 +[Iteration 9, Thread 3] Got lock +[Iteration 9, Thread 3] Critical section done, previously next=2, now next=3 +[Iteration 9, Thread 1] Got lock +[Iteration 9, Thread 1] Critical section done, previously next=3, now next=1 +Iteration 9 completed +[Iteration 10, Thread 2] Got lock +[Iteration 10, Thread 2] Critical section done, previously next=0, now next=2 +[Iteration 10, Thread 1] Got lock +[Iteration 10, Thread 1] Critical section done, previously next=2, now next=1 +[Iteration 10, Thread 3] Got lock +[Iteration 10, Thread 3] Critical section done, previously next=1, now next=3 +Iteration 10 completed +PASSED :-) +Exiting @ tick 220484500 because target called exit() diff --git a/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/stats.txt b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/stats.txt new file mode 100644 index 000000000..0689a00e0 --- /dev/null +++ b/tests/quick/40.m5threads-test-atomic/ref/sparc/linux/o3-timing-mp/stats.txt @@ -0,0 +1,1394 @@ + +---------- Begin Simulation Statistics ---------- +host_inst_rate 28911 # Simulator instruction rate (inst/s) +host_mem_usage 217084 # Number of bytes of host memory used +host_seconds 15.18 # Real time elapsed on the host +host_tick_rate 14522493 # Simulator tick rate (ticks/s) +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 438923 # Number of instructions simulated +sim_seconds 0.000220 # Number of seconds simulated +sim_ticks 220484500 # Number of ticks simulated +system.cpu0.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu0.BPredUnit.BTBHits 54549 # Number of BTB hits +system.cpu0.BPredUnit.BTBLookups 70955 # Number of BTB lookups +system.cpu0.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu0.BPredUnit.condIncorrect 31037 # Number of conditional branches incorrect +system.cpu0.BPredUnit.condPredicted 79925 # Number of conditional branches predicted +system.cpu0.BPredUnit.lookups 79925 # Number of BP lookups +system.cpu0.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. +system.cpu0.commit.COM:branches 25657 # Number of branches committed +system.cpu0.commit.COM:bw_lim_events 567 # number cycles where commit BW limit reached +system.cpu0.commit.COM:bw_limited 0 # number of insts not committed due to BW limits +system.cpu0.commit.COM:committed_per_cycle::samples 355685 # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::underflows 0 0.00% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::0-1 269749 75.84% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::1-2 56588 15.91% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::2-3 24519 6.89% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::3-4 1287 0.36% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::4-5 786 0.22% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::5-6 567 0.16% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::6-7 1608 0.45% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::7-8 14 0.00% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::8 567 0.16% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::overflows 0 0.00% # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::total 355685 # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::mean 0.364783 # Number of insts commited each cycle +system.cpu0.commit.COM:committed_per_cycle::stdev 0.822342 # Number of insts commited each cycle +system.cpu0.commit.COM:count 129748 # Number of instructions committed +system.cpu0.commit.COM:loads 30551 # Number of loads committed +system.cpu0.commit.COM:membars 8310 # Number of memory barriers committed +system.cpu0.commit.COM:refs 41937 # Number of memory references committed +system.cpu0.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu0.commit.branchMispredicts 31037 # The number of times a branch was mispredicted +system.cpu0.commit.commitCommittedInsts 129748 # The number of committed instructions +system.cpu0.commit.commitNonSpecStalls 9029 # The number of times commit has been forced to stall to communicate backwards +system.cpu0.commit.commitSquashedInsts 140741 # The number of squashed insts skipped by commit +system.cpu0.committedInsts 104996 # Number of Instructions Simulated +system.cpu0.committedInsts_total 104996 # Number of Instructions Simulated +system.cpu0.cpi 3.832270 # CPI: Cycles Per Instruction +system.cpu0.cpi_total 3.832270 # CPI: Total CPI of All Threads +system.cpu0.dcache.ReadReq_accesses 29224 # number of ReadReq accesses(hits+misses) +system.cpu0.dcache.ReadReq_avg_miss_latency 18192.118227 # average ReadReq miss latency +system.cpu0.dcache.ReadReq_avg_mshr_miss_latency 15806.818182 # average ReadReq mshr miss latency +system.cpu0.dcache.ReadReq_hits 29021 # number of ReadReq hits +system.cpu0.dcache.ReadReq_miss_latency 3693000 # number of ReadReq miss cycles +system.cpu0.dcache.ReadReq_miss_rate 0.006946 # miss rate for ReadReq accesses +system.cpu0.dcache.ReadReq_misses 203 # number of ReadReq misses +system.cpu0.dcache.ReadReq_mshr_hits 27 # number of ReadReq MSHR hits +system.cpu0.dcache.ReadReq_mshr_miss_latency 2782000 # number of ReadReq MSHR miss cycles +system.cpu0.dcache.ReadReq_mshr_miss_rate 0.006022 # mshr miss rate for ReadReq accesses +system.cpu0.dcache.ReadReq_mshr_misses 176 # number of ReadReq MSHR misses +system.cpu0.dcache.SwapReq_accesses 73 # number of SwapReq accesses(hits+misses) +system.cpu0.dcache.SwapReq_avg_miss_latency 21093.220339 # average SwapReq miss latency +system.cpu0.dcache.SwapReq_avg_mshr_miss_latency 22239.583333 # average SwapReq mshr miss latency +system.cpu0.dcache.SwapReq_hits 14 # number of SwapReq hits +system.cpu0.dcache.SwapReq_miss_latency 1244500 # number of SwapReq miss cycles +system.cpu0.dcache.SwapReq_miss_rate 0.808219 # miss rate for SwapReq accesses +system.cpu0.dcache.SwapReq_misses 59 # number of SwapReq misses +system.cpu0.dcache.SwapReq_mshr_hits 11 # number of SwapReq MSHR hits +system.cpu0.dcache.SwapReq_mshr_miss_latency 1067500 # number of SwapReq MSHR miss cycles +system.cpu0.dcache.SwapReq_mshr_miss_rate 0.657534 # mshr miss rate for SwapReq accesses +system.cpu0.dcache.SwapReq_mshr_misses 48 # number of SwapReq MSHR misses +system.cpu0.dcache.WriteReq_accesses 11313 # number of WriteReq accesses(hits+misses) +system.cpu0.dcache.WriteReq_avg_miss_latency 23258.064516 # average WriteReq miss latency +system.cpu0.dcache.WriteReq_avg_mshr_miss_latency 14768.867925 # average WriteReq mshr miss latency +system.cpu0.dcache.WriteReq_hits 11189 # number of WriteReq hits +system.cpu0.dcache.WriteReq_miss_latency 2884000 # number of WriteReq miss cycles +system.cpu0.dcache.WriteReq_miss_rate 0.010961 # miss rate for WriteReq accesses +system.cpu0.dcache.WriteReq_misses 124 # number of WriteReq misses +system.cpu0.dcache.WriteReq_mshr_hits 18 # number of WriteReq MSHR hits +system.cpu0.dcache.WriteReq_mshr_miss_latency 1565500 # number of WriteReq MSHR miss cycles +system.cpu0.dcache.WriteReq_mshr_miss_rate 0.009370 # mshr miss rate for WriteReq accesses +system.cpu0.dcache.WriteReq_mshr_misses 106 # number of WriteReq MSHR misses +system.cpu0.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu0.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu0.dcache.avg_refs 735.966667 # Average number of references to valid blocks. +system.cpu0.dcache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu0.dcache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu0.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu0.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu0.dcache.cache_copies 0 # number of cache copies performed +system.cpu0.dcache.demand_accesses 40537 # number of demand (read+write) accesses +system.cpu0.dcache.demand_avg_miss_latency 20113.149847 # average overall miss latency +system.cpu0.dcache.demand_avg_mshr_miss_latency 15416.666667 # average overall mshr miss latency +system.cpu0.dcache.demand_hits 40210 # number of demand (read+write) hits +system.cpu0.dcache.demand_miss_latency 6577000 # number of demand (read+write) miss cycles +system.cpu0.dcache.demand_miss_rate 0.008067 # miss rate for demand accesses +system.cpu0.dcache.demand_misses 327 # number of demand (read+write) misses +system.cpu0.dcache.demand_mshr_hits 45 # number of demand (read+write) MSHR hits +system.cpu0.dcache.demand_mshr_miss_latency 4347500 # number of demand (read+write) MSHR miss cycles +system.cpu0.dcache.demand_mshr_miss_rate 0.006957 # mshr miss rate for demand accesses +system.cpu0.dcache.demand_mshr_misses 282 # number of demand (read+write) MSHR misses +system.cpu0.dcache.fast_writes 0 # number of fast writes performed +system.cpu0.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu0.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu0.dcache.overall_accesses 40537 # number of overall (read+write) accesses +system.cpu0.dcache.overall_avg_miss_latency 20113.149847 # average overall miss latency +system.cpu0.dcache.overall_avg_mshr_miss_latency 15416.666667 # average overall mshr miss latency +system.cpu0.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu0.dcache.overall_hits 40210 # number of overall hits +system.cpu0.dcache.overall_miss_latency 6577000 # number of overall miss cycles +system.cpu0.dcache.overall_miss_rate 0.008067 # miss rate for overall accesses +system.cpu0.dcache.overall_misses 327 # number of overall misses +system.cpu0.dcache.overall_mshr_hits 45 # number of overall MSHR hits +system.cpu0.dcache.overall_mshr_miss_latency 4347500 # number of overall MSHR miss cycles +system.cpu0.dcache.overall_mshr_miss_rate 0.006957 # mshr miss rate for overall accesses +system.cpu0.dcache.overall_mshr_misses 282 # number of overall MSHR misses +system.cpu0.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu0.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu0.dcache.replacements 2 # number of replacements +system.cpu0.dcache.sampled_refs 30 # Sample count of references to valid blocks. +system.cpu0.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu0.dcache.tagsinuse 28.280349 # Cycle average of tags in use +system.cpu0.dcache.total_refs 22079 # Total number of references to valid blocks. +system.cpu0.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu0.dcache.writebacks 1 # number of writebacks +system.cpu0.decode.DECODE:BlockedCycles 31385 # Number of cycles decode is blocked +system.cpu0.decode.DECODE:DecodedInsts 367055 # Number of instructions handled by decode +system.cpu0.decode.DECODE:IdleCycles 175688 # Number of cycles decode is idle +system.cpu0.decode.DECODE:RunCycles 148454 # Number of cycles decode is running +system.cpu0.decode.DECODE:SquashCycles 34938 # Number of cycles decode is squashing +system.cpu0.decode.DECODE:UnblockCycles 158 # Number of cycles decode is unblocking +system.cpu0.fetch.Branches 79925 # Number of branches that fetch encountered +system.cpu0.fetch.CacheLines 83600 # Number of cache lines fetched +system.cpu0.fetch.Cycles 244044 # Number of cycles fetch has run and was not squashing or blocked +system.cpu0.fetch.IcacheSquashes 9987 # Number of outstanding Icache misses that were squashed +system.cpu0.fetch.Insts 413648 # Number of instructions fetch has processed +system.cpu0.fetch.SquashCycles 31188 # Number of cycles fetch has spent squashing +system.cpu0.fetch.branchRate 0.198634 # Number of branch fetches per cycle +system.cpu0.fetch.icacheStallCycles 83600 # Number of cycles fetch is stalled on an Icache miss +system.cpu0.fetch.predictedBranches 54549 # Number of branches that fetch has predicted taken +system.cpu0.fetch.rate 1.028021 # Number of inst fetches per cycle +system.cpu0.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) +system.cpu0.fetch.rateDist.samples 399788 +system.cpu0.fetch.rateDist.min_value 0 + 0 239369 5987.40% + 1 86666 2167.80% + 2 18970 474.50% + 3 18363 459.32% + 4 2993 74.86% + 5 13233 331.00% + 6 1665 41.65% + 7 2406 60.18% + 8 16123 403.29% +system.cpu0.fetch.rateDist.max_value 8 +system.cpu0.fetch.rateDist.end_dist + +system.cpu0.icache.ReadReq_accesses 83600 # number of ReadReq accesses(hits+misses) +system.cpu0.icache.ReadReq_avg_miss_latency 14035.763411 # average ReadReq miss latency +system.cpu0.icache.ReadReq_avg_mshr_miss_latency 11552.755906 # average ReadReq mshr miss latency +system.cpu0.icache.ReadReq_hits 82873 # number of ReadReq hits +system.cpu0.icache.ReadReq_miss_latency 10204000 # number of ReadReq miss cycles +system.cpu0.icache.ReadReq_miss_rate 0.008696 # miss rate for ReadReq accesses +system.cpu0.icache.ReadReq_misses 727 # number of ReadReq misses +system.cpu0.icache.ReadReq_mshr_hits 92 # number of ReadReq MSHR hits +system.cpu0.icache.ReadReq_mshr_miss_latency 7336000 # number of ReadReq MSHR miss cycles +system.cpu0.icache.ReadReq_mshr_miss_rate 0.007596 # mshr miss rate for ReadReq accesses +system.cpu0.icache.ReadReq_mshr_misses 635 # number of ReadReq MSHR misses +system.cpu0.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu0.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu0.icache.avg_refs 130.508661 # Average number of references to valid blocks. +system.cpu0.icache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu0.icache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu0.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu0.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu0.icache.cache_copies 0 # number of cache copies performed +system.cpu0.icache.demand_accesses 83600 # number of demand (read+write) accesses +system.cpu0.icache.demand_avg_miss_latency 14035.763411 # average overall miss latency +system.cpu0.icache.demand_avg_mshr_miss_latency 11552.755906 # average overall mshr miss latency +system.cpu0.icache.demand_hits 82873 # number of demand (read+write) hits +system.cpu0.icache.demand_miss_latency 10204000 # number of demand (read+write) miss cycles +system.cpu0.icache.demand_miss_rate 0.008696 # miss rate for demand accesses +system.cpu0.icache.demand_misses 727 # number of demand (read+write) misses +system.cpu0.icache.demand_mshr_hits 92 # number of demand (read+write) MSHR hits +system.cpu0.icache.demand_mshr_miss_latency 7336000 # number of demand (read+write) MSHR miss cycles +system.cpu0.icache.demand_mshr_miss_rate 0.007596 # mshr miss rate for demand accesses +system.cpu0.icache.demand_mshr_misses 635 # number of demand (read+write) MSHR misses +system.cpu0.icache.fast_writes 0 # number of fast writes performed +system.cpu0.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu0.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu0.icache.overall_accesses 83600 # number of overall (read+write) accesses +system.cpu0.icache.overall_avg_miss_latency 14035.763411 # average overall miss latency +system.cpu0.icache.overall_avg_mshr_miss_latency 11552.755906 # average overall mshr miss latency +system.cpu0.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu0.icache.overall_hits 82873 # number of overall hits +system.cpu0.icache.overall_miss_latency 10204000 # number of overall miss cycles +system.cpu0.icache.overall_miss_rate 0.008696 # miss rate for overall accesses +system.cpu0.icache.overall_misses 727 # number of overall misses +system.cpu0.icache.overall_mshr_hits 92 # number of overall MSHR hits +system.cpu0.icache.overall_mshr_miss_latency 7336000 # number of overall MSHR miss cycles +system.cpu0.icache.overall_mshr_miss_rate 0.007596 # mshr miss rate for overall accesses +system.cpu0.icache.overall_mshr_misses 635 # number of overall MSHR misses +system.cpu0.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu0.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu0.icache.replacements 524 # number of replacements +system.cpu0.icache.sampled_refs 635 # Sample count of references to valid blocks. +system.cpu0.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu0.icache.tagsinuse 95.921890 # Cycle average of tags in use +system.cpu0.icache.total_refs 82873 # Total number of references to valid blocks. +system.cpu0.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu0.icache.writebacks 0 # number of writebacks +system.cpu0.idleCycles 2585 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu0.iew.EXEC:branches 37656 # Number of branches executed +system.cpu0.iew.EXEC:nop 48476 # number of nop insts executed +system.cpu0.iew.EXEC:rate 0.417965 # Inst execution rate +system.cpu0.iew.EXEC:refs 49837 # number of memory reference insts executed +system.cpu0.iew.EXEC:stores 13176 # Number of stores executed +system.cpu0.iew.EXEC:swp 0 # number of swp insts executed +system.cpu0.iew.WB:consumers 81944 # num instructions consuming a value +system.cpu0.iew.WB:count 164449 # cumulative count of insts written-back +system.cpu0.iew.WB:fanout 0.932149 # average fanout of values written-back +system.cpu0.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ +system.cpu0.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu0.iew.WB:producers 76384 # num instructions producing a value +system.cpu0.iew.WB:rate 0.408698 # insts written-back per cycle +system.cpu0.iew.WB:sent 164672 # cumulative count of insts sent to commit +system.cpu0.iew.branchMispredicts 31697 # Number of branch mispredicts detected at execute +system.cpu0.iew.iewBlockCycles 0 # Number of cycles IEW is blocking +system.cpu0.iew.iewDispLoadInsts 41051 # Number of dispatched load instructions +system.cpu0.iew.iewDispNonSpecInsts 9374 # Number of dispatched non-speculative instructions +system.cpu0.iew.iewDispSquashedInsts 4077 # Number of squashed instructions skipped by dispatch +system.cpu0.iew.iewDispStoreInsts 22447 # Number of dispatched store instructions +system.cpu0.iew.iewDispatchedInsts 270509 # Number of instructions dispatched to IQ +system.cpu0.iew.iewExecLoadInsts 36661 # Number of load instructions executed +system.cpu0.iew.iewExecSquashedInsts 34703 # Number of squashed instructions skipped in execute +system.cpu0.iew.iewExecutedInsts 168178 # Number of executed instructions +system.cpu0.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall +system.cpu0.iew.iewIdleCycles 0 # Number of cycles IEW is idle +system.cpu0.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall +system.cpu0.iew.iewSquashCycles 34938 # Number of cycles IEW is squashing +system.cpu0.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking +system.cpu0.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding +system.cpu0.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked +system.cpu0.iew.lsq.thread.0.forwLoads 7417 # Number of loads that had data forwarded from stores +system.cpu0.iew.lsq.thread.0.ignoredResponses 11 # Number of memory responses ignored because the instruction is squashed +system.cpu0.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu0.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu0.iew.lsq.thread.0.memOrderViolation 646 # Number of memory ordering violations +system.cpu0.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled +system.cpu0.iew.lsq.thread.0.squashedLoads 10500 # Number of loads squashed +system.cpu0.iew.lsq.thread.0.squashedStores 11061 # Number of stores squashed +system.cpu0.iew.memOrderViolationEvents 646 # Number of memory order violations +system.cpu0.iew.predictedNotTakenIncorrect 856 # Number of branches that were predicted not taken incorrectly +system.cpu0.iew.predictedTakenIncorrect 30841 # Number of branches that were predicted taken incorrectly +system.cpu0.ipc 0.260942 # IPC: Instructions Per Cycle +system.cpu0.ipc_total 0.260942 # IPC: Total IPC of All Threads +system.cpu0.iq.ISSUE:FU_type_0 202881 # Type of FU issued +system.cpu0.iq.ISSUE:FU_type_0.start_dist + No_OpClass 0 0.00% # Type of FU issued + IntAlu 142871 70.42% # Type of FU issued + IntMult 0 0.00% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 0 0.00% # 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 46166 22.76% # Type of FU issued + MemWrite 13844 6.82% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu0.iq.ISSUE:FU_type_0.end_dist +system.cpu0.iq.ISSUE:fu_busy_cnt 173 # FU busy when requested +system.cpu0.iq.ISSUE:fu_busy_rate 0.000853 # FU busy rate (busy events/executed inst) +system.cpu0.iq.ISSUE:fu_full.start_dist + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 23 13.29% # 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 11 6.36% # attempts to use FU when none available + MemWrite 139 80.35% # 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.cpu0.iq.ISSUE:fu_full.end_dist +system.cpu0.iq.ISSUE:issued_per_cycle::samples 399788 +system.cpu0.iq.ISSUE:issued_per_cycle::min_value 0 +system.cpu0.iq.ISSUE:issued_per_cycle::underflows 0 0.00% +system.cpu0.iq.ISSUE:issued_per_cycle::0-1 279763 69.98% +system.cpu0.iq.ISSUE:issued_per_cycle::1-2 72065 18.03% +system.cpu0.iq.ISSUE:issued_per_cycle::2-3 24983 6.25% +system.cpu0.iq.ISSUE:issued_per_cycle::3-4 14756 3.69% +system.cpu0.iq.ISSUE:issued_per_cycle::4-5 5406 1.35% +system.cpu0.iq.ISSUE:issued_per_cycle::5-6 2153 0.54% +system.cpu0.iq.ISSUE:issued_per_cycle::6-7 473 0.12% +system.cpu0.iq.ISSUE:issued_per_cycle::7-8 157 0.04% +system.cpu0.iq.ISSUE:issued_per_cycle::8 32 0.01% +system.cpu0.iq.ISSUE:issued_per_cycle::overflows 0 0.00% +system.cpu0.iq.ISSUE:issued_per_cycle::total 399788 +system.cpu0.iq.ISSUE:issued_per_cycle::max_value 8 +system.cpu0.iq.ISSUE:issued_per_cycle::mean 0.507471 +system.cpu0.iq.ISSUE:issued_per_cycle::stdev 0.960639 +system.cpu0.iq.ISSUE:rate 0.504211 # Inst issue rate +system.cpu0.iq.iqInstsAdded 204299 # Number of instructions added to the IQ (excludes non-spec) +system.cpu0.iq.iqInstsIssued 202881 # Number of instructions issued +system.cpu0.iq.iqNonSpecInstsAdded 17734 # Number of non-speculative instructions added to the IQ +system.cpu0.iq.iqSquashedInstsExamined 79448 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu0.iq.iqSquashedInstsIssued 3 # Number of squashed instructions issued +system.cpu0.iq.iqSquashedNonSpecRemoved 8705 # Number of squashed non-spec instructions that were removed +system.cpu0.iq.iqSquashedOperandsExamined 34402 # Number of squashed operands that are examined and possibly removed from graph +system.cpu0.memDep0.conflictingLoads 7616 # Number of conflicting loads. +system.cpu0.memDep0.conflictingStores 83 # Number of conflicting stores. +system.cpu0.memDep0.insertedLoads 41051 # Number of loads inserted to the mem dependence unit. +system.cpu0.memDep0.insertedStores 22447 # Number of stores inserted to the mem dependence unit. +system.cpu0.numCycles 402373 # number of cpu cycles simulated +system.cpu0.rename.RENAME:CommittedMaps 87918 # Number of HB maps that are committed +system.cpu0.rename.RENAME:IdleCycles 188663 # Number of cycles rename is idle +system.cpu0.rename.RENAME:LSQFullEvents 1 # Number of times rename has blocked due to LSQ full +system.cpu0.rename.RENAME:RenameLookups 464430 # Number of register rename lookups that rename has made +system.cpu0.rename.RENAME:RenamedInsts 298607 # Number of instructions processed by rename +system.cpu0.rename.RENAME:RenamedOperands 213629 # Number of destination operands rename has renamed +system.cpu0.rename.RENAME:RunCycles 135723 # Number of cycles rename is running +system.cpu0.rename.RENAME:SquashCycles 34938 # Number of cycles rename is squashing +system.cpu0.rename.RENAME:UnblockCycles 563 # Number of cycles rename is unblocking +system.cpu0.rename.RENAME:UndoneMaps 125711 # Number of HB maps that are undone due to squashing +system.cpu0.rename.RENAME:serializeStallCycles 30736 # count of cycles rename stalled for serializing inst +system.cpu0.rename.RENAME:serializingInsts 9619 # count of serializing insts renamed +system.cpu0.rename.RENAME:skidInsts 36235 # count of insts added to the skid buffer +system.cpu0.rename.RENAME:tempSerializingInsts 9747 # count of temporary serializing insts renamed +system.cpu0.timesIdled 284 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu0.workload.PROG:num_syscalls 89 # Number of system calls +system.cpu1.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu1.BPredUnit.BTBHits 53615 # Number of BTB hits +system.cpu1.BPredUnit.BTBLookups 73516 # Number of BTB lookups +system.cpu1.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu1.BPredUnit.condIncorrect 30904 # Number of conditional branches incorrect +system.cpu1.BPredUnit.condPredicted 87311 # Number of conditional branches predicted +system.cpu1.BPredUnit.lookups 87311 # Number of BP lookups +system.cpu1.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. +system.cpu1.commit.COM:branches 25648 # Number of branches committed +system.cpu1.commit.COM:bw_lim_events 570 # number cycles where commit BW limit reached +system.cpu1.commit.COM:bw_limited 0 # number of insts not committed due to BW limits +system.cpu1.commit.COM:committed_per_cycle::samples 355192 # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::underflows 0 0.00% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::0-1 269483 75.87% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::1-2 56385 15.87% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::2-3 24471 6.89% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::3-4 1296 0.36% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::4-5 793 0.22% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::5-6 569 0.16% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::6-7 1611 0.45% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::7-8 14 0.00% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::8 570 0.16% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::overflows 0 0.00% # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::total 355192 # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::mean 0.364749 # Number of insts commited each cycle +system.cpu1.commit.COM:committed_per_cycle::stdev 0.823293 # Number of insts commited each cycle +system.cpu1.commit.COM:count 129556 # Number of instructions committed +system.cpu1.commit.COM:loads 30466 # Number of loads committed +system.cpu1.commit.COM:membars 8390 # Number of memory barriers committed +system.cpu1.commit.COM:refs 41763 # Number of memory references committed +system.cpu1.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu1.commit.branchMispredicts 30904 # The number of times a branch was mispredicted +system.cpu1.commit.commitCommittedInsts 129556 # The number of committed instructions +system.cpu1.commit.commitNonSpecStalls 9104 # The number of times commit has been forced to stall to communicate backwards +system.cpu1.commit.commitSquashedInsts 142883 # The number of squashed insts skipped by commit +system.cpu1.committedInsts 104728 # Number of Instructions Simulated +system.cpu1.committedInsts_total 104728 # Number of Instructions Simulated +system.cpu1.cpi 3.839040 # CPI: Cycles Per Instruction +system.cpu1.cpi_total 3.839040 # CPI: Total CPI of All Threads +system.cpu1.dcache.ReadReq_accesses 29199 # number of ReadReq accesses(hits+misses) +system.cpu1.dcache.ReadReq_avg_miss_latency 17894.736842 # average ReadReq miss latency +system.cpu1.dcache.ReadReq_avg_mshr_miss_latency 15858.433735 # average ReadReq mshr miss latency +system.cpu1.dcache.ReadReq_hits 29009 # number of ReadReq hits +system.cpu1.dcache.ReadReq_miss_latency 3400000 # number of ReadReq miss cycles +system.cpu1.dcache.ReadReq_miss_rate 0.006507 # miss rate for ReadReq accesses +system.cpu1.dcache.ReadReq_misses 190 # number of ReadReq misses +system.cpu1.dcache.ReadReq_mshr_hits 24 # number of ReadReq MSHR hits +system.cpu1.dcache.ReadReq_mshr_miss_latency 2632500 # number of ReadReq MSHR miss cycles +system.cpu1.dcache.ReadReq_mshr_miss_rate 0.005685 # mshr miss rate for ReadReq accesses +system.cpu1.dcache.ReadReq_mshr_misses 166 # number of ReadReq MSHR misses +system.cpu1.dcache.SwapReq_accesses 68 # number of SwapReq accesses(hits+misses) +system.cpu1.dcache.SwapReq_avg_miss_latency 22592.592593 # average SwapReq miss latency +system.cpu1.dcache.SwapReq_avg_mshr_miss_latency 24604.651163 # average SwapReq mshr miss latency +system.cpu1.dcache.SwapReq_hits 14 # number of SwapReq hits +system.cpu1.dcache.SwapReq_miss_latency 1220000 # number of SwapReq miss cycles +system.cpu1.dcache.SwapReq_miss_rate 0.794118 # miss rate for SwapReq accesses +system.cpu1.dcache.SwapReq_misses 54 # number of SwapReq misses +system.cpu1.dcache.SwapReq_mshr_hits 11 # number of SwapReq MSHR hits +system.cpu1.dcache.SwapReq_mshr_miss_latency 1058000 # number of SwapReq MSHR miss cycles +system.cpu1.dcache.SwapReq_mshr_miss_rate 0.632353 # mshr miss rate for SwapReq accesses +system.cpu1.dcache.SwapReq_mshr_misses 43 # number of SwapReq MSHR misses +system.cpu1.dcache.WriteReq_accesses 11229 # number of WriteReq accesses(hits+misses) +system.cpu1.dcache.WriteReq_avg_miss_latency 23876.984127 # average WriteReq miss latency +system.cpu1.dcache.WriteReq_avg_mshr_miss_latency 15889.908257 # average WriteReq mshr miss latency +system.cpu1.dcache.WriteReq_hits 11103 # number of WriteReq hits +system.cpu1.dcache.WriteReq_miss_latency 3008500 # number of WriteReq miss cycles +system.cpu1.dcache.WriteReq_miss_rate 0.011221 # miss rate for WriteReq accesses +system.cpu1.dcache.WriteReq_misses 126 # number of WriteReq misses +system.cpu1.dcache.WriteReq_mshr_hits 17 # number of WriteReq MSHR hits +system.cpu1.dcache.WriteReq_mshr_miss_latency 1732000 # number of WriteReq MSHR miss cycles +system.cpu1.dcache.WriteReq_mshr_miss_rate 0.009707 # mshr miss rate for WriteReq accesses +system.cpu1.dcache.WriteReq_mshr_misses 109 # number of WriteReq MSHR misses +system.cpu1.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu1.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu1.dcache.avg_refs 709.516129 # Average number of references to valid blocks. +system.cpu1.dcache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu1.dcache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu1.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu1.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu1.dcache.cache_copies 0 # number of cache copies performed +system.cpu1.dcache.demand_accesses 40428 # number of demand (read+write) accesses +system.cpu1.dcache.demand_avg_miss_latency 20280.063291 # average overall miss latency +system.cpu1.dcache.demand_avg_mshr_miss_latency 15870.909091 # average overall mshr miss latency +system.cpu1.dcache.demand_hits 40112 # number of demand (read+write) hits +system.cpu1.dcache.demand_miss_latency 6408500 # number of demand (read+write) miss cycles +system.cpu1.dcache.demand_miss_rate 0.007816 # miss rate for demand accesses +system.cpu1.dcache.demand_misses 316 # number of demand (read+write) misses +system.cpu1.dcache.demand_mshr_hits 41 # number of demand (read+write) MSHR hits +system.cpu1.dcache.demand_mshr_miss_latency 4364500 # number of demand (read+write) MSHR miss cycles +system.cpu1.dcache.demand_mshr_miss_rate 0.006802 # mshr miss rate for demand accesses +system.cpu1.dcache.demand_mshr_misses 275 # number of demand (read+write) MSHR misses +system.cpu1.dcache.fast_writes 0 # number of fast writes performed +system.cpu1.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu1.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu1.dcache.overall_accesses 40428 # number of overall (read+write) accesses +system.cpu1.dcache.overall_avg_miss_latency 20280.063291 # average overall miss latency +system.cpu1.dcache.overall_avg_mshr_miss_latency 15870.909091 # average overall mshr miss latency +system.cpu1.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu1.dcache.overall_hits 40112 # number of overall hits +system.cpu1.dcache.overall_miss_latency 6408500 # number of overall miss cycles +system.cpu1.dcache.overall_miss_rate 0.007816 # miss rate for overall accesses +system.cpu1.dcache.overall_misses 316 # number of overall misses +system.cpu1.dcache.overall_mshr_hits 41 # number of overall MSHR hits +system.cpu1.dcache.overall_mshr_miss_latency 4364500 # number of overall MSHR miss cycles +system.cpu1.dcache.overall_mshr_miss_rate 0.006802 # mshr miss rate for overall accesses +system.cpu1.dcache.overall_mshr_misses 275 # number of overall MSHR misses +system.cpu1.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu1.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu1.dcache.replacements 2 # number of replacements +system.cpu1.dcache.sampled_refs 31 # Sample count of references to valid blocks. +system.cpu1.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu1.dcache.tagsinuse 27.424102 # Cycle average of tags in use +system.cpu1.dcache.total_refs 21995 # Total number of references to valid blocks. +system.cpu1.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu1.dcache.writebacks 1 # number of writebacks +system.cpu1.decode.DECODE:BlockedCycles 31080 # Number of cycles decode is blocked +system.cpu1.decode.DECODE:DecodedInsts 370792 # Number of instructions handled by decode +system.cpu1.decode.DECODE:IdleCycles 175773 # Number of cycles decode is idle +system.cpu1.decode.DECODE:RunCycles 148188 # Number of cycles decode is running +system.cpu1.decode.DECODE:SquashCycles 35250 # Number of cycles decode is squashing +system.cpu1.decode.DECODE:UnblockCycles 151 # Number of cycles decode is unblocking +system.cpu1.fetch.Branches 87311 # Number of branches that fetch encountered +system.cpu1.fetch.CacheLines 83559 # Number of cache lines fetched +system.cpu1.fetch.Cycles 243794 # Number of cycles fetch has run and was not squashing or blocked +system.cpu1.fetch.IcacheSquashes 9908 # Number of outstanding Icache misses that were squashed +system.cpu1.fetch.Insts 428254 # Number of instructions fetch has processed +system.cpu1.fetch.SquashCycles 31054 # Number of cycles fetch has spent squashing +system.cpu1.fetch.branchRate 0.217162 # Number of branch fetches per cycle +system.cpu1.fetch.icacheStallCycles 83559 # Number of cycles fetch is stalled on an Icache miss +system.cpu1.fetch.predictedBranches 53615 # Number of branches that fetch has predicted taken +system.cpu1.fetch.rate 1.065163 # Number of inst fetches per cycle +system.cpu1.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) +system.cpu1.fetch.rateDist.samples 399545 +system.cpu1.fetch.rateDist.min_value 0 + 0 239335 5990.19% + 1 86108 2155.15% + 2 18621 466.06% + 3 13625 341.01% + 4 2965 74.21% + 5 17436 436.40% + 6 2130 53.31% + 7 2391 59.84% + 8 16934 423.83% +system.cpu1.fetch.rateDist.max_value 8 +system.cpu1.fetch.rateDist.end_dist + +system.cpu1.icache.ReadReq_accesses 83559 # number of ReadReq accesses(hits+misses) +system.cpu1.icache.ReadReq_avg_miss_latency 13800.273598 # average ReadReq miss latency +system.cpu1.icache.ReadReq_avg_mshr_miss_latency 11301.412873 # average ReadReq mshr miss latency +system.cpu1.icache.ReadReq_hits 82828 # number of ReadReq hits +system.cpu1.icache.ReadReq_miss_latency 10088000 # number of ReadReq miss cycles +system.cpu1.icache.ReadReq_miss_rate 0.008748 # miss rate for ReadReq accesses +system.cpu1.icache.ReadReq_misses 731 # number of ReadReq misses +system.cpu1.icache.ReadReq_mshr_hits 94 # number of ReadReq MSHR hits +system.cpu1.icache.ReadReq_mshr_miss_latency 7199000 # number of ReadReq MSHR miss cycles +system.cpu1.icache.ReadReq_mshr_miss_rate 0.007623 # mshr miss rate for ReadReq accesses +system.cpu1.icache.ReadReq_mshr_misses 637 # number of ReadReq MSHR misses +system.cpu1.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu1.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu1.icache.avg_refs 130.028257 # Average number of references to valid blocks. +system.cpu1.icache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu1.icache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu1.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu1.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu1.icache.cache_copies 0 # number of cache copies performed +system.cpu1.icache.demand_accesses 83559 # number of demand (read+write) accesses +system.cpu1.icache.demand_avg_miss_latency 13800.273598 # average overall miss latency +system.cpu1.icache.demand_avg_mshr_miss_latency 11301.412873 # average overall mshr miss latency +system.cpu1.icache.demand_hits 82828 # number of demand (read+write) hits +system.cpu1.icache.demand_miss_latency 10088000 # number of demand (read+write) miss cycles +system.cpu1.icache.demand_miss_rate 0.008748 # miss rate for demand accesses +system.cpu1.icache.demand_misses 731 # number of demand (read+write) misses +system.cpu1.icache.demand_mshr_hits 94 # number of demand (read+write) MSHR hits +system.cpu1.icache.demand_mshr_miss_latency 7199000 # number of demand (read+write) MSHR miss cycles +system.cpu1.icache.demand_mshr_miss_rate 0.007623 # mshr miss rate for demand accesses +system.cpu1.icache.demand_mshr_misses 637 # number of demand (read+write) MSHR misses +system.cpu1.icache.fast_writes 0 # number of fast writes performed +system.cpu1.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu1.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu1.icache.overall_accesses 83559 # number of overall (read+write) accesses +system.cpu1.icache.overall_avg_miss_latency 13800.273598 # average overall miss latency +system.cpu1.icache.overall_avg_mshr_miss_latency 11301.412873 # average overall mshr miss latency +system.cpu1.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu1.icache.overall_hits 82828 # number of overall hits +system.cpu1.icache.overall_miss_latency 10088000 # number of overall miss cycles +system.cpu1.icache.overall_miss_rate 0.008748 # miss rate for overall accesses +system.cpu1.icache.overall_misses 731 # number of overall misses +system.cpu1.icache.overall_mshr_hits 94 # number of overall MSHR hits +system.cpu1.icache.overall_mshr_miss_latency 7199000 # number of overall MSHR miss cycles +system.cpu1.icache.overall_mshr_miss_rate 0.007623 # mshr miss rate for overall accesses +system.cpu1.icache.overall_mshr_misses 637 # number of overall MSHR misses +system.cpu1.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu1.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu1.icache.replacements 525 # number of replacements +system.cpu1.icache.sampled_refs 637 # Sample count of references to valid blocks. +system.cpu1.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu1.icache.tagsinuse 94.025224 # Cycle average of tags in use +system.cpu1.icache.total_refs 82828 # Total number of references to valid blocks. +system.cpu1.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu1.icache.writebacks 0 # number of writebacks +system.cpu1.idleCycles 2510 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu1.iew.EXEC:branches 37542 # Number of branches executed +system.cpu1.iew.EXEC:nop 48922 # number of nop insts executed +system.cpu1.iew.EXEC:rate 0.416853 # Inst execution rate +system.cpu1.iew.EXEC:refs 49631 # number of memory reference insts executed +system.cpu1.iew.EXEC:stores 13081 # Number of stores executed +system.cpu1.iew.EXEC:swp 0 # number of swp insts executed +system.cpu1.iew.WB:consumers 81643 # num instructions consuming a value +system.cpu1.iew.WB:count 163892 # cumulative count of insts written-back +system.cpu1.iew.WB:fanout 0.931911 # average fanout of values written-back +system.cpu1.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ +system.cpu1.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu1.iew.WB:producers 76084 # num instructions producing a value +system.cpu1.iew.WB:rate 0.407636 # insts written-back per cycle +system.cpu1.iew.WB:sent 164117 # cumulative count of insts sent to commit +system.cpu1.iew.branchMispredicts 31560 # Number of branch mispredicts detected at execute +system.cpu1.iew.iewBlockCycles 0 # Number of cycles IEW is blocking +system.cpu1.iew.iewDispLoadInsts 41822 # Number of dispatched load instructions +system.cpu1.iew.iewDispNonSpecInsts 9263 # Number of dispatched non-speculative instructions +system.cpu1.iew.iewDispSquashedInsts 4013 # Number of squashed instructions skipped by dispatch +system.cpu1.iew.iewDispStoreInsts 22260 # Number of dispatched store instructions +system.cpu1.iew.iewDispatchedInsts 272458 # Number of instructions dispatched to IQ +system.cpu1.iew.iewExecLoadInsts 36550 # Number of load instructions executed +system.cpu1.iew.iewExecSquashedInsts 35100 # Number of squashed instructions skipped in execute +system.cpu1.iew.iewExecutedInsts 167598 # Number of executed instructions +system.cpu1.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall +system.cpu1.iew.iewIdleCycles 0 # Number of cycles IEW is idle +system.cpu1.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall +system.cpu1.iew.iewSquashCycles 35250 # Number of cycles IEW is squashing +system.cpu1.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking +system.cpu1.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding +system.cpu1.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked +system.cpu1.iew.lsq.thread.0.forwLoads 7331 # Number of loads that had data forwarded from stores +system.cpu1.iew.lsq.thread.0.ignoredResponses 11 # Number of memory responses ignored because the instruction is squashed +system.cpu1.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu1.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu1.iew.lsq.thread.0.memOrderViolation 641 # Number of memory ordering violations +system.cpu1.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled +system.cpu1.iew.lsq.thread.0.squashedLoads 11356 # Number of loads squashed +system.cpu1.iew.lsq.thread.0.squashedStores 10963 # Number of stores squashed +system.cpu1.iew.memOrderViolationEvents 641 # Number of memory order violations +system.cpu1.iew.predictedNotTakenIncorrect 844 # Number of branches that were predicted not taken incorrectly +system.cpu1.iew.predictedTakenIncorrect 30716 # Number of branches that were predicted taken incorrectly +system.cpu1.ipc 0.260482 # IPC: Instructions Per Cycle +system.cpu1.ipc_total 0.260482 # IPC: Total IPC of All Threads +system.cpu1.iq.ISSUE:FU_type_0 202698 # Type of FU issued +system.cpu1.iq.ISSUE:FU_type_0.start_dist + No_OpClass 0 0.00% # Type of FU issued + IntAlu 142808 70.45% # Type of FU issued + IntMult 0 0.00% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 0 0.00% # 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 46141 22.76% # Type of FU issued + MemWrite 13749 6.78% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu1.iq.ISSUE:FU_type_0.end_dist +system.cpu1.iq.ISSUE:fu_busy_cnt 173 # FU busy when requested +system.cpu1.iq.ISSUE:fu_busy_rate 0.000853 # FU busy rate (busy events/executed inst) +system.cpu1.iq.ISSUE:fu_full.start_dist + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 23 13.29% # 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 11 6.36% # attempts to use FU when none available + MemWrite 139 80.35% # 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.cpu1.iq.ISSUE:fu_full.end_dist +system.cpu1.iq.ISSUE:issued_per_cycle::samples 399545 +system.cpu1.iq.ISSUE:issued_per_cycle::min_value 0 +system.cpu1.iq.ISSUE:issued_per_cycle::underflows 0 0.00% +system.cpu1.iq.ISSUE:issued_per_cycle::0-1 279804 70.03% +system.cpu1.iq.ISSUE:issued_per_cycle::1-2 71581 17.92% +system.cpu1.iq.ISSUE:issued_per_cycle::2-3 25282 6.33% +system.cpu1.iq.ISSUE:issued_per_cycle::3-4 14650 3.67% +system.cpu1.iq.ISSUE:issued_per_cycle::4-5 5420 1.36% +system.cpu1.iq.ISSUE:issued_per_cycle::5-6 2146 0.54% +system.cpu1.iq.ISSUE:issued_per_cycle::6-7 473 0.12% +system.cpu1.iq.ISSUE:issued_per_cycle::7-8 157 0.04% +system.cpu1.iq.ISSUE:issued_per_cycle::8 32 0.01% +system.cpu1.iq.ISSUE:issued_per_cycle::overflows 0 0.00% +system.cpu1.iq.ISSUE:issued_per_cycle::total 399545 +system.cpu1.iq.ISSUE:issued_per_cycle::max_value 8 +system.cpu1.iq.ISSUE:issued_per_cycle::mean 0.507322 +system.cpu1.iq.ISSUE:issued_per_cycle::stdev 0.960841 +system.cpu1.iq.ISSUE:rate 0.504155 # Inst issue rate +system.cpu1.iq.iqInstsAdded 205352 # Number of instructions added to the IQ (excludes non-spec) +system.cpu1.iq.iqInstsIssued 202698 # Number of instructions issued +system.cpu1.iq.iqNonSpecInstsAdded 18184 # Number of non-speculative instructions added to the IQ +system.cpu1.iq.iqSquashedInstsExamined 81269 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu1.iq.iqSquashedInstsIssued 3 # Number of squashed instructions issued +system.cpu1.iq.iqSquashedNonSpecRemoved 9080 # Number of squashed non-spec instructions that were removed +system.cpu1.iq.iqSquashedOperandsExamined 37464 # Number of squashed operands that are examined and possibly removed from graph +system.cpu1.memDep0.conflictingLoads 8438 # Number of conflicting loads. +system.cpu1.memDep0.conflictingStores 93 # Number of conflicting stores. +system.cpu1.memDep0.insertedLoads 41822 # Number of loads inserted to the mem dependence unit. +system.cpu1.memDep0.insertedStores 22260 # Number of stores inserted to the mem dependence unit. +system.cpu1.numCycles 402055 # number of cpu cycles simulated +system.cpu1.rename.RENAME:CommittedMaps 87658 # Number of HB maps that are committed +system.cpu1.rename.RENAME:IdleCycles 188598 # Number of cycles rename is idle +system.cpu1.rename.RENAME:LSQFullEvents 1 # Number of times rename has blocked due to LSQ full +system.cpu1.rename.RENAME:RenameLookups 466261 # Number of register rename lookups that rename has made +system.cpu1.rename.RENAME:RenamedInsts 302877 # Number of instructions processed by rename +system.cpu1.rename.RENAME:RenamedOperands 213560 # Number of destination operands rename has renamed +system.cpu1.rename.RENAME:RunCycles 135600 # Number of cycles rename is running +system.cpu1.rename.RENAME:SquashCycles 35250 # Number of cycles rename is squashing +system.cpu1.rename.RENAME:UnblockCycles 564 # Number of cycles rename is unblocking +system.cpu1.rename.RENAME:UndoneMaps 125902 # Number of HB maps that are undone due to squashing +system.cpu1.rename.RENAME:serializeStallCycles 30430 # count of cycles rename stalled for serializing inst +system.cpu1.rename.RENAME:serializingInsts 9493 # count of serializing insts renamed +system.cpu1.rename.RENAME:skidInsts 36017 # count of insts added to the skid buffer +system.cpu1.rename.RENAME:tempSerializingInsts 9618 # count of temporary serializing insts renamed +system.cpu1.timesIdled 280 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu2.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu2.BPredUnit.BTBHits 44906 # Number of BTB hits +system.cpu2.BPredUnit.BTBLookups 70035 # Number of BTB lookups +system.cpu2.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu2.BPredUnit.condIncorrect 43027 # Number of conditional branches incorrect +system.cpu2.BPredUnit.condPredicted 71789 # Number of conditional branches predicted +system.cpu2.BPredUnit.lookups 71789 # Number of BP lookups +system.cpu2.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. +system.cpu2.commit.COM:branches 23667 # Number of branches committed +system.cpu2.commit.COM:bw_lim_events 171 # number cycles where commit BW limit reached +system.cpu2.commit.COM:bw_limited 0 # number of insts not committed due to BW limits +system.cpu2.commit.COM:committed_per_cycle::samples 377940 # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::underflows 0 0.00% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::0-1 268475 71.04% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::1-2 84750 22.42% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::2-3 22813 6.04% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::3-4 683 0.18% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::4-5 329 0.09% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::5-6 229 0.06% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::6-7 453 0.12% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::7-8 37 0.01% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::8 171 0.05% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::overflows 0 0.00% # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::total 377940 # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::mean 0.368394 # Number of insts commited each cycle +system.cpu2.commit.COM:committed_per_cycle::stdev 0.672472 # Number of insts commited each cycle +system.cpu2.commit.COM:count 139231 # Number of instructions committed +system.cpu2.commit.COM:loads 42546 # Number of loads committed +system.cpu2.commit.COM:membars 84 # Number of memory barriers committed +system.cpu2.commit.COM:refs 64325 # Number of memory references committed +system.cpu2.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu2.commit.branchMispredicts 43027 # The number of times a branch was mispredicted +system.cpu2.commit.commitCommittedInsts 139231 # The number of committed instructions +system.cpu2.commit.commitNonSpecStalls 559 # The number of times commit has been forced to stall to communicate backwards +system.cpu2.commit.commitSquashedInsts 182418 # The number of squashed insts skipped by commit +system.cpu2.committedInsts 118749 # Number of Instructions Simulated +system.cpu2.committedInsts_total 118749 # Number of Instructions Simulated +system.cpu2.cpi 3.713463 # CPI: Cycles Per Instruction +system.cpu2.cpi_total 3.713463 # CPI: Total CPI of All Threads +system.cpu2.dcache.ReadReq_accesses 24971 # number of ReadReq accesses(hits+misses) +system.cpu2.dcache.ReadReq_avg_miss_latency 30599.025974 # average ReadReq miss latency +system.cpu2.dcache.ReadReq_avg_mshr_miss_latency 23979.820628 # average ReadReq mshr miss latency +system.cpu2.dcache.ReadReq_hits 24663 # number of ReadReq hits +system.cpu2.dcache.ReadReq_miss_latency 9424500 # number of ReadReq miss cycles +system.cpu2.dcache.ReadReq_miss_rate 0.012334 # miss rate for ReadReq accesses +system.cpu2.dcache.ReadReq_misses 308 # number of ReadReq misses +system.cpu2.dcache.ReadReq_mshr_hits 85 # number of ReadReq MSHR hits +system.cpu2.dcache.ReadReq_mshr_miss_latency 5347500 # number of ReadReq MSHR miss cycles +system.cpu2.dcache.ReadReq_mshr_miss_rate 0.008930 # mshr miss rate for ReadReq accesses +system.cpu2.dcache.ReadReq_mshr_misses 223 # number of ReadReq MSHR misses +system.cpu2.dcache.SwapReq_accesses 42 # number of SwapReq accesses(hits+misses) +system.cpu2.dcache.SwapReq_avg_miss_latency 15538.461538 # average SwapReq miss latency +system.cpu2.dcache.SwapReq_avg_mshr_miss_latency 12538.461538 # average SwapReq mshr miss latency +system.cpu2.dcache.SwapReq_hits 16 # number of SwapReq hits +system.cpu2.dcache.SwapReq_miss_latency 404000 # number of SwapReq miss cycles +system.cpu2.dcache.SwapReq_miss_rate 0.619048 # miss rate for SwapReq accesses +system.cpu2.dcache.SwapReq_misses 26 # number of SwapReq misses +system.cpu2.dcache.SwapReq_mshr_miss_latency 326000 # number of SwapReq MSHR miss cycles +system.cpu2.dcache.SwapReq_mshr_miss_rate 0.619048 # mshr miss rate for SwapReq accesses +system.cpu2.dcache.SwapReq_mshr_misses 26 # number of SwapReq MSHR misses +system.cpu2.dcache.WriteReq_accesses 21737 # number of WriteReq accesses(hits+misses) +system.cpu2.dcache.WriteReq_avg_miss_latency 45735.701906 # average WriteReq miss latency +system.cpu2.dcache.WriteReq_avg_mshr_miss_latency 39151.515152 # average WriteReq mshr miss latency +system.cpu2.dcache.WriteReq_hits 21160 # number of WriteReq hits +system.cpu2.dcache.WriteReq_miss_latency 26389500 # number of WriteReq miss cycles +system.cpu2.dcache.WriteReq_miss_rate 0.026545 # miss rate for WriteReq accesses +system.cpu2.dcache.WriteReq_misses 577 # number of WriteReq misses +system.cpu2.dcache.WriteReq_mshr_hits 379 # number of WriteReq MSHR hits +system.cpu2.dcache.WriteReq_mshr_miss_latency 7752000 # number of WriteReq MSHR miss cycles +system.cpu2.dcache.WriteReq_mshr_miss_rate 0.009109 # mshr miss rate for WriteReq accesses +system.cpu2.dcache.WriteReq_mshr_misses 198 # number of WriteReq MSHR misses +system.cpu2.dcache.avg_blocked_cycles_no_mshrs 22000 # average number of cycles each access was blocked +system.cpu2.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu2.dcache.avg_refs 168.806818 # Average number of references to valid blocks. +system.cpu2.dcache.blocked_no_mshrs 3 # number of cycles access was blocked +system.cpu2.dcache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu2.dcache.blocked_cycles_no_mshrs 66000 # number of cycles access was blocked +system.cpu2.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu2.dcache.cache_copies 0 # number of cache copies performed +system.cpu2.dcache.demand_accesses 46708 # number of demand (read+write) accesses +system.cpu2.dcache.demand_avg_miss_latency 40467.796610 # average overall miss latency +system.cpu2.dcache.demand_avg_mshr_miss_latency 31115.201900 # average overall mshr miss latency +system.cpu2.dcache.demand_hits 45823 # number of demand (read+write) hits +system.cpu2.dcache.demand_miss_latency 35814000 # number of demand (read+write) miss cycles +system.cpu2.dcache.demand_miss_rate 0.018948 # miss rate for demand accesses +system.cpu2.dcache.demand_misses 885 # number of demand (read+write) misses +system.cpu2.dcache.demand_mshr_hits 464 # number of demand (read+write) MSHR hits +system.cpu2.dcache.demand_mshr_miss_latency 13099500 # number of demand (read+write) MSHR miss cycles +system.cpu2.dcache.demand_mshr_miss_rate 0.009013 # mshr miss rate for demand accesses +system.cpu2.dcache.demand_mshr_misses 421 # number of demand (read+write) MSHR misses +system.cpu2.dcache.fast_writes 0 # number of fast writes performed +system.cpu2.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu2.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu2.dcache.overall_accesses 46708 # number of overall (read+write) accesses +system.cpu2.dcache.overall_avg_miss_latency 40467.796610 # average overall miss latency +system.cpu2.dcache.overall_avg_mshr_miss_latency 31115.201900 # average overall mshr miss latency +system.cpu2.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu2.dcache.overall_hits 45823 # number of overall hits +system.cpu2.dcache.overall_miss_latency 35814000 # number of overall miss cycles +system.cpu2.dcache.overall_miss_rate 0.018948 # miss rate for overall accesses +system.cpu2.dcache.overall_misses 885 # number of overall misses +system.cpu2.dcache.overall_mshr_hits 464 # number of overall MSHR hits +system.cpu2.dcache.overall_mshr_miss_latency 13099500 # number of overall MSHR miss cycles +system.cpu2.dcache.overall_mshr_miss_rate 0.009013 # mshr miss rate for overall accesses +system.cpu2.dcache.overall_mshr_misses 421 # number of overall MSHR misses +system.cpu2.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu2.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu2.dcache.replacements 10 # number of replacements +system.cpu2.dcache.sampled_refs 176 # Sample count of references to valid blocks. +system.cpu2.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu2.dcache.tagsinuse 142.409748 # Cycle average of tags in use +system.cpu2.dcache.total_refs 29710 # Total number of references to valid blocks. +system.cpu2.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu2.dcache.writebacks 6 # number of writebacks +system.cpu2.decode.DECODE:BlockedCycles 54269 # Number of cycles decode is blocked +system.cpu2.decode.DECODE:DecodedInsts 458617 # Number of instructions handled by decode +system.cpu2.decode.DECODE:IdleCycles 166605 # Number of cycles decode is idle +system.cpu2.decode.DECODE:RunCycles 156987 # Number of cycles decode is running +system.cpu2.decode.DECODE:SquashCycles 44866 # Number of cycles decode is squashing +system.cpu2.decode.DECODE:UnblockCycles 79 # Number of cycles decode is unblocking +system.cpu2.fetch.Branches 71789 # Number of branches that fetch encountered +system.cpu2.fetch.CacheLines 88443 # Number of cache lines fetched +system.cpu2.fetch.Cycles 246728 # Number of cycles fetch has run and was not squashing or blocked +system.cpu2.fetch.IcacheSquashes 21058 # Number of outstanding Icache misses that were squashed +system.cpu2.fetch.Insts 464576 # Number of instructions fetch has processed +system.cpu2.fetch.SquashCycles 43179 # Number of cycles fetch has spent squashing +system.cpu2.fetch.branchRate 0.162798 # Number of branch fetches per cycle +system.cpu2.fetch.icacheStallCycles 88443 # Number of cycles fetch is stalled on an Icache miss +system.cpu2.fetch.predictedBranches 44906 # Number of branches that fetch has predicted taken +system.cpu2.fetch.rate 1.053532 # Number of inst fetches per cycle +system.cpu2.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) +system.cpu2.fetch.rateDist.samples 422806 +system.cpu2.fetch.rateDist.min_value 0 + 0 264558 6257.20% + 1 88255 2087.36% + 2 1011 23.91% + 3 21518 508.93% + 4 1067 25.24% + 5 21230 502.12% + 6 652 15.42% + 7 705 16.67% + 8 23810 563.14% +system.cpu2.fetch.rateDist.max_value 8 +system.cpu2.fetch.rateDist.end_dist + +system.cpu2.icache.ReadReq_accesses 88443 # number of ReadReq accesses(hits+misses) +system.cpu2.icache.ReadReq_avg_miss_latency 37054.535017 # average ReadReq miss latency +system.cpu2.icache.ReadReq_avg_mshr_miss_latency 35099.253731 # average ReadReq mshr miss latency +system.cpu2.icache.ReadReq_hits 87572 # number of ReadReq hits +system.cpu2.icache.ReadReq_miss_latency 32274500 # number of ReadReq miss cycles +system.cpu2.icache.ReadReq_miss_rate 0.009848 # miss rate for ReadReq accesses +system.cpu2.icache.ReadReq_misses 871 # number of ReadReq misses +system.cpu2.icache.ReadReq_mshr_hits 201 # number of ReadReq MSHR hits +system.cpu2.icache.ReadReq_mshr_miss_latency 23516500 # number of ReadReq MSHR miss cycles +system.cpu2.icache.ReadReq_mshr_miss_rate 0.007576 # mshr miss rate for ReadReq accesses +system.cpu2.icache.ReadReq_mshr_misses 670 # number of ReadReq MSHR misses +system.cpu2.icache.avg_blocked_cycles_no_mshrs 10250 # average number of cycles each access was blocked +system.cpu2.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu2.icache.avg_refs 130.899851 # Average number of references to valid blocks. +system.cpu2.icache.blocked_no_mshrs 2 # number of cycles access was blocked +system.cpu2.icache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu2.icache.blocked_cycles_no_mshrs 20500 # number of cycles access was blocked +system.cpu2.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu2.icache.cache_copies 0 # number of cache copies performed +system.cpu2.icache.demand_accesses 88443 # number of demand (read+write) accesses +system.cpu2.icache.demand_avg_miss_latency 37054.535017 # average overall miss latency +system.cpu2.icache.demand_avg_mshr_miss_latency 35099.253731 # average overall mshr miss latency +system.cpu2.icache.demand_hits 87572 # number of demand (read+write) hits +system.cpu2.icache.demand_miss_latency 32274500 # number of demand (read+write) miss cycles +system.cpu2.icache.demand_miss_rate 0.009848 # miss rate for demand accesses +system.cpu2.icache.demand_misses 871 # number of demand (read+write) misses +system.cpu2.icache.demand_mshr_hits 201 # number of demand (read+write) MSHR hits +system.cpu2.icache.demand_mshr_miss_latency 23516500 # number of demand (read+write) MSHR miss cycles +system.cpu2.icache.demand_mshr_miss_rate 0.007576 # mshr miss rate for demand accesses +system.cpu2.icache.demand_mshr_misses 670 # number of demand (read+write) MSHR misses +system.cpu2.icache.fast_writes 0 # number of fast writes performed +system.cpu2.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu2.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu2.icache.overall_accesses 88443 # number of overall (read+write) accesses +system.cpu2.icache.overall_avg_miss_latency 37054.535017 # average overall miss latency +system.cpu2.icache.overall_avg_mshr_miss_latency 35099.253731 # average overall mshr miss latency +system.cpu2.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu2.icache.overall_hits 87572 # number of overall hits +system.cpu2.icache.overall_miss_latency 32274500 # number of overall miss cycles +system.cpu2.icache.overall_miss_rate 0.009848 # miss rate for overall accesses +system.cpu2.icache.overall_misses 871 # number of overall misses +system.cpu2.icache.overall_mshr_hits 201 # number of overall MSHR hits +system.cpu2.icache.overall_mshr_miss_latency 23516500 # number of overall MSHR miss cycles +system.cpu2.icache.overall_mshr_miss_rate 0.007576 # mshr miss rate for overall accesses +system.cpu2.icache.overall_mshr_misses 670 # number of overall MSHR misses +system.cpu2.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu2.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu2.icache.replacements 363 # number of replacements +system.cpu2.icache.sampled_refs 669 # Sample count of references to valid blocks. +system.cpu2.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu2.icache.tagsinuse 269.771036 # Cycle average of tags in use +system.cpu2.icache.total_refs 87572 # Total number of references to valid blocks. +system.cpu2.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu2.icache.writebacks 0 # number of writebacks +system.cpu2.idleCycles 18164 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu2.iew.EXEC:branches 45174 # Number of branches executed +system.cpu2.iew.EXEC:nop 60963 # number of nop insts executed +system.cpu2.iew.EXEC:rate 0.434102 # Inst execution rate +system.cpu2.iew.EXEC:refs 67735 # number of memory reference insts executed +system.cpu2.iew.EXEC:stores 22705 # Number of stores executed +system.cpu2.iew.EXEC:swp 0 # number of swp insts executed +system.cpu2.iew.WB:consumers 96501 # num instructions consuming a value +system.cpu2.iew.WB:count 189859 # cumulative count of insts written-back +system.cpu2.iew.WB:fanout 0.973959 # average fanout of values written-back +system.cpu2.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ +system.cpu2.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu2.iew.WB:producers 93988 # num instructions producing a value +system.cpu2.iew.WB:rate 0.430549 # insts written-back per cycle +system.cpu2.iew.WB:sent 190138 # cumulative count of insts sent to commit +system.cpu2.iew.branchMispredicts 43334 # Number of branch mispredicts detected at execute +system.cpu2.iew.iewBlockCycles 24 # Number of cycles IEW is blocking +system.cpu2.iew.iewDispLoadInsts 46475 # Number of dispatched load instructions +system.cpu2.iew.iewDispNonSpecInsts 21048 # Number of dispatched non-speculative instructions +system.cpu2.iew.iewDispSquashedInsts 2818 # Number of squashed instructions skipped by dispatch +system.cpu2.iew.iewDispStoreInsts 43788 # Number of dispatched store instructions +system.cpu2.iew.iewDispatchedInsts 321686 # Number of instructions dispatched to IQ +system.cpu2.iew.iewExecLoadInsts 45030 # Number of load instructions executed +system.cpu2.iew.iewExecSquashedInsts 43684 # Number of squashed instructions skipped in execute +system.cpu2.iew.iewExecutedInsts 191426 # Number of executed instructions +system.cpu2.iew.iewIQFullEvents 3 # Number of times the IQ has become full, causing a stall +system.cpu2.iew.iewIdleCycles 0 # Number of cycles IEW is idle +system.cpu2.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall +system.cpu2.iew.iewSquashCycles 44866 # Number of cycles IEW is squashing +system.cpu2.iew.iewUnblockCycles 4 # Number of cycles IEW is unblocking +system.cpu2.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding +system.cpu2.iew.lsq.thread.0.cacheBlocked 16 # Number of times an access to memory failed due to the cache being blocked +system.cpu2.iew.lsq.thread.0.forwLoads 19969 # Number of loads that had data forwarded from stores +system.cpu2.iew.lsq.thread.0.ignoredResponses 11 # Number of memory responses ignored because the instruction is squashed +system.cpu2.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu2.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu2.iew.lsq.thread.0.memOrderViolation 186 # Number of memory ordering violations +system.cpu2.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled +system.cpu2.iew.lsq.thread.0.squashedLoads 3929 # Number of loads squashed +system.cpu2.iew.lsq.thread.0.squashedStores 22009 # Number of stores squashed +system.cpu2.iew.memOrderViolationEvents 186 # Number of memory order violations +system.cpu2.iew.predictedNotTakenIncorrect 868 # Number of branches that were predicted not taken incorrectly +system.cpu2.iew.predictedTakenIncorrect 42466 # Number of branches that were predicted taken incorrectly +system.cpu2.ipc 0.269290 # IPC: Instructions Per Cycle +system.cpu2.ipc_total 0.269290 # IPC: Total IPC of All Threads +system.cpu2.iq.ISSUE:FU_type_0 235110 # Type of FU issued +system.cpu2.iq.ISSUE:FU_type_0.start_dist + No_OpClass 0 0.00% # Type of FU issued + IntAlu 166509 70.82% # Type of FU issued + IntMult 0 0.00% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 0 0.00% # 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 45663 19.42% # Type of FU issued + MemWrite 22938 9.76% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu2.iq.ISSUE:FU_type_0.end_dist +system.cpu2.iq.ISSUE:fu_busy_cnt 133 # FU busy when requested +system.cpu2.iq.ISSUE:fu_busy_rate 0.000566 # FU busy rate (busy events/executed inst) +system.cpu2.iq.ISSUE:fu_full.start_dist + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 38 28.57% # 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 27 20.30% # attempts to use FU when none available + MemWrite 68 51.13% # 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.cpu2.iq.ISSUE:fu_full.end_dist +system.cpu2.iq.ISSUE:issued_per_cycle::samples 422806 +system.cpu2.iq.ISSUE:issued_per_cycle::min_value 0 +system.cpu2.iq.ISSUE:issued_per_cycle::underflows 0 0.00% +system.cpu2.iq.ISSUE:issued_per_cycle::0-1 286677 67.80% +system.cpu2.iq.ISSUE:issued_per_cycle::1-2 67298 15.92% +system.cpu2.iq.ISSUE:issued_per_cycle::2-3 43645 10.32% +system.cpu2.iq.ISSUE:issued_per_cycle::3-4 22116 5.23% +system.cpu2.iq.ISSUE:issued_per_cycle::4-5 1740 0.41% +system.cpu2.iq.ISSUE:issued_per_cycle::5-6 920 0.22% +system.cpu2.iq.ISSUE:issued_per_cycle::6-7 282 0.07% +system.cpu2.iq.ISSUE:issued_per_cycle::7-8 102 0.02% +system.cpu2.iq.ISSUE:issued_per_cycle::8 26 0.01% +system.cpu2.iq.ISSUE:issued_per_cycle::overflows 0 0.00% +system.cpu2.iq.ISSUE:issued_per_cycle::total 422806 +system.cpu2.iq.ISSUE:issued_per_cycle::max_value 8 +system.cpu2.iq.ISSUE:issued_per_cycle::mean 0.556071 +system.cpu2.iq.ISSUE:issued_per_cycle::stdev 0.945329 +system.cpu2.iq.ISSUE:rate 0.533166 # Inst issue rate +system.cpu2.iq.iqInstsAdded 239551 # Number of instructions added to the IQ (excludes non-spec) +system.cpu2.iq.iqInstsIssued 235110 # Number of instructions issued +system.cpu2.iq.iqNonSpecInstsAdded 21172 # Number of non-speculative instructions added to the IQ +system.cpu2.iq.iqSquashedInstsExamined 99184 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu2.iq.iqSquashedInstsIssued 52 # Number of squashed instructions issued +system.cpu2.iq.iqSquashedNonSpecRemoved 20613 # Number of squashed non-spec instructions that were removed +system.cpu2.iq.iqSquashedOperandsExamined 15669 # Number of squashed operands that are examined and possibly removed from graph +system.cpu2.memDep0.conflictingLoads 20136 # Number of conflicting loads. +system.cpu2.memDep0.conflictingStores 109 # Number of conflicting stores. +system.cpu2.memDep0.insertedLoads 46475 # Number of loads inserted to the mem dependence unit. +system.cpu2.memDep0.insertedStores 43788 # Number of stores inserted to the mem dependence unit. +system.cpu2.numCycles 440970 # number of cpu cycles simulated +system.cpu2.rename.RENAME:BlockCycles 32 # Number of cycles rename is blocking +system.cpu2.rename.RENAME:CommittedMaps 97924 # Number of HB maps that are committed +system.cpu2.rename.RENAME:IdleCycles 188399 # Number of cycles rename is idle +system.cpu2.rename.RENAME:LSQFullEvents 5 # Number of times rename has blocked due to LSQ full +system.cpu2.rename.RENAME:RenameLookups 512581 # Number of register rename lookups that rename has made +system.cpu2.rename.RENAME:RenamedInsts 328892 # Number of instructions processed by rename +system.cpu2.rename.RENAME:RenamedOperands 245007 # Number of destination operands rename has renamed +system.cpu2.rename.RENAME:RunCycles 135302 # Number of cycles rename is running +system.cpu2.rename.RENAME:SquashCycles 44866 # Number of cycles rename is squashing +system.cpu2.rename.RENAME:UnblockCycles 350 # Number of cycles rename is unblocking +system.cpu2.rename.RENAME:UndoneMaps 147083 # Number of HB maps that are undone due to squashing +system.cpu2.rename.RENAME:serializeStallCycles 53857 # count of cycles rename stalled for serializing inst +system.cpu2.rename.RENAME:serializingInsts 21162 # count of serializing insts renamed +system.cpu2.rename.RENAME:skidInsts 84753 # count of insts added to the skid buffer +system.cpu2.rename.RENAME:tempSerializingInsts 21158 # count of temporary serializing insts renamed +system.cpu2.timesIdled 339 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu3.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu3.BPredUnit.BTBHits 51243 # Number of BTB hits +system.cpu3.BPredUnit.BTBLookups 69683 # Number of BTB lookups +system.cpu3.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu3.BPredUnit.condIncorrect 32692 # Number of conditional branches incorrect +system.cpu3.BPredUnit.condPredicted 78569 # Number of conditional branches predicted +system.cpu3.BPredUnit.lookups 78569 # Number of BP lookups +system.cpu3.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. +system.cpu3.commit.COM:branches 25257 # Number of branches committed +system.cpu3.commit.COM:bw_lim_events 568 # number cycles where commit BW limit reached +system.cpu3.commit.COM:bw_limited 0 # number of insts not committed due to BW limits +system.cpu3.commit.COM:committed_per_cycle::samples 351415 # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::underflows 0 0.00% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::0-1 262526 74.71% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::1-2 59947 17.06% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::2-3 24097 6.86% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::3-4 1297 0.37% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::4-5 787 0.22% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::5-6 568 0.16% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::6-7 1611 0.46% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::7-8 14 0.00% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::8 568 0.16% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::overflows 0 0.00% # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::total 351415 # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::mean 0.376558 # Number of insts commited each cycle +system.cpu3.commit.COM:committed_per_cycle::stdev 0.826419 # Number of insts commited each cycle +system.cpu3.commit.COM:count 132328 # Number of instructions committed +system.cpu3.commit.COM:loads 32245 # Number of loads committed +system.cpu3.commit.COM:membars 5830 # Number of memory barriers committed +system.cpu3.commit.COM:refs 45707 # Number of memory references committed +system.cpu3.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu3.commit.branchMispredicts 32692 # The number of times a branch was mispredicted +system.cpu3.commit.commitCommittedInsts 132328 # The number of committed instructions +system.cpu3.commit.commitNonSpecStalls 6543 # The number of times commit has been forced to stall to communicate backwards +system.cpu3.commit.commitSquashedInsts 149632 # The number of squashed insts skipped by commit +system.cpu3.committedInsts 110450 # Number of Instructions Simulated +system.cpu3.committedInsts_total 110450 # Number of Instructions Simulated +system.cpu3.cpi 3.645957 # CPI: Cycles Per Instruction +system.cpu3.cpi_total 3.645957 # CPI: Total CPI of All Threads +system.cpu3.dcache.ReadReq_accesses 28797 # number of ReadReq accesses(hits+misses) +system.cpu3.dcache.ReadReq_avg_miss_latency 19788.770053 # average ReadReq miss latency +system.cpu3.dcache.ReadReq_avg_mshr_miss_latency 16721.212121 # average ReadReq mshr miss latency +system.cpu3.dcache.ReadReq_hits 28610 # number of ReadReq hits +system.cpu3.dcache.ReadReq_miss_latency 3700500 # number of ReadReq miss cycles +system.cpu3.dcache.ReadReq_miss_rate 0.006494 # miss rate for ReadReq accesses +system.cpu3.dcache.ReadReq_misses 187 # number of ReadReq misses +system.cpu3.dcache.ReadReq_mshr_hits 22 # number of ReadReq MSHR hits +system.cpu3.dcache.ReadReq_mshr_miss_latency 2759000 # number of ReadReq MSHR miss cycles +system.cpu3.dcache.ReadReq_mshr_miss_rate 0.005730 # mshr miss rate for ReadReq accesses +system.cpu3.dcache.ReadReq_mshr_misses 165 # number of ReadReq MSHR misses +system.cpu3.dcache.SwapReq_accesses 67 # number of SwapReq accesses(hits+misses) +system.cpu3.dcache.SwapReq_avg_miss_latency 21918.181818 # average SwapReq miss latency +system.cpu3.dcache.SwapReq_avg_mshr_miss_latency 22138.297872 # average SwapReq mshr miss latency +system.cpu3.dcache.SwapReq_hits 12 # number of SwapReq hits +system.cpu3.dcache.SwapReq_miss_latency 1205500 # number of SwapReq miss cycles +system.cpu3.dcache.SwapReq_miss_rate 0.820896 # miss rate for SwapReq accesses +system.cpu3.dcache.SwapReq_misses 55 # number of SwapReq misses +system.cpu3.dcache.SwapReq_mshr_hits 8 # number of SwapReq MSHR hits +system.cpu3.dcache.SwapReq_mshr_miss_latency 1040500 # number of SwapReq MSHR miss cycles +system.cpu3.dcache.SwapReq_mshr_miss_rate 0.701493 # mshr miss rate for SwapReq accesses +system.cpu3.dcache.SwapReq_mshr_misses 47 # number of SwapReq MSHR misses +system.cpu3.dcache.WriteReq_accesses 13395 # number of WriteReq accesses(hits+misses) +system.cpu3.dcache.WriteReq_avg_miss_latency 23007.751938 # average WriteReq miss latency +system.cpu3.dcache.WriteReq_avg_mshr_miss_latency 14729.729730 # average WriteReq mshr miss latency +system.cpu3.dcache.WriteReq_hits 13266 # number of WriteReq hits +system.cpu3.dcache.WriteReq_miss_latency 2968000 # number of WriteReq miss cycles +system.cpu3.dcache.WriteReq_miss_rate 0.009630 # miss rate for WriteReq accesses +system.cpu3.dcache.WriteReq_misses 129 # number of WriteReq misses +system.cpu3.dcache.WriteReq_mshr_hits 18 # number of WriteReq MSHR hits +system.cpu3.dcache.WriteReq_mshr_miss_latency 1635000 # number of WriteReq MSHR miss cycles +system.cpu3.dcache.WriteReq_mshr_miss_rate 0.008287 # mshr miss rate for WriteReq accesses +system.cpu3.dcache.WriteReq_mshr_misses 111 # number of WriteReq MSHR misses +system.cpu3.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu3.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu3.dcache.avg_refs 804.066667 # Average number of references to valid blocks. +system.cpu3.dcache.blocked_no_mshrs 0 # number of cycles access was blocked +system.cpu3.dcache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu3.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.cpu3.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu3.dcache.cache_copies 0 # number of cache copies performed +system.cpu3.dcache.demand_accesses 42192 # number of demand (read+write) accesses +system.cpu3.dcache.demand_avg_miss_latency 21102.848101 # average overall miss latency +system.cpu3.dcache.demand_avg_mshr_miss_latency 15920.289855 # average overall mshr miss latency +system.cpu3.dcache.demand_hits 41876 # number of demand (read+write) hits +system.cpu3.dcache.demand_miss_latency 6668500 # number of demand (read+write) miss cycles +system.cpu3.dcache.demand_miss_rate 0.007490 # miss rate for demand accesses +system.cpu3.dcache.demand_misses 316 # number of demand (read+write) misses +system.cpu3.dcache.demand_mshr_hits 40 # number of demand (read+write) MSHR hits +system.cpu3.dcache.demand_mshr_miss_latency 4394000 # number of demand (read+write) MSHR miss cycles +system.cpu3.dcache.demand_mshr_miss_rate 0.006542 # mshr miss rate for demand accesses +system.cpu3.dcache.demand_mshr_misses 276 # number of demand (read+write) MSHR misses +system.cpu3.dcache.fast_writes 0 # number of fast writes performed +system.cpu3.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu3.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu3.dcache.overall_accesses 42192 # number of overall (read+write) accesses +system.cpu3.dcache.overall_avg_miss_latency 21102.848101 # average overall miss latency +system.cpu3.dcache.overall_avg_mshr_miss_latency 15920.289855 # average overall mshr miss latency +system.cpu3.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu3.dcache.overall_hits 41876 # number of overall hits +system.cpu3.dcache.overall_miss_latency 6668500 # number of overall miss cycles +system.cpu3.dcache.overall_miss_rate 0.007490 # miss rate for overall accesses +system.cpu3.dcache.overall_misses 316 # number of overall misses +system.cpu3.dcache.overall_mshr_hits 40 # number of overall MSHR hits +system.cpu3.dcache.overall_mshr_miss_latency 4394000 # number of overall MSHR miss cycles +system.cpu3.dcache.overall_mshr_miss_rate 0.006542 # mshr miss rate for overall accesses +system.cpu3.dcache.overall_mshr_misses 276 # number of overall MSHR misses +system.cpu3.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu3.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu3.dcache.replacements 2 # number of replacements +system.cpu3.dcache.sampled_refs 30 # Sample count of references to valid blocks. +system.cpu3.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu3.dcache.tagsinuse 29.172631 # Cycle average of tags in use +system.cpu3.dcache.total_refs 24122 # Total number of references to valid blocks. +system.cpu3.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu3.dcache.writebacks 1 # number of writebacks +system.cpu3.decode.DECODE:BlockedCycles 35128 # Number of cycles decode is blocked +system.cpu3.decode.DECODE:DecodedInsts 388171 # Number of instructions handled by decode +system.cpu3.decode.DECODE:IdleCycles 168108 # Number of cycles decode is idle +system.cpu3.decode.DECODE:RunCycles 148027 # Number of cycles decode is running +system.cpu3.decode.DECODE:SquashCycles 36551 # Number of cycles decode is squashing +system.cpu3.decode.DECODE:UnblockCycles 152 # Number of cycles decode is unblocking +system.cpu3.fetch.Branches 78569 # Number of branches that fetch encountered +system.cpu3.fetch.CacheLines 81998 # Number of cache lines fetched +system.cpu3.fetch.Cycles 239499 # Number of cycles fetch has run and was not squashing or blocked +system.cpu3.fetch.IcacheSquashes 12083 # Number of outstanding Icache misses that were squashed +system.cpu3.fetch.Insts 427102 # Number of instructions fetch has processed +system.cpu3.fetch.SquashCycles 32841 # Number of cycles fetch has spent squashing +system.cpu3.fetch.branchRate 0.195107 # Number of branch fetches per cycle +system.cpu3.fetch.icacheStallCycles 81998 # Number of cycles fetch is stalled on an Icache miss +system.cpu3.fetch.predictedBranches 51243 # Number of branches that fetch has predicted taken +system.cpu3.fetch.rate 1.060607 # Number of inst fetches per cycle +system.cpu3.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) +system.cpu3.fetch.rateDist.samples 397135 +system.cpu3.fetch.rateDist.min_value 0 + 0 239656 6034.62% + 1 85048 2141.54% + 2 14012 352.83% + 3 17951 452.01% + 4 2990 75.29% + 5 15291 385.03% + 6 1676 42.20% + 7 2382 59.98% + 8 18129 456.49% +system.cpu3.fetch.rateDist.max_value 8 +system.cpu3.fetch.rateDist.end_dist + +system.cpu3.icache.ReadReq_accesses 81998 # number of ReadReq accesses(hits+misses) +system.cpu3.icache.ReadReq_avg_miss_latency 19529.880478 # average ReadReq miss latency +system.cpu3.icache.ReadReq_avg_mshr_miss_latency 16592.417062 # average ReadReq mshr miss latency +system.cpu3.icache.ReadReq_hits 81245 # number of ReadReq hits +system.cpu3.icache.ReadReq_miss_latency 14706000 # number of ReadReq miss cycles +system.cpu3.icache.ReadReq_miss_rate 0.009183 # miss rate for ReadReq accesses +system.cpu3.icache.ReadReq_misses 753 # number of ReadReq misses +system.cpu3.icache.ReadReq_mshr_hits 120 # number of ReadReq MSHR hits +system.cpu3.icache.ReadReq_mshr_miss_latency 10503000 # number of ReadReq MSHR miss cycles +system.cpu3.icache.ReadReq_mshr_miss_rate 0.007720 # mshr miss rate for ReadReq accesses +system.cpu3.icache.ReadReq_mshr_misses 633 # number of ReadReq MSHR misses +system.cpu3.icache.avg_blocked_cycles_no_mshrs 32500 # average number of cycles each access was blocked +system.cpu3.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu3.icache.avg_refs 128.349131 # Average number of references to valid blocks. +system.cpu3.icache.blocked_no_mshrs 1 # number of cycles access was blocked +system.cpu3.icache.blocked_no_targets 0 # number of cycles access was blocked +system.cpu3.icache.blocked_cycles_no_mshrs 32500 # number of cycles access was blocked +system.cpu3.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu3.icache.cache_copies 0 # number of cache copies performed +system.cpu3.icache.demand_accesses 81998 # number of demand (read+write) accesses +system.cpu3.icache.demand_avg_miss_latency 19529.880478 # average overall miss latency +system.cpu3.icache.demand_avg_mshr_miss_latency 16592.417062 # average overall mshr miss latency +system.cpu3.icache.demand_hits 81245 # number of demand (read+write) hits +system.cpu3.icache.demand_miss_latency 14706000 # number of demand (read+write) miss cycles +system.cpu3.icache.demand_miss_rate 0.009183 # miss rate for demand accesses +system.cpu3.icache.demand_misses 753 # number of demand (read+write) misses +system.cpu3.icache.demand_mshr_hits 120 # number of demand (read+write) MSHR hits +system.cpu3.icache.demand_mshr_miss_latency 10503000 # number of demand (read+write) MSHR miss cycles +system.cpu3.icache.demand_mshr_miss_rate 0.007720 # mshr miss rate for demand accesses +system.cpu3.icache.demand_mshr_misses 633 # number of demand (read+write) MSHR misses +system.cpu3.icache.fast_writes 0 # number of fast writes performed +system.cpu3.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu3.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu3.icache.overall_accesses 81998 # number of overall (read+write) accesses +system.cpu3.icache.overall_avg_miss_latency 19529.880478 # average overall miss latency +system.cpu3.icache.overall_avg_mshr_miss_latency 16592.417062 # average overall mshr miss latency +system.cpu3.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.cpu3.icache.overall_hits 81245 # number of overall hits +system.cpu3.icache.overall_miss_latency 14706000 # number of overall miss cycles +system.cpu3.icache.overall_miss_rate 0.009183 # miss rate for overall accesses +system.cpu3.icache.overall_misses 753 # number of overall misses +system.cpu3.icache.overall_mshr_hits 120 # number of overall MSHR hits +system.cpu3.icache.overall_mshr_miss_latency 10503000 # number of overall MSHR miss cycles +system.cpu3.icache.overall_mshr_miss_rate 0.007720 # mshr miss rate for overall accesses +system.cpu3.icache.overall_mshr_misses 633 # number of overall MSHR misses +system.cpu3.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu3.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu3.icache.replacements 522 # number of replacements +system.cpu3.icache.sampled_refs 633 # Sample count of references to valid blocks. +system.cpu3.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu3.icache.tagsinuse 98.793514 # Cycle average of tags in use +system.cpu3.icache.total_refs 81245 # Total number of references to valid blocks. +system.cpu3.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu3.icache.writebacks 0 # number of writebacks +system.cpu3.idleCycles 5561 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu3.iew.EXEC:branches 39289 # Number of branches executed +system.cpu3.iew.EXEC:nop 47300 # number of nop insts executed +system.cpu3.iew.EXEC:rate 0.440007 # Inst execution rate +system.cpu3.iew.EXEC:refs 53548 # number of memory reference insts executed +system.cpu3.iew.EXEC:stores 15235 # Number of stores executed +system.cpu3.iew.EXEC:swp 0 # number of swp insts executed +system.cpu3.iew.WB:consumers 87751 # num instructions consuming a value +system.cpu3.iew.WB:count 173492 # cumulative count of insts written-back +system.cpu3.iew.WB:fanout 0.936696 # average fanout of values written-back +system.cpu3.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ +system.cpu3.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu3.iew.WB:producers 82196 # num instructions producing a value +system.cpu3.iew.WB:rate 0.430826 # insts written-back per cycle +system.cpu3.iew.WB:sent 173712 # cumulative count of insts sent to commit +system.cpu3.iew.branchMispredicts 33345 # Number of branch mispredicts detected at execute +system.cpu3.iew.iewBlockCycles 0 # Number of cycles IEW is blocking +system.cpu3.iew.iewDispLoadInsts 42639 # Number of dispatched load instructions +system.cpu3.iew.iewDispNonSpecInsts 11434 # Number of dispatched non-speculative instructions +system.cpu3.iew.iewDispSquashedInsts 4085 # Number of squashed instructions skipped by dispatch +system.cpu3.iew.iewDispStoreInsts 26562 # Number of dispatched store instructions +system.cpu3.iew.iewDispatchedInsts 281979 # Number of instructions dispatched to IQ +system.cpu3.iew.iewExecLoadInsts 38313 # Number of load instructions executed +system.cpu3.iew.iewExecSquashedInsts 36396 # Number of squashed instructions skipped in execute +system.cpu3.iew.iewExecutedInsts 177189 # Number of executed instructions +system.cpu3.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall +system.cpu3.iew.iewIdleCycles 0 # Number of cycles IEW is idle +system.cpu3.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall +system.cpu3.iew.iewSquashCycles 36551 # Number of cycles IEW is squashing +system.cpu3.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking +system.cpu3.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding +system.cpu3.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked +system.cpu3.iew.lsq.thread.0.forwLoads 9499 # Number of loads that had data forwarded from stores +system.cpu3.iew.lsq.thread.0.ignoredResponses 11 # Number of memory responses ignored because the instruction is squashed +system.cpu3.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu3.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu3.iew.lsq.thread.0.memOrderViolation 639 # Number of memory ordering violations +system.cpu3.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled +system.cpu3.iew.lsq.thread.0.squashedLoads 10394 # Number of loads squashed +system.cpu3.iew.lsq.thread.0.squashedStores 13100 # Number of stores squashed +system.cpu3.iew.memOrderViolationEvents 639 # Number of memory order violations +system.cpu3.iew.predictedNotTakenIncorrect 830 # Number of branches that were predicted not taken incorrectly +system.cpu3.iew.predictedTakenIncorrect 32515 # Number of branches that were predicted taken incorrectly +system.cpu3.ipc 0.274276 # IPC: Instructions Per Cycle +system.cpu3.ipc_total 0.274276 # IPC: Total IPC of All Threads +system.cpu3.iq.ISSUE:FU_type_0 213585 # Type of FU issued +system.cpu3.iq.ISSUE:FU_type_0.start_dist + No_OpClass 0 0.00% # Type of FU issued + IntAlu 152352 71.33% # Type of FU issued + IntMult 0 0.00% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 0 0.00% # 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 45332 21.22% # Type of FU issued + MemWrite 15901 7.44% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu3.iq.ISSUE:FU_type_0.end_dist +system.cpu3.iq.ISSUE:fu_busy_cnt 168 # FU busy when requested +system.cpu3.iq.ISSUE:fu_busy_rate 0.000787 # FU busy rate (busy events/executed inst) +system.cpu3.iq.ISSUE:fu_full.start_dist + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 18 10.71% # 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 11 6.55% # attempts to use FU when none available + MemWrite 139 82.74% # 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.cpu3.iq.ISSUE:fu_full.end_dist +system.cpu3.iq.ISSUE:issued_per_cycle::samples 397135 +system.cpu3.iq.ISSUE:issued_per_cycle::min_value 0 +system.cpu3.iq.ISSUE:issued_per_cycle::underflows 0 0.00% +system.cpu3.iq.ISSUE:issued_per_cycle::0-1 274584 69.14% +system.cpu3.iq.ISSUE:issued_per_cycle::1-2 68377 17.22% +system.cpu3.iq.ISSUE:issued_per_cycle::2-3 29162 7.34% +system.cpu3.iq.ISSUE:issued_per_cycle::3-4 16815 4.23% +system.cpu3.iq.ISSUE:issued_per_cycle::4-5 5405 1.36% +system.cpu3.iq.ISSUE:issued_per_cycle::5-6 2141 0.54% +system.cpu3.iq.ISSUE:issued_per_cycle::6-7 468 0.12% +system.cpu3.iq.ISSUE:issued_per_cycle::7-8 158 0.04% +system.cpu3.iq.ISSUE:issued_per_cycle::8 25 0.01% +system.cpu3.iq.ISSUE:issued_per_cycle::overflows 0 0.00% +system.cpu3.iq.ISSUE:issued_per_cycle::total 397135 +system.cpu3.iq.ISSUE:issued_per_cycle::max_value 8 +system.cpu3.iq.ISSUE:issued_per_cycle::mean 0.537815 +system.cpu3.iq.ISSUE:issued_per_cycle::stdev 0.988033 +system.cpu3.iq.ISSUE:rate 0.530388 # Inst issue rate +system.cpu3.iq.iqInstsAdded 217367 # Number of instructions added to the IQ (excludes non-spec) +system.cpu3.iq.iqInstsIssued 213585 # Number of instructions issued +system.cpu3.iq.iqNonSpecInstsAdded 17312 # Number of non-speculative instructions added to the IQ +system.cpu3.iq.iqSquashedInstsExamined 84893 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu3.iq.iqSquashedInstsIssued 2 # Number of squashed instructions issued +system.cpu3.iq.iqSquashedNonSpecRemoved 10769 # Number of squashed non-spec instructions that were removed +system.cpu3.iq.iqSquashedOperandsExamined 34030 # Number of squashed operands that are examined and possibly removed from graph +system.cpu3.memDep0.conflictingLoads 9667 # Number of conflicting loads. +system.cpu3.memDep0.conflictingStores 80 # Number of conflicting stores. +system.cpu3.memDep0.insertedLoads 42639 # Number of loads inserted to the mem dependence unit. +system.cpu3.memDep0.insertedStores 26562 # Number of stores inserted to the mem dependence unit. +system.cpu3.numCycles 402696 # number of cpu cycles simulated +system.cpu3.rename.RENAME:CommittedMaps 93774 # Number of HB maps that are committed +system.cpu3.rename.RENAME:IdleCycles 183092 # Number of cycles rename is idle +system.cpu3.rename.RENAME:RenameLookups 489966 # Number of register rename lookups that rename has made +system.cpu3.rename.RENAME:RenamedInsts 307555 # Number of instructions processed by rename +system.cpu3.rename.RENAME:RenamedOperands 229124 # Number of destination operands rename has renamed +system.cpu3.rename.RENAME:RunCycles 133281 # Number of cycles rename is running +system.cpu3.rename.RENAME:SquashCycles 36551 # Number of cycles rename is squashing +system.cpu3.rename.RENAME:UnblockCycles 561 # Number of cycles rename is unblocking +system.cpu3.rename.RENAME:UndoneMaps 135350 # Number of HB maps that are undone due to squashing +system.cpu3.rename.RENAME:serializeStallCycles 34481 # count of cycles rename stalled for serializing inst +system.cpu3.rename.RENAME:serializingInsts 11653 # count of serializing insts renamed +system.cpu3.rename.RENAME:skidInsts 44534 # count of insts added to the skid buffer +system.cpu3.rename.RENAME:tempSerializingInsts 11782 # count of temporary serializing insts renamed +system.cpu3.timesIdled 293 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.l2c.ReadExReq_accesses 131 # number of ReadExReq accesses(hits+misses) +system.l2c.ReadExReq_avg_miss_latency 52477.099237 # average ReadExReq miss latency +system.l2c.ReadExReq_avg_mshr_miss_latency 40316.793893 # average ReadExReq mshr miss latency +system.l2c.ReadExReq_miss_latency 6874500 # number of ReadExReq miss cycles +system.l2c.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.l2c.ReadExReq_misses 131 # number of ReadExReq misses +system.l2c.ReadExReq_mshr_miss_latency 5281500 # number of ReadExReq MSHR miss cycles +system.l2c.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.l2c.ReadExReq_mshr_misses 131 # number of ReadExReq MSHR misses +system.l2c.ReadReq_accesses 2699 # number of ReadReq accesses(hits+misses) +system.l2c.ReadReq_avg_miss_latency 52060.143627 # average ReadReq miss latency +system.l2c.ReadReq_avg_mshr_miss_latency 39997.282609 # average ReadReq mshr miss latency +system.l2c.ReadReq_hits 2142 # number of ReadReq hits +system.l2c.ReadReq_miss_latency 28997500 # number of ReadReq miss cycles +system.l2c.ReadReq_miss_rate 0.206373 # miss rate for ReadReq accesses +system.l2c.ReadReq_misses 557 # number of ReadReq misses +system.l2c.ReadReq_mshr_hits 5 # number of ReadReq MSHR hits +system.l2c.ReadReq_mshr_miss_latency 22078500 # number of ReadReq MSHR miss cycles +system.l2c.ReadReq_mshr_miss_rate 0.204520 # mshr miss rate for ReadReq accesses +system.l2c.ReadReq_mshr_misses 552 # number of ReadReq MSHR misses +system.l2c.UpgradeReq_accesses 114 # number of UpgradeReq accesses(hits+misses) +system.l2c.UpgradeReq_avg_miss_latency 11482.456140 # average UpgradeReq miss latency +system.l2c.UpgradeReq_avg_mshr_miss_latency 40039.473684 # average UpgradeReq mshr miss latency +system.l2c.UpgradeReq_miss_latency 1309000 # number of UpgradeReq miss cycles +system.l2c.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.l2c.UpgradeReq_misses 114 # number of UpgradeReq misses +system.l2c.UpgradeReq_mshr_miss_latency 4564500 # number of UpgradeReq MSHR miss cycles +system.l2c.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.l2c.UpgradeReq_mshr_misses 114 # number of UpgradeReq MSHR misses +system.l2c.Writeback_accesses 9 # number of Writeback accesses(hits+misses) +system.l2c.Writeback_hits 9 # number of Writeback hits +system.l2c.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.l2c.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.l2c.avg_refs 3.998131 # Average number of references to valid blocks. +system.l2c.blocked_no_mshrs 0 # number of cycles access was blocked +system.l2c.blocked_no_targets 0 # number of cycles access was blocked +system.l2c.blocked_cycles_no_mshrs 0 # number of cycles access was blocked +system.l2c.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.l2c.cache_copies 0 # number of cache copies performed +system.l2c.demand_accesses 2830 # number of demand (read+write) accesses +system.l2c.demand_avg_miss_latency 52139.534884 # average overall miss latency +system.l2c.demand_avg_mshr_miss_latency 40058.565154 # average overall mshr miss latency +system.l2c.demand_hits 2142 # number of demand (read+write) hits +system.l2c.demand_miss_latency 35872000 # number of demand (read+write) miss cycles +system.l2c.demand_miss_rate 0.243110 # miss rate for demand accesses +system.l2c.demand_misses 688 # number of demand (read+write) misses +system.l2c.demand_mshr_hits 5 # number of demand (read+write) MSHR hits +system.l2c.demand_mshr_miss_latency 27360000 # number of demand (read+write) MSHR miss cycles +system.l2c.demand_mshr_miss_rate 0.241343 # mshr miss rate for demand accesses +system.l2c.demand_mshr_misses 683 # number of demand (read+write) MSHR misses +system.l2c.fast_writes 0 # number of fast writes performed +system.l2c.mshr_cap_events 0 # number of times MSHR cap was activated +system.l2c.no_allocate_misses 0 # Number of misses that were no-allocate +system.l2c.overall_accesses 2830 # number of overall (read+write) accesses +system.l2c.overall_avg_miss_latency 52139.534884 # average overall miss latency +system.l2c.overall_avg_mshr_miss_latency 40058.565154 # average overall mshr miss latency +system.l2c.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency +system.l2c.overall_hits 2142 # number of overall hits +system.l2c.overall_miss_latency 35872000 # number of overall miss cycles +system.l2c.overall_miss_rate 0.243110 # miss rate for overall accesses +system.l2c.overall_misses 688 # number of overall misses +system.l2c.overall_mshr_hits 5 # number of overall MSHR hits +system.l2c.overall_mshr_miss_latency 27360000 # number of overall MSHR miss cycles +system.l2c.overall_mshr_miss_rate 0.241343 # mshr miss rate for overall accesses +system.l2c.overall_mshr_misses 683 # number of overall MSHR misses +system.l2c.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.l2c.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.l2c.replacements 0 # number of replacements +system.l2c.sampled_refs 535 # Sample count of references to valid blocks. +system.l2c.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.l2c.tagsinuse 454.684423 # Cycle average of tags in use +system.l2c.total_refs 2139 # Total number of references to valid blocks. +system.l2c.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.l2c.writebacks 0 # number of writebacks + +---------- End Simulation Statistics ---------- |