sanchayanmaity/gem5
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
gem5/tests/quick/fs/10.linux-boot/ref/arm/linux/realview-switcheroo-atomic/stats.txt

1080 lines
125 KiB
Text
Raw Normal View History

tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
---------- Begin Simulation Statistics ----------
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
sim_seconds 2.783867 # Number of seconds simulated
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
sim_ticks 2783867052000 # Number of ticks simulated
final_tick 2783867052000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
sim_freq 1000000000000 # Frequency of simulated ticks
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
host_inst_rate 1174884 # Simulator instruction rate (inst/s)
host_op_rate 1430233 # Simulator op (including micro ops) rate (op/s)
host_tick_rate 22908545755 # Simulator tick rate (ticks/s)
host_mem_usage 623708 # Number of bytes of host memory used
host_seconds 121.52 # Real time elapsed on the host
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
sim_insts 142772879 # Number of instructions simulated
sim_ops 173803124 # Number of ops (including micro ops) simulated
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
system.voltage_domain.voltage 1 # Voltage in Volts
system.clk_domain.clock 1000 # Clock period in ticks
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bytes_read::cpu0.dtb.walker 320 # Number of bytes read from this memory
system.physmem.bytes_read::cpu0.itb.walker 64 # Number of bytes read from this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bytes_read::cpu0.inst 725796 # Number of bytes read from this memory
system.physmem.bytes_read::cpu0.data 4660896 # Number of bytes read from this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bytes_read::cpu1.dtb.walker 128 # Number of bytes read from this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bytes_read::cpu1.inst 481216 # Number of bytes read from this memory
system.physmem.bytes_read::cpu1.data 5663620 # Number of bytes read from this memory
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.physmem.bytes_read::realview.ide 960 # Number of bytes read from this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bytes_read::total 11533000 # Number of bytes read from this memory
system.physmem.bytes_inst_read::cpu0.inst 725796 # Number of instructions bytes read from this memory
system.physmem.bytes_inst_read::cpu1.inst 481216 # Number of instructions bytes read from this memory
system.physmem.bytes_inst_read::total 1207012 # Number of instructions bytes read from this memory
system.physmem.bytes_written::writebacks 8840512 # Number of bytes written to this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bytes_written::cpu0.data 17516 # Number of bytes written to this memory
system.physmem.bytes_written::cpu1.data 8 # Number of bytes written to this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bytes_written::total 8858036 # Number of bytes written to this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.num_reads::cpu0.dtb.walker 5 # Number of read requests responded to by this memory
system.physmem.num_reads::cpu0.itb.walker 1 # Number of read requests responded to by this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.num_reads::cpu0.inst 19794 # Number of read requests responded to by this memory
system.physmem.num_reads::cpu0.data 73345 # Number of read requests responded to by this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.num_reads::cpu1.dtb.walker 2 # Number of read requests responded to by this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.num_reads::cpu1.inst 7519 # Number of read requests responded to by this memory
system.physmem.num_reads::cpu1.data 88495 # Number of read requests responded to by this memory
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.physmem.num_reads::realview.ide 15 # Number of read requests responded to by this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.num_reads::total 189176 # Number of read requests responded to by this memory
system.physmem.num_writes::writebacks 138133 # Number of write requests responded to by this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.num_writes::cpu0.data 4379 # Number of write requests responded to by this memory
system.physmem.num_writes::cpu1.data 2 # Number of write requests responded to by this memory
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.num_writes::total 142514 # Number of write requests responded to by this memory
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bw_read::cpu0.dtb.walker 115 # Total read bandwidth from this memory (bytes/s)
system.physmem.bw_read::cpu0.itb.walker 23 # Total read bandwidth from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_read::cpu0.inst 260715 # Total read bandwidth from this memory (bytes/s)
system.physmem.bw_read::cpu0.data 1674252 # Total read bandwidth from this memory (bytes/s)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bw_read::cpu1.dtb.walker 46 # Total read bandwidth from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_read::cpu1.inst 172859 # Total read bandwidth from this memory (bytes/s)
system.physmem.bw_read::cpu1.data 2034443 # Total read bandwidth from this memory (bytes/s)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.physmem.bw_read::realview.ide 345 # Total read bandwidth from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_read::total 4142798 # Total read bandwidth from this memory (bytes/s)
system.physmem.bw_inst_read::cpu0.inst 260715 # Instruction read bandwidth from this memory (bytes/s)
system.physmem.bw_inst_read::cpu1.inst 172859 # Instruction read bandwidth from this memory (bytes/s)
system.physmem.bw_inst_read::total 433574 # Instruction read bandwidth from this memory (bytes/s)
system.physmem.bw_write::writebacks 3175623 # Write bandwidth from this memory (bytes/s)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bw_write::cpu0.data 6292 # Write bandwidth from this memory (bytes/s)
system.physmem.bw_write::cpu1.data 3 # Write bandwidth from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_write::total 3181918 # Write bandwidth from this memory (bytes/s)
system.physmem.bw_total::writebacks 3175623 # Total bandwidth to/from this memory (bytes/s)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bw_total::cpu0.dtb.walker 115 # Total bandwidth to/from this memory (bytes/s)
system.physmem.bw_total::cpu0.itb.walker 23 # Total bandwidth to/from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_total::cpu0.inst 260715 # Total bandwidth to/from this memory (bytes/s)
system.physmem.bw_total::cpu0.data 1680544 # Total bandwidth to/from this memory (bytes/s)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.physmem.bw_total::cpu1.dtb.walker 46 # Total bandwidth to/from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_total::cpu1.inst 172859 # Total bandwidth to/from this memory (bytes/s)
system.physmem.bw_total::cpu1.data 2034446 # Total bandwidth to/from this memory (bytes/s)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.physmem.bw_total::realview.ide 345 # Total bandwidth to/from this memory (bytes/s)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.physmem.bw_total::total 7324716 # Total bandwidth to/from this memory (bytes/s)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.realview.nvmem.bytes_read::cpu0.inst 20 # Number of bytes read from this memory
system.realview.nvmem.bytes_read::total 20 # Number of bytes read from this memory
system.realview.nvmem.bytes_inst_read::cpu0.inst 20 # Number of instructions bytes read from this memory
system.realview.nvmem.bytes_inst_read::total 20 # Number of instructions bytes read from this memory
system.realview.nvmem.num_reads::cpu0.inst 5 # Number of read requests responded to by this memory
system.realview.nvmem.num_reads::total 5 # Number of read requests responded to by this memory
system.realview.nvmem.bw_read::cpu0.inst 7 # Total read bandwidth from this memory (bytes/s)
system.realview.nvmem.bw_read::total 7 # Total read bandwidth from this memory (bytes/s)
system.realview.nvmem.bw_inst_read::cpu0.inst 7 # Instruction read bandwidth from this memory (bytes/s)
system.realview.nvmem.bw_inst_read::total 7 # Instruction read bandwidth from this memory (bytes/s)
system.realview.nvmem.bw_total::cpu0.inst 7 # Total bandwidth to/from this memory (bytes/s)
system.realview.nvmem.bw_total::total 7 # Total bandwidth to/from this memory (bytes/s)
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cf0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD).
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cf0.dma_read_bytes 1024 # Number of bytes transfered via DMA reads (not PRD).
system.cf0.dma_read_txs 1 # Number of DMA read transactions (not PRD).
system.cf0.dma_write_full_pages 540 # Number of full page size DMA writes.
system.cf0.dma_write_bytes 2318336 # Number of bytes transfered via DMA writes.
system.cf0.dma_write_txs 631 # Number of DMA write transactions.
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.cpu_clk_domain.clock 500 # Clock period in ticks
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.dstage2_mmu.stage2_tlb.walker.walks 0 # Table walker walks requested
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::total 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::total 0 # Table walker requests started/completed, data/inst
system.cpu0.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin::total 0 # Table walker requests started/completed, data/inst
stats: update stats for ARMv8 changes
2014-01-24 22:29:34 +01:00
system.cpu0.dstage2_mmu.stage2_tlb.inst_hits 0 # ITB inst hits
system.cpu0.dstage2_mmu.stage2_tlb.inst_misses 0 # ITB inst misses
system.cpu0.dstage2_mmu.stage2_tlb.read_hits 0 # DTB read hits
system.cpu0.dstage2_mmu.stage2_tlb.read_misses 0 # DTB read misses
system.cpu0.dstage2_mmu.stage2_tlb.write_hits 0 # DTB write hits
system.cpu0.dstage2_mmu.stage2_tlb.write_misses 0 # DTB write misses
system.cpu0.dstage2_mmu.stage2_tlb.flush_tlb 0 # Number of times complete TLB was flushed
system.cpu0.dstage2_mmu.stage2_tlb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA
system.cpu0.dstage2_mmu.stage2_tlb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu0.dstage2_mmu.stage2_tlb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
system.cpu0.dstage2_mmu.stage2_tlb.flush_entries 0 # Number of entries that have been flushed from TLB
system.cpu0.dstage2_mmu.stage2_tlb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu0.dstage2_mmu.stage2_tlb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu0.dstage2_mmu.stage2_tlb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu0.dstage2_mmu.stage2_tlb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu0.dstage2_mmu.stage2_tlb.read_accesses 0 # DTB read accesses
system.cpu0.dstage2_mmu.stage2_tlb.write_accesses 0 # DTB write accesses
system.cpu0.dstage2_mmu.stage2_tlb.inst_accesses 0 # ITB inst accesses
system.cpu0.dstage2_mmu.stage2_tlb.hits 0 # DTB hits
system.cpu0.dstage2_mmu.stage2_tlb.misses 0 # DTB misses
system.cpu0.dstage2_mmu.stage2_tlb.accesses 0 # DTB accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.walker.walks 5683 # Table walker walks requested
system.cpu0.dtb.walker.walksShort 5683 # Table walker walks initiated with short descriptors
system.cpu0.dtb.walker.walkWaitTime::samples 5683 # Table walker wait (enqueue to first request) latency
system.cpu0.dtb.walker.walkWaitTime::0 5683 100.00% 100.00% # Table walker wait (enqueue to first request) latency
system.cpu0.dtb.walker.walkWaitTime::total 5683 # Table walker wait (enqueue to first request) latency
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.dtb.walker.walksPending::samples 6705500 # Table walker pending requests distribution
system.cpu0.dtb.walker.walksPending::0 6705500 100.00% 100.00% # Table walker pending requests distribution
system.cpu0.dtb.walker.walksPending::total 6705500 # Table walker pending requests distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.walker.walkPageSizes::4K 3049 65.40% 65.40% # Table walker page sizes translated
system.cpu0.dtb.walker.walkPageSizes::1M 1613 34.60% 100.00% # Table walker page sizes translated
system.cpu0.dtb.walker.walkPageSizes::total 4662 # Table walker page sizes translated
system.cpu0.dtb.walker.walkRequestOrigin_Requested::Data 5683 # Table walker requests started/completed, data/inst
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.dtb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.walker.walkRequestOrigin_Requested::total 5683 # Table walker requests started/completed, data/inst
system.cpu0.dtb.walker.walkRequestOrigin_Completed::Data 4662 # Table walker requests started/completed, data/inst
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.dtb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.walker.walkRequestOrigin_Completed::total 4662 # Table walker requests started/completed, data/inst
system.cpu0.dtb.walker.walkRequestOrigin::total 10345 # Table walker requests started/completed, data/inst
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.dtb.inst_hits 0 # ITB inst hits
system.cpu0.dtb.inst_misses 0 # ITB inst misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.read_hits 15994593 # DTB read hits
system.cpu0.dtb.read_misses 4788 # DTB read misses
system.cpu0.dtb.write_hits 11285810 # DTB write hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dtb.write_misses 895 # DTB write misses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu0.dtb.flush_tlb 2813 # Number of times complete TLB was flushed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dtb.flush_tlb_mva 394 # Number of times TLB was flushed by MVA
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.dtb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu0.dtb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.flush_entries 3234 # Number of entries that have been flushed from TLB
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.dtb.align_faults 0 # Number of TLB faults due to alignment restrictions
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.prefetch_faults 773 # Number of TLB faults due to prefetch
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.dtb.domain_faults 0 # Number of TLB faults due to domain restrictions
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dtb.perms_faults 200 # Number of TLB faults due to permissions restrictions
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.read_accesses 15999381 # DTB read accesses
system.cpu0.dtb.write_accesses 11286705 # DTB write accesses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.dtb.inst_accesses 0 # ITB inst accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dtb.hits 27280403 # DTB hits
system.cpu0.dtb.misses 5683 # DTB misses
system.cpu0.dtb.accesses 27286086 # DTB accesses
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.istage2_mmu.stage2_tlb.walker.walks 0 # Table walker walks requested
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::total 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::total 0 # Table walker requests started/completed, data/inst
system.cpu0.istage2_mmu.stage2_tlb.walker.walkRequestOrigin::total 0 # Table walker requests started/completed, data/inst
stats: update stats for ARMv8 changes
2014-01-24 22:29:34 +01:00
system.cpu0.istage2_mmu.stage2_tlb.inst_hits 0 # ITB inst hits
system.cpu0.istage2_mmu.stage2_tlb.inst_misses 0 # ITB inst misses
system.cpu0.istage2_mmu.stage2_tlb.read_hits 0 # DTB read hits
system.cpu0.istage2_mmu.stage2_tlb.read_misses 0 # DTB read misses
system.cpu0.istage2_mmu.stage2_tlb.write_hits 0 # DTB write hits
system.cpu0.istage2_mmu.stage2_tlb.write_misses 0 # DTB write misses
system.cpu0.istage2_mmu.stage2_tlb.flush_tlb 0 # Number of times complete TLB was flushed
system.cpu0.istage2_mmu.stage2_tlb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA
system.cpu0.istage2_mmu.stage2_tlb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu0.istage2_mmu.stage2_tlb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
system.cpu0.istage2_mmu.stage2_tlb.flush_entries 0 # Number of entries that have been flushed from TLB
system.cpu0.istage2_mmu.stage2_tlb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu0.istage2_mmu.stage2_tlb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu0.istage2_mmu.stage2_tlb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu0.istage2_mmu.stage2_tlb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu0.istage2_mmu.stage2_tlb.read_accesses 0 # DTB read accesses
system.cpu0.istage2_mmu.stage2_tlb.write_accesses 0 # DTB write accesses
system.cpu0.istage2_mmu.stage2_tlb.inst_accesses 0 # ITB inst accesses
system.cpu0.istage2_mmu.stage2_tlb.hits 0 # DTB hits
system.cpu0.istage2_mmu.stage2_tlb.misses 0 # DTB misses
system.cpu0.istage2_mmu.stage2_tlb.accesses 0 # DTB accesses
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu0.itb.walker.walks 2611 # Table walker walks requested
system.cpu0.itb.walker.walksShort 2611 # Table walker walks initiated with short descriptors
system.cpu0.itb.walker.walkWaitTime::samples 2611 # Table walker wait (enqueue to first request) latency
system.cpu0.itb.walker.walkWaitTime::0 2611 100.00% 100.00% # Table walker wait (enqueue to first request) latency
system.cpu0.itb.walker.walkWaitTime::total 2611 # Table walker wait (enqueue to first request) latency
system.cpu0.itb.walker.walksPending::samples 6702500 # Table walker pending requests distribution
system.cpu0.itb.walker.walksPending::0 6702500 100.00% 100.00% # Table walker pending requests distribution
system.cpu0.itb.walker.walksPending::total 6702500 # Table walker pending requests distribution
system.cpu0.itb.walker.walkPageSizes::4K 1374 72.85% 72.85% # Table walker page sizes translated
system.cpu0.itb.walker.walkPageSizes::1M 512 27.15% 100.00% # Table walker page sizes translated
system.cpu0.itb.walker.walkPageSizes::total 1886 # Table walker page sizes translated
system.cpu0.itb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin_Requested::Inst 2611 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin_Requested::total 2611 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin_Completed::Inst 1886 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin_Completed::total 1886 # Table walker requests started/completed, data/inst
system.cpu0.itb.walker.walkRequestOrigin::total 4497 # Table walker requests started/completed, data/inst
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.itb.inst_hits 74779098 # ITB inst hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.itb.inst_misses 2611 # ITB inst misses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.itb.read_hits 0 # DTB read hits
system.cpu0.itb.read_misses 0 # DTB read misses
system.cpu0.itb.write_hits 0 # DTB write hits
system.cpu0.itb.write_misses 0 # DTB write misses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu0.itb.flush_tlb 2813 # Number of times complete TLB was flushed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.itb.flush_tlb_mva 394 # Number of times TLB was flushed by MVA
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.itb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu0.itb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.itb.flush_entries 1917 # Number of entries that have been flushed from TLB
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.itb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu0.itb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu0.itb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu0.itb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu0.itb.read_accesses 0 # DTB read accesses
system.cpu0.itb.write_accesses 0 # DTB write accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.itb.inst_accesses 74781709 # ITB inst accesses
system.cpu0.itb.hits 74779098 # DTB hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.itb.misses 2611 # DTB misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.itb.accesses 74781709 # DTB accesses
system.cpu0.numCycles 5536444792 # number of cpu cycles simulated
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.numWorkItemsStarted 0 # number of work items this cpu started
system.cpu0.numWorkItemsCompleted 0 # number of work items this cpu completed
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.committedInsts 72626333 # Number of instructions committed
system.cpu0.committedOps 87972335 # Number of ops (including micro ops) committed
system.cpu0.num_int_alu_accesses 77485858 # Number of integer alu accesses
system.cpu0.num_fp_alu_accesses 5256 # Number of float alu accesses
system.cpu0.num_func_calls 8692525 # number of times a function call or return occured
system.cpu0.num_conditional_control_insts 9458276 # number of instructions that are conditional controls
system.cpu0.num_int_insts 77485858 # number of integer instructions
system.cpu0.num_fp_insts 5256 # number of float instructions
system.cpu0.num_int_register_reads 144065688 # number of times the integer registers were read
system.cpu0.num_int_register_writes 54441738 # number of times the integer registers were written
system.cpu0.num_fp_register_reads 4098 # number of times the floating registers were read
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.num_fp_register_writes 1160 # number of times the floating registers were written
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.num_cc_register_reads 268855171 # number of times the CC registers were read
system.cpu0.num_cc_register_writes 31825079 # number of times the CC registers were written
system.cpu0.num_mem_refs 27911721 # number of memory refs
system.cpu0.num_load_insts 16162181 # Number of load instructions
system.cpu0.num_store_insts 11749540 # Number of store instructions
system.cpu0.num_idle_cycles 5353607317.458248 # Number of idle cycles
system.cpu0.num_busy_cycles 182837474.541752 # Number of busy cycles
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.not_idle_fraction 0.033024 # Percentage of non-idle cycles
system.cpu0.idle_fraction 0.966976 # Percentage of idle cycles
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.Branches 18597106 # Number of branches fetched
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.op_class::No_OpClass 2189 0.00% 0.00% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.op_class::IntAlu 61764727 68.82% 68.83% # Class of executed instruction
system.cpu0.op_class::IntMult 59660 0.07% 68.89% # Class of executed instruction
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.op_class::IntDiv 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatAdd 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatCmp 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatCvt 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatMult 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatDiv 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::FloatSqrt 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdAdd 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdAddAcc 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdAlu 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdCmp 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdCvt 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdMisc 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdMult 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdMultAcc 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdShift 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdShiftAcc 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdSqrt 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdFloatAdd 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdFloatAlu 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdFloatCmp 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdFloatCvt 0 0.00% 68.89% # Class of executed instruction
system.cpu0.op_class::SimdFloatDiv 0 0.00% 68.89% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.op_class::SimdFloatMisc 4403 0.00% 68.90% # Class of executed instruction
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.op_class::SimdFloatMult 0 0.00% 68.90% # Class of executed instruction
system.cpu0.op_class::SimdFloatMultAcc 0 0.00% 68.90% # Class of executed instruction
system.cpu0.op_class::SimdFloatSqrt 0 0.00% 68.90% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.op_class::MemRead 16162181 18.01% 86.91% # Class of executed instruction
system.cpu0.op_class::MemWrite 11749540 13.09% 100.00% # Class of executed instruction
stats: Bump stats for the fixes, and mostly DRAM controller changes
2014-05-10 00:58:50 +02:00
system.cpu0.op_class::IprAccess 0 0.00% 100.00% # Class of executed instruction
system.cpu0.op_class::InstPrefetch 0 0.00% 100.00% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.op_class::total 89742700 # Class of executed instruction
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.kern.inst.arm 0 # number of arm instructions executed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.kern.inst.quiesce 3083 # number of quiesce instructions executed
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.tags.replacements 819402 # number of replacements
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.dcache.tags.tagsinuse 511.997174 # Cycle average of tags in use
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.tags.total_refs 53784414 # Total number of references to valid blocks.
system.cpu0.dcache.tags.sampled_refs 819914 # Sample count of references to valid blocks.
system.cpu0.dcache.tags.avg_refs 65.597629 # Average number of references to valid blocks.
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu0.dcache.tags.warmup_cycle 23053500 # Cycle when the warmup percentage was hit.
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.tags.occ_blocks::cpu0.data 475.821817 # Average occupied blocks per requestor
system.cpu0.dcache.tags.occ_blocks::cpu1.data 36.175357 # Average occupied blocks per requestor
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.tags.occ_percent::cpu0.data 0.929339 # Average percentage of cache occupancy
system.cpu0.dcache.tags.occ_percent::cpu1.data 0.070655 # Average percentage of cache occupancy
stats: Cumulative stats update This patch updates the stats to reflect the: 1) addition of the internal queue in SimpleMemory, 2) moving of the memory class outside FSConfig, 3) fixing up of the 2D vector printing format, 4) specifying burst size and interface width for the DRAM instead of relying on cache-line size, 5) performing merging in the DRAM controller write buffer, and 6) fixing how idle cycles are counted in the atomic and timing CPU models. The main reason for bundling them up is to minimise the changeset size.
2013-08-19 09:52:36 +02:00
system.cpu0.dcache.tags.occ_percent::total 0.999994 # Average percentage of cache occupancy
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
system.cpu0.dcache.tags.occ_task_id_blocks::1024 512 # Occupied blocks per task id
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.dcache.tags.age_task_id_blocks_1024::0 286 # Occupied blocks per task id
system.cpu0.dcache.tags.age_task_id_blocks_1024::1 196 # Occupied blocks per task id
system.cpu0.dcache.tags.age_task_id_blocks_1024::2 30 # Occupied blocks per task id
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
system.cpu0.dcache.tags.occ_task_id_percent::1024 1 # Percentage of cache occupancy per task id
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.tags.tag_accesses 219237306 # Number of tag accesses
system.cpu0.dcache.tags.data_accesses 219237306 # Number of data accesses
system.cpu0.dcache.ReadReq_hits::cpu0.data 15302738 # number of ReadReq hits
system.cpu0.dcache.ReadReq_hits::cpu1.data 14826284 # number of ReadReq hits
system.cpu0.dcache.ReadReq_hits::total 30129022 # number of ReadReq hits
system.cpu0.dcache.WriteReq_hits::cpu0.data 10898497 # number of WriteReq hits
system.cpu0.dcache.WriteReq_hits::cpu1.data 11441613 # number of WriteReq hits
system.cpu0.dcache.WriteReq_hits::total 22340110 # number of WriteReq hits
system.cpu0.dcache.SoftPFReq_hits::cpu0.data 186051 # number of SoftPFReq hits
system.cpu0.dcache.SoftPFReq_hits::cpu1.data 209007 # number of SoftPFReq hits
system.cpu0.dcache.SoftPFReq_hits::total 395058 # number of SoftPFReq hits
system.cpu0.dcache.LoadLockedReq_hits::cpu0.data 235059 # number of LoadLockedReq hits
system.cpu0.dcache.LoadLockedReq_hits::cpu1.data 222271 # number of LoadLockedReq hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.LoadLockedReq_hits::total 457330 # number of LoadLockedReq hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.StoreCondReq_hits::cpu0.data 236765 # number of StoreCondReq hits
system.cpu0.dcache.StoreCondReq_hits::cpu1.data 223371 # number of StoreCondReq hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.StoreCondReq_hits::total 460136 # number of StoreCondReq hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.demand_hits::cpu0.data 26201235 # number of demand (read+write) hits
system.cpu0.dcache.demand_hits::cpu1.data 26267897 # number of demand (read+write) hits
system.cpu0.dcache.demand_hits::total 52469132 # number of demand (read+write) hits
system.cpu0.dcache.overall_hits::cpu0.data 26387286 # number of overall hits
system.cpu0.dcache.overall_hits::cpu1.data 26476904 # number of overall hits
system.cpu0.dcache.overall_hits::total 52864190 # number of overall hits
system.cpu0.dcache.ReadReq_misses::cpu0.data 197065 # number of ReadReq misses
system.cpu0.dcache.ReadReq_misses::cpu1.data 199241 # number of ReadReq misses
system.cpu0.dcache.ReadReq_misses::total 396306 # number of ReadReq misses
system.cpu0.dcache.WriteReq_misses::cpu0.data 137741 # number of WriteReq misses
system.cpu0.dcache.WriteReq_misses::cpu1.data 163937 # number of WriteReq misses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.WriteReq_misses::total 301678 # number of WriteReq misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.SoftPFReq_misses::cpu0.data 54401 # number of SoftPFReq misses
system.cpu0.dcache.SoftPFReq_misses::cpu1.data 61672 # number of SoftPFReq misses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.SoftPFReq_misses::total 116073 # number of SoftPFReq misses
system.cpu0.dcache.LoadLockedReq_misses::cpu0.data 4662 # number of LoadLockedReq misses
system.cpu0.dcache.LoadLockedReq_misses::cpu1.data 3967 # number of LoadLockedReq misses
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.dcache.LoadLockedReq_misses::total 8629 # number of LoadLockedReq misses
system.cpu0.dcache.StoreCondReq_misses::cpu1.data 2 # number of StoreCondReq misses
system.cpu0.dcache.StoreCondReq_misses::total 2 # number of StoreCondReq misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.demand_misses::cpu0.data 334806 # number of demand (read+write) misses
system.cpu0.dcache.demand_misses::cpu1.data 363178 # number of demand (read+write) misses
system.cpu0.dcache.demand_misses::total 697984 # number of demand (read+write) misses
system.cpu0.dcache.overall_misses::cpu0.data 389207 # number of overall misses
system.cpu0.dcache.overall_misses::cpu1.data 424850 # number of overall misses
system.cpu0.dcache.overall_misses::total 814057 # number of overall misses
system.cpu0.dcache.ReadReq_accesses::cpu0.data 15499803 # number of ReadReq accesses(hits+misses)
system.cpu0.dcache.ReadReq_accesses::cpu1.data 15025525 # number of ReadReq accesses(hits+misses)
system.cpu0.dcache.ReadReq_accesses::total 30525328 # number of ReadReq accesses(hits+misses)
system.cpu0.dcache.WriteReq_accesses::cpu0.data 11036238 # number of WriteReq accesses(hits+misses)
system.cpu0.dcache.WriteReq_accesses::cpu1.data 11605550 # number of WriteReq accesses(hits+misses)
system.cpu0.dcache.WriteReq_accesses::total 22641788 # number of WriteReq accesses(hits+misses)
system.cpu0.dcache.SoftPFReq_accesses::cpu0.data 240452 # number of SoftPFReq accesses(hits+misses)
system.cpu0.dcache.SoftPFReq_accesses::cpu1.data 270679 # number of SoftPFReq accesses(hits+misses)
system.cpu0.dcache.SoftPFReq_accesses::total 511131 # number of SoftPFReq accesses(hits+misses)
system.cpu0.dcache.LoadLockedReq_accesses::cpu0.data 239721 # number of LoadLockedReq accesses(hits+misses)
system.cpu0.dcache.LoadLockedReq_accesses::cpu1.data 226238 # number of LoadLockedReq accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.LoadLockedReq_accesses::total 465959 # number of LoadLockedReq accesses(hits+misses)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.StoreCondReq_accesses::cpu0.data 236765 # number of StoreCondReq accesses(hits+misses)
system.cpu0.dcache.StoreCondReq_accesses::cpu1.data 223373 # number of StoreCondReq accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.StoreCondReq_accesses::total 460138 # number of StoreCondReq accesses(hits+misses)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.demand_accesses::cpu0.data 26536041 # number of demand (read+write) accesses
system.cpu0.dcache.demand_accesses::cpu1.data 26631075 # number of demand (read+write) accesses
system.cpu0.dcache.demand_accesses::total 53167116 # number of demand (read+write) accesses
system.cpu0.dcache.overall_accesses::cpu0.data 26776493 # number of overall (read+write) accesses
system.cpu0.dcache.overall_accesses::cpu1.data 26901754 # number of overall (read+write) accesses
system.cpu0.dcache.overall_accesses::total 53678247 # number of overall (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.ReadReq_miss_rate::cpu0.data 0.012714 # miss rate for ReadReq accesses
system.cpu0.dcache.ReadReq_miss_rate::cpu1.data 0.013260 # miss rate for ReadReq accesses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu0.dcache.ReadReq_miss_rate::total 0.012983 # miss rate for ReadReq accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.WriteReq_miss_rate::cpu0.data 0.012481 # miss rate for WriteReq accesses
system.cpu0.dcache.WriteReq_miss_rate::cpu1.data 0.014126 # miss rate for WriteReq accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.cpu0.dcache.WriteReq_miss_rate::total 0.013324 # miss rate for WriteReq accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.SoftPFReq_miss_rate::cpu0.data 0.226245 # miss rate for SoftPFReq accesses
system.cpu0.dcache.SoftPFReq_miss_rate::cpu1.data 0.227842 # miss rate for SoftPFReq accesses
system.cpu0.dcache.SoftPFReq_miss_rate::total 0.227091 # miss rate for SoftPFReq accesses
system.cpu0.dcache.LoadLockedReq_miss_rate::cpu0.data 0.019448 # miss rate for LoadLockedReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.LoadLockedReq_miss_rate::cpu1.data 0.017535 # miss rate for LoadLockedReq accesses
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu0.dcache.LoadLockedReq_miss_rate::total 0.018519 # miss rate for LoadLockedReq accesses
system.cpu0.dcache.StoreCondReq_miss_rate::cpu1.data 0.000009 # miss rate for StoreCondReq accesses
system.cpu0.dcache.StoreCondReq_miss_rate::total 0.000004 # miss rate for StoreCondReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.demand_miss_rate::cpu0.data 0.012617 # miss rate for demand accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.dcache.demand_miss_rate::cpu1.data 0.013637 # miss rate for demand accesses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu0.dcache.demand_miss_rate::total 0.013128 # miss rate for demand accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.dcache.overall_miss_rate::cpu0.data 0.014535 # miss rate for overall accesses
system.cpu0.dcache.overall_miss_rate::cpu1.data 0.015793 # miss rate for overall accesses
system.cpu0.dcache.overall_miss_rate::total 0.015165 # miss rate for overall accesses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
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.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.avg_blocked_cycles::no_mshrs nan # average number of cycles each access was blocked
system.cpu0.dcache.avg_blocked_cycles::no_targets nan # average number of cycles each access was blocked
system.cpu0.dcache.fast_writes 0 # number of fast writes performed
system.cpu0.dcache.cache_copies 0 # number of cache copies performed
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.cpu0.dcache.writebacks::writebacks 682264 # number of writebacks
system.cpu0.dcache.writebacks::total 682264 # number of writebacks
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu0.dcache.no_allocate_misses 0 # Number of misses that were no-allocate
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.tags.replacements 1699214 # number of replacements
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.tags.tagsinuse 511.663681 # Cycle average of tags in use
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.tags.total_refs 145342721 # Total number of references to valid blocks.
system.cpu0.icache.tags.sampled_refs 1699726 # Sample count of references to valid blocks.
system.cpu0.icache.tags.avg_refs 85.509500 # Average number of references to valid blocks.
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.cpu0.icache.tags.warmup_cycle 7831491500 # Cycle when the warmup percentage was hit.
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.tags.occ_blocks::cpu0.inst 455.127325 # Average occupied blocks per requestor
system.cpu0.icache.tags.occ_blocks::cpu1.inst 56.536356 # Average occupied blocks per requestor
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.tags.occ_percent::cpu0.inst 0.888921 # Average percentage of cache occupancy
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.tags.occ_percent::cpu1.inst 0.110423 # Average percentage of cache occupancy
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.cpu0.icache.tags.occ_percent::total 0.999343 # Average percentage of cache occupancy
system.cpu0.icache.tags.occ_task_id_blocks::1024 512 # Occupied blocks per task id
system.cpu0.icache.tags.age_task_id_blocks_1024::0 197 # Occupied blocks per task id
system.cpu0.icache.tags.age_task_id_blocks_1024::1 77 # Occupied blocks per task id
system.cpu0.icache.tags.age_task_id_blocks_1024::2 233 # Occupied blocks per task id
system.cpu0.icache.tags.age_task_id_blocks_1024::3 5 # Occupied blocks per task id
system.cpu0.icache.tags.occ_task_id_percent::1024 1 # Percentage of cache occupancy per task id
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.tags.tag_accesses 148742185 # Number of tag accesses
system.cpu0.icache.tags.data_accesses 148742185 # Number of data accesses
system.cpu0.icache.ReadReq_hits::cpu0.inst 73936444 # number of ReadReq hits
system.cpu0.icache.ReadReq_hits::cpu1.inst 71406277 # number of ReadReq hits
system.cpu0.icache.ReadReq_hits::total 145342721 # number of ReadReq hits
system.cpu0.icache.demand_hits::cpu0.inst 73936444 # number of demand (read+write) hits
system.cpu0.icache.demand_hits::cpu1.inst 71406277 # number of demand (read+write) hits
system.cpu0.icache.demand_hits::total 145342721 # number of demand (read+write) hits
system.cpu0.icache.overall_hits::cpu0.inst 73936444 # number of overall hits
system.cpu0.icache.overall_hits::cpu1.inst 71406277 # number of overall hits
system.cpu0.icache.overall_hits::total 145342721 # number of overall hits
system.cpu0.icache.ReadReq_misses::cpu0.inst 844540 # number of ReadReq misses
system.cpu0.icache.ReadReq_misses::cpu1.inst 855192 # number of ReadReq misses
system.cpu0.icache.ReadReq_misses::total 1699732 # number of ReadReq misses
system.cpu0.icache.demand_misses::cpu0.inst 844540 # number of demand (read+write) misses
system.cpu0.icache.demand_misses::cpu1.inst 855192 # number of demand (read+write) misses
system.cpu0.icache.demand_misses::total 1699732 # number of demand (read+write) misses
system.cpu0.icache.overall_misses::cpu0.inst 844540 # number of overall misses
system.cpu0.icache.overall_misses::cpu1.inst 855192 # number of overall misses
system.cpu0.icache.overall_misses::total 1699732 # number of overall misses
system.cpu0.icache.ReadReq_accesses::cpu0.inst 74780984 # number of ReadReq accesses(hits+misses)
system.cpu0.icache.ReadReq_accesses::cpu1.inst 72261469 # number of ReadReq accesses(hits+misses)
system.cpu0.icache.ReadReq_accesses::total 147042453 # number of ReadReq accesses(hits+misses)
system.cpu0.icache.demand_accesses::cpu0.inst 74780984 # number of demand (read+write) accesses
system.cpu0.icache.demand_accesses::cpu1.inst 72261469 # number of demand (read+write) accesses
system.cpu0.icache.demand_accesses::total 147042453 # number of demand (read+write) accesses
system.cpu0.icache.overall_accesses::cpu0.inst 74780984 # number of overall (read+write) accesses
system.cpu0.icache.overall_accesses::cpu1.inst 72261469 # number of overall (read+write) accesses
system.cpu0.icache.overall_accesses::total 147042453 # number of overall (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.ReadReq_miss_rate::cpu0.inst 0.011294 # miss rate for ReadReq accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.ReadReq_miss_rate::cpu1.inst 0.011835 # miss rate for ReadReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.ReadReq_miss_rate::total 0.011559 # miss rate for ReadReq accesses
system.cpu0.icache.demand_miss_rate::cpu0.inst 0.011294 # miss rate for demand accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.demand_miss_rate::cpu1.inst 0.011835 # miss rate for demand accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.demand_miss_rate::total 0.011559 # miss rate for demand accesses
system.cpu0.icache.overall_miss_rate::cpu0.inst 0.011294 # miss rate for overall accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu0.icache.overall_miss_rate::cpu1.inst 0.011835 # miss rate for overall accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu0.icache.overall_miss_rate::total 0.011559 # miss rate for overall accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
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.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.avg_blocked_cycles::no_mshrs nan # average number of cycles each access was blocked
system.cpu0.icache.avg_blocked_cycles::no_targets nan # average number of cycles each access was blocked
system.cpu0.icache.fast_writes 0 # number of fast writes performed
system.cpu0.icache.cache_copies 0 # number of cache copies performed
system.cpu0.icache.no_allocate_misses 0 # Number of misses that were no-allocate
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.dstage2_mmu.stage2_tlb.walker.walks 0 # Table walker walks requested
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::total 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::total 0 # Table walker requests started/completed, data/inst
system.cpu1.dstage2_mmu.stage2_tlb.walker.walkRequestOrigin::total 0 # Table walker requests started/completed, data/inst
stats: update stats for ARMv8 changes
2014-01-24 22:29:34 +01:00
system.cpu1.dstage2_mmu.stage2_tlb.inst_hits 0 # ITB inst hits
system.cpu1.dstage2_mmu.stage2_tlb.inst_misses 0 # ITB inst misses
system.cpu1.dstage2_mmu.stage2_tlb.read_hits 0 # DTB read hits
system.cpu1.dstage2_mmu.stage2_tlb.read_misses 0 # DTB read misses
system.cpu1.dstage2_mmu.stage2_tlb.write_hits 0 # DTB write hits
system.cpu1.dstage2_mmu.stage2_tlb.write_misses 0 # DTB write misses
system.cpu1.dstage2_mmu.stage2_tlb.flush_tlb 0 # Number of times complete TLB was flushed
system.cpu1.dstage2_mmu.stage2_tlb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA
system.cpu1.dstage2_mmu.stage2_tlb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu1.dstage2_mmu.stage2_tlb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
system.cpu1.dstage2_mmu.stage2_tlb.flush_entries 0 # Number of entries that have been flushed from TLB
system.cpu1.dstage2_mmu.stage2_tlb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu1.dstage2_mmu.stage2_tlb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu1.dstage2_mmu.stage2_tlb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu1.dstage2_mmu.stage2_tlb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu1.dstage2_mmu.stage2_tlb.read_accesses 0 # DTB read accesses
system.cpu1.dstage2_mmu.stage2_tlb.write_accesses 0 # DTB write accesses
system.cpu1.dstage2_mmu.stage2_tlb.inst_accesses 0 # ITB inst accesses
system.cpu1.dstage2_mmu.stage2_tlb.hits 0 # DTB hits
system.cpu1.dstage2_mmu.stage2_tlb.misses 0 # DTB misses
system.cpu1.dstage2_mmu.stage2_tlb.accesses 0 # DTB accesses
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.dtb.walker.walks 6203 # Table walker walks requested
system.cpu1.dtb.walker.walksShort 6203 # Table walker walks initiated with short descriptors
system.cpu1.dtb.walker.walkWaitTime::samples 6203 # Table walker wait (enqueue to first request) latency
system.cpu1.dtb.walker.walkWaitTime::0 6203 100.00% 100.00% # Table walker wait (enqueue to first request) latency
system.cpu1.dtb.walker.walkWaitTime::total 6203 # Table walker wait (enqueue to first request) latency
system.cpu1.dtb.walker.walksPending::samples 1000002000 # Table walker pending requests distribution
system.cpu1.dtb.walker.walksPending::0 1000002000 100.00% 100.00% # Table walker pending requests distribution
system.cpu1.dtb.walker.walksPending::total 1000002000 # Table walker pending requests distribution
system.cpu1.dtb.walker.walkPageSizes::4K 3703 73.18% 73.18% # Table walker page sizes translated
system.cpu1.dtb.walker.walkPageSizes::1M 1357 26.82% 100.00% # Table walker page sizes translated
system.cpu1.dtb.walker.walkPageSizes::total 5060 # Table walker page sizes translated
system.cpu1.dtb.walker.walkRequestOrigin_Requested::Data 6203 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin_Requested::total 6203 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin_Completed::Data 5060 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin_Completed::total 5060 # Table walker requests started/completed, data/inst
system.cpu1.dtb.walker.walkRequestOrigin::total 11263 # Table walker requests started/completed, data/inst
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.dtb.inst_hits 0 # ITB inst hits
system.cpu1.dtb.inst_misses 0 # ITB inst misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.dtb.read_hits 15529940 # DTB read hits
system.cpu1.dtb.read_misses 5414 # DTB read misses
system.cpu1.dtb.write_hits 11838406 # DTB write hits
system.cpu1.dtb.write_misses 789 # DTB write misses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu1.dtb.flush_tlb 2817 # Number of times complete TLB was flushed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.dtb.flush_tlb_mva 523 # Number of times TLB was flushed by MVA
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu1.dtb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu1.dtb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.dtb.flush_entries 3183 # Number of entries that have been flushed from TLB
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.dtb.align_faults 0 # Number of TLB faults due to alignment restrictions
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.dtb.prefetch_faults 909 # Number of TLB faults due to prefetch
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.dtb.domain_faults 0 # Number of TLB faults due to domain restrictions
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.dtb.perms_faults 245 # Number of TLB faults due to permissions restrictions
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.dtb.read_accesses 15535354 # DTB read accesses
system.cpu1.dtb.write_accesses 11839195 # DTB write accesses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.dtb.inst_accesses 0 # ITB inst accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.dtb.hits 27368346 # DTB hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.dtb.misses 6203 # DTB misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.dtb.accesses 27374549 # DTB accesses
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.istage2_mmu.stage2_tlb.walker.walks 0 # Table walker walks requested
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Requested::total 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::Inst 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin_Completed::total 0 # Table walker requests started/completed, data/inst
system.cpu1.istage2_mmu.stage2_tlb.walker.walkRequestOrigin::total 0 # Table walker requests started/completed, data/inst
stats: update stats for ARMv8 changes
2014-01-24 22:29:34 +01:00
system.cpu1.istage2_mmu.stage2_tlb.inst_hits 0 # ITB inst hits
system.cpu1.istage2_mmu.stage2_tlb.inst_misses 0 # ITB inst misses
system.cpu1.istage2_mmu.stage2_tlb.read_hits 0 # DTB read hits
system.cpu1.istage2_mmu.stage2_tlb.read_misses 0 # DTB read misses
system.cpu1.istage2_mmu.stage2_tlb.write_hits 0 # DTB write hits
system.cpu1.istage2_mmu.stage2_tlb.write_misses 0 # DTB write misses
system.cpu1.istage2_mmu.stage2_tlb.flush_tlb 0 # Number of times complete TLB was flushed
system.cpu1.istage2_mmu.stage2_tlb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA
system.cpu1.istage2_mmu.stage2_tlb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu1.istage2_mmu.stage2_tlb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
system.cpu1.istage2_mmu.stage2_tlb.flush_entries 0 # Number of entries that have been flushed from TLB
system.cpu1.istage2_mmu.stage2_tlb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu1.istage2_mmu.stage2_tlb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu1.istage2_mmu.stage2_tlb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu1.istage2_mmu.stage2_tlb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu1.istage2_mmu.stage2_tlb.read_accesses 0 # DTB read accesses
system.cpu1.istage2_mmu.stage2_tlb.write_accesses 0 # DTB write accesses
system.cpu1.istage2_mmu.stage2_tlb.inst_accesses 0 # ITB inst accesses
system.cpu1.istage2_mmu.stage2_tlb.hits 0 # DTB hits
system.cpu1.istage2_mmu.stage2_tlb.misses 0 # DTB misses
system.cpu1.istage2_mmu.stage2_tlb.accesses 0 # DTB accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.walker.walks 3041 # Table walker walks requested
system.cpu1.itb.walker.walksShort 3041 # Table walker walks initiated with short descriptors
system.cpu1.itb.walker.walkWaitTime::samples 3041 # Table walker wait (enqueue to first request) latency
system.cpu1.itb.walker.walkWaitTime::0 3041 100.00% 100.00% # Table walker wait (enqueue to first request) latency
system.cpu1.itb.walker.walkWaitTime::total 3041 # Table walker wait (enqueue to first request) latency
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.itb.walker.walksPending::samples 1000000500 # Table walker pending requests distribution
system.cpu1.itb.walker.walksPending::0 1000000500 100.00% 100.00% # Table walker pending requests distribution
system.cpu1.itb.walker.walksPending::total 1000000500 # Table walker pending requests distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.walker.walkPageSizes::4K 1721 81.53% 81.53% # Table walker page sizes translated
system.cpu1.itb.walker.walkPageSizes::1M 390 18.47% 100.00% # Table walker page sizes translated
system.cpu1.itb.walker.walkPageSizes::total 2111 # Table walker page sizes translated
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.itb.walker.walkRequestOrigin_Requested::Data 0 # Table walker requests started/completed, data/inst
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.walker.walkRequestOrigin_Requested::Inst 3041 # Table walker requests started/completed, data/inst
system.cpu1.itb.walker.walkRequestOrigin_Requested::total 3041 # Table walker requests started/completed, data/inst
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes Changes due to speculative execution of an unaligned PC, introduction of TLB stats, changes and re-work of the prefetcher, and the introduction of rank-wise refresh in the DRAM controller.
2014-12-23 15:31:20 +01:00
system.cpu1.itb.walker.walkRequestOrigin_Completed::Data 0 # Table walker requests started/completed, data/inst
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.walker.walkRequestOrigin_Completed::Inst 2111 # Table walker requests started/completed, data/inst
system.cpu1.itb.walker.walkRequestOrigin_Completed::total 2111 # Table walker requests started/completed, data/inst
system.cpu1.itb.walker.walkRequestOrigin::total 5152 # Table walker requests started/completed, data/inst
system.cpu1.itb.inst_hits 72259358 # ITB inst hits
system.cpu1.itb.inst_misses 3041 # ITB inst misses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.itb.read_hits 0 # DTB read hits
system.cpu1.itb.read_misses 0 # DTB read misses
system.cpu1.itb.write_hits 0 # DTB write hits
system.cpu1.itb.write_misses 0 # DTB write misses
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.cpu1.itb.flush_tlb 2817 # Number of times complete TLB was flushed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.itb.flush_tlb_mva 523 # Number of times TLB was flushed by MVA
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.cpu1.itb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID
system.cpu1.itb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.flush_entries 2022 # Number of entries that have been flushed from TLB
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.itb.align_faults 0 # Number of TLB faults due to alignment restrictions
system.cpu1.itb.prefetch_faults 0 # Number of TLB faults due to prefetch
system.cpu1.itb.domain_faults 0 # Number of TLB faults due to domain restrictions
system.cpu1.itb.perms_faults 0 # Number of TLB faults due to permissions restrictions
system.cpu1.itb.read_accesses 0 # DTB read accesses
system.cpu1.itb.write_accesses 0 # DTB write accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.itb.inst_accesses 72262399 # ITB inst accesses
system.cpu1.itb.hits 72259358 # DTB hits
system.cpu1.itb.misses 3041 # DTB misses
system.cpu1.itb.accesses 72262399 # DTB accesses
system.cpu1.numCycles 88040649 # number of cpu cycles simulated
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.numWorkItemsStarted 0 # number of work items this cpu started
system.cpu1.numWorkItemsCompleted 0 # number of work items this cpu completed
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.committedInsts 70146546 # Number of instructions committed
system.cpu1.committedOps 85830789 # Number of ops (including micro ops) committed
system.cpu1.num_int_alu_accesses 75676825 # Number of integer alu accesses
system.cpu1.num_fp_alu_accesses 6228 # Number of float alu accesses
system.cpu1.num_func_calls 8181374 # number of times a function call or return occured
system.cpu1.num_conditional_control_insts 9272054 # number of instructions that are conditional controls
system.cpu1.num_int_insts 75676825 # number of integer instructions
system.cpu1.num_fp_insts 6228 # number of float instructions
system.cpu1.num_int_register_reads 140994115 # number of times the integer registers were read
system.cpu1.num_int_register_writes 52737742 # number of times the integer registers were written
system.cpu1.num_fp_register_reads 4674 # number of times the floating registers were read
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.num_fp_register_writes 1556 # number of times the floating registers were written
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.num_cc_register_reads 261998832 # number of times the CC registers were read
system.cpu1.num_cc_register_writes 30539220 # number of times the CC registers were written
system.cpu1.num_mem_refs 28027555 # number of memory refs
system.cpu1.num_load_insts 15693703 # Number of load instructions
system.cpu1.num_store_insts 12333852 # Number of store instructions
system.cpu1.num_idle_cycles 85384966.713327 # Number of idle cycles
system.cpu1.num_busy_cycles 2655682.286673 # Number of busy cycles
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.not_idle_fraction 0.030164 # Percentage of non-idle cycles
system.cpu1.idle_fraction 0.969836 # Percentage of idle cycles
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.Branches 17799875 # Number of branches fetched
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.op_class::No_OpClass 148 0.00% 0.00% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.op_class::IntAlu 59388111 67.89% 67.89% # Class of executed instruction
system.cpu1.op_class::IntMult 57232 0.07% 67.96% # Class of executed instruction
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.op_class::IntDiv 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatAdd 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatCmp 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatCvt 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatMult 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatDiv 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::FloatSqrt 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdAdd 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdAddAcc 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdAlu 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdCmp 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdCvt 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdMisc 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdMult 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdMultAcc 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdShift 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdShiftAcc 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdSqrt 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatAdd 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatAlu 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatCmp 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatCvt 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatDiv 0 0.00% 67.96% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.op_class::SimdFloatMisc 4166 0.00% 67.96% # Class of executed instruction
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.cpu1.op_class::SimdFloatMult 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatMultAcc 0 0.00% 67.96% # Class of executed instruction
system.cpu1.op_class::SimdFloatSqrt 0 0.00% 67.96% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.op_class::MemRead 15693703 17.94% 85.90% # Class of executed instruction
system.cpu1.op_class::MemWrite 12333852 14.10% 100.00% # Class of executed instruction
stats: Bump stats for the fixes, and mostly DRAM controller changes
2014-05-10 00:58:50 +02:00
system.cpu1.op_class::IprAccess 0 0.00% 100.00% # Class of executed instruction
system.cpu1.op_class::InstPrefetch 0 0.00% 100.00% # Class of executed instruction
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.cpu1.op_class::total 87477212 # Class of executed instruction
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.cpu1.kern.inst.arm 0 # number of arm instructions executed
system.cpu1.kern.inst.quiesce 0 # number of quiesce instructions executed
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.trans_dist::ReadReq 30164 # Transaction distribution
system.iobus.trans_dist::ReadResp 30164 # Transaction distribution
system.iobus.trans_dist::WriteReq 59002 # Transaction distribution
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.iobus.trans_dist::WriteResp 59002 # Transaction distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.pkt_count_system.bridge.master::system.realview.uart.pio 54116 # Packet count per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.iobus.pkt_count_system.bridge.master::system.realview.realview_io.pio 116 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.timer0.pio 34 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.timer1.pio 20 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.kmi0.pio 120 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.kmi1.pio 834 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.rtc.pio 32 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.uart1_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.uart2_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.uart3_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.sp810_fake.pio 76 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.watchdog_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.aaci_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.lan_fake.pio 4 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.usb_fake.pio 10 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.mmc_fake.pio 16 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.ide.pio 7244 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.ide-pciconf 210 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.ethernet.pio 42268 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.ethernet-pciconf 164 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.bridge.master::system.realview.pciconfig.pio 60 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.pkt_count_system.bridge.master::total 105404 # Packet count per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.iobus.pkt_count_system.realview.ide.dma::system.iocache.cpu_side 72928 # Packet count per connected master and slave (bytes)
system.iobus.pkt_count_system.realview.ide.dma::total 72928 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.pkt_count::total 178332 # Packet count per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.uart.pio 67833 # Cumulative packet size per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.iobus.pkt_size_system.bridge.master::system.realview.realview_io.pio 232 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.timer0.pio 68 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.timer1.pio 40 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.kmi0.pio 84 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.kmi1.pio 441 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.rtc.pio 64 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.uart1_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.uart2_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.uart3_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.sp810_fake.pio 152 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.watchdog_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.aaci_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.lan_fake.pio 8 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.usb_fake.pio 20 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.mmc_fake.pio 32 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.ide.pio 4753 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.ide-pciconf 265 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.ethernet.pio 84536 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.ethernet-pciconf 253 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.bridge.master::system.realview.pciconfig.pio 120 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.pkt_size_system.bridge.master::total 159061 # Cumulative packet size per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.iobus.pkt_size_system.realview.ide.dma::system.iocache.cpu_side 2321152 # Cumulative packet size per connected master and slave (bytes)
system.iobus.pkt_size_system.realview.ide.dma::total 2321152 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iobus.pkt_size::total 2480213 # Cumulative packet size per connected master and slave (bytes)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.tags.replacements 36430 # number of replacements
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iocache.tags.tagsinuse 0.909961 # Cycle average of tags in use
stats: Cumulative stats update This patch updates the stats to reflect the: 1) addition of the internal queue in SimpleMemory, 2) moving of the memory class outside FSConfig, 3) fixing up of the 2D vector printing format, 4) specifying burst size and interface width for the DRAM instead of relying on cache-line size, 5) performing merging in the DRAM controller write buffer, and 6) fixing how idle cycles are counted in the atomic and timing CPU models. The main reason for bundling them up is to minimise the changeset size.
2013-08-19 09:52:36 +02:00
system.iocache.tags.total_refs 0 # Total number of references to valid blocks.
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.tags.sampled_refs 36446 # Sample count of references to valid blocks.
system.iocache.tags.avg_refs 0 # Average number of references to valid blocks.
tests: Update stats no match. Bootloader I had on my sytem was an older version with a couple of instruction differences.
2014-11-03 17:14:42 +01:00
system.iocache.tags.warmup_cycle 227409731009 # Cycle when the warmup percentage was hit.
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.iocache.tags.occ_blocks::realview.ide 0.909961 # Average occupied blocks per requestor
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.iocache.tags.occ_percent::realview.ide 0.056873 # Average percentage of cache occupancy
system.iocache.tags.occ_percent::total 0.056873 # Average percentage of cache occupancy
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.tags.occ_task_id_blocks::1023 16 # Occupied blocks per task id
system.iocache.tags.age_task_id_blocks_1023::3 16 # Occupied blocks per task id
system.iocache.tags.occ_task_id_percent::1023 1 # Percentage of cache occupancy per task id
system.iocache.tags.tag_accesses 328176 # Number of tag accesses
system.iocache.tags.data_accesses 328176 # Number of data accesses
system.iocache.ReadReq_misses::realview.ide 240 # number of ReadReq misses
system.iocache.ReadReq_misses::total 240 # number of ReadReq misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.iocache.WriteLineReq_misses::realview.ide 36224 # number of WriteLineReq misses
system.iocache.WriteLineReq_misses::total 36224 # number of WriteLineReq misses
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.demand_misses::realview.ide 240 # number of demand (read+write) misses
system.iocache.demand_misses::total 240 # number of demand (read+write) misses
system.iocache.overall_misses::realview.ide 240 # number of overall misses
system.iocache.overall_misses::total 240 # number of overall misses
system.iocache.ReadReq_accesses::realview.ide 240 # number of ReadReq accesses(hits+misses)
system.iocache.ReadReq_accesses::total 240 # number of ReadReq accesses(hits+misses)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.iocache.WriteLineReq_accesses::realview.ide 36224 # number of WriteLineReq accesses(hits+misses)
system.iocache.WriteLineReq_accesses::total 36224 # number of WriteLineReq accesses(hits+misses)
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.demand_accesses::realview.ide 240 # number of demand (read+write) accesses
system.iocache.demand_accesses::total 240 # number of demand (read+write) accesses
system.iocache.overall_accesses::realview.ide 240 # number of overall (read+write) accesses
system.iocache.overall_accesses::total 240 # number of overall (read+write) accesses
system.iocache.ReadReq_miss_rate::realview.ide 1 # miss rate for ReadReq accesses
system.iocache.ReadReq_miss_rate::total 1 # miss rate for ReadReq accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.iocache.WriteLineReq_miss_rate::realview.ide 1 # miss rate for WriteLineReq accesses
system.iocache.WriteLineReq_miss_rate::total 1 # miss rate for WriteLineReq accesses
tests: Update regressions for the new kernels and various preceeding fixes.
2014-10-30 05:18:29 +01:00
system.iocache.demand_miss_rate::realview.ide 1 # miss rate for demand accesses
system.iocache.demand_miss_rate::total 1 # miss rate for demand accesses
system.iocache.overall_miss_rate::realview.ide 1 # miss rate for overall accesses
system.iocache.overall_miss_rate::total 1 # miss rate for overall accesses
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.iocache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked
system.iocache.blocked_cycles::no_targets 0 # number of cycles access was blocked
system.iocache.blocked::no_mshrs 0 # number of cycles access was blocked
system.iocache.blocked::no_targets 0 # number of cycles access was blocked
system.iocache.avg_blocked_cycles::no_mshrs nan # average number of cycles each access was blocked
system.iocache.avg_blocked_cycles::no_targets nan # average number of cycles each access was blocked
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.iocache.fast_writes 0 # number of fast writes performed
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.iocache.cache_copies 0 # number of cache copies performed
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.iocache.writebacks::writebacks 36190 # number of writebacks
system.iocache.writebacks::total 36190 # number of writebacks
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
system.iocache.no_allocate_misses 0 # Number of misses that were no-allocate
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.replacements 109907 # number of replacements
system.l2c.tags.tagsinuse 65155.309141 # Cycle average of tags in use
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.l2c.tags.total_refs 4528496 # Total number of references to valid blocks.
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.sampled_refs 175188 # Sample count of references to valid blocks.
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.l2c.tags.avg_refs 25.849350 # Average number of references to valid blocks.
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.warmup_cycle 0 # Cycle when the warmup percentage was hit.
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.occ_blocks::writebacks 48764.072075 # Average occupied blocks per requestor
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.tags.occ_blocks::cpu0.dtb.walker 2.924326 # Average occupied blocks per requestor
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_blocks::cpu0.itb.walker 0.000096 # Average occupied blocks per requestor
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.occ_blocks::cpu0.inst 5143.224775 # Average occupied blocks per requestor
system.l2c.tags.occ_blocks::cpu0.data 4734.504525 # Average occupied blocks per requestor
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_blocks::cpu1.dtb.walker 0.978702 # Average occupied blocks per requestor
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.occ_blocks::cpu1.inst 4025.377664 # Average occupied blocks per requestor
system.l2c.tags.occ_blocks::cpu1.data 2484.226979 # Average occupied blocks per requestor
system.l2c.tags.occ_percent::writebacks 0.744081 # Average percentage of cache occupancy
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_percent::cpu0.dtb.walker 0.000045 # Average percentage of cache occupancy
system.l2c.tags.occ_percent::cpu0.itb.walker 0.000000 # Average percentage of cache occupancy
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.occ_percent::cpu0.inst 0.078479 # Average percentage of cache occupancy
system.l2c.tags.occ_percent::cpu0.data 0.072243 # Average percentage of cache occupancy
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_percent::cpu1.dtb.walker 0.000015 # Average percentage of cache occupancy
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.occ_percent::cpu1.inst 0.061422 # Average percentage of cache occupancy
system.l2c.tags.occ_percent::cpu1.data 0.037906 # Average percentage of cache occupancy
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_percent::total 0.994191 # Average percentage of cache occupancy
system.l2c.tags.occ_task_id_blocks::1023 4 # Occupied blocks per task id
system.l2c.tags.occ_task_id_blocks::1024 65277 # Occupied blocks per task id
system.l2c.tags.age_task_id_blocks_1023::4 4 # Occupied blocks per task id
system.l2c.tags.age_task_id_blocks_1024::0 40 # Occupied blocks per task id
system.l2c.tags.age_task_id_blocks_1024::1 180 # Occupied blocks per task id
system.l2c.tags.age_task_id_blocks_1024::2 3716 # Occupied blocks per task id
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.tags.age_task_id_blocks_1024::3 10699 # Occupied blocks per task id
system.l2c.tags.age_task_id_blocks_1024::4 50642 # Occupied blocks per task id
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.tags.occ_task_id_percent::1023 0.000061 # Percentage of cache occupancy per task id
system.l2c.tags.occ_task_id_percent::1024 0.996048 # Percentage of cache occupancy per task id
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.l2c.tags.tag_accesses 40608233 # Number of tag accesses
system.l2c.tags.data_accesses 40608233 # Number of data accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadReq_hits::cpu0.dtb.walker 4700 # number of ReadReq hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_hits::cpu0.itb.walker 2287 # number of ReadReq hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadReq_hits::cpu1.dtb.walker 5001 # number of ReadReq hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_hits::cpu1.itb.walker 2453 # number of ReadReq hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadReq_hits::total 14441 # number of ReadReq hits
system.l2c.Writeback_hits::writebacks 682264 # number of Writeback hits
system.l2c.Writeback_hits::total 682264 # number of Writeback hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.UpgradeReq_hits::cpu0.data 13 # number of UpgradeReq hits
system.l2c.UpgradeReq_hits::cpu1.data 15 # number of UpgradeReq hits
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.UpgradeReq_hits::total 28 # number of UpgradeReq hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadExReq_hits::cpu0.data 72515 # number of ReadExReq hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadExReq_hits::cpu1.data 78631 # number of ReadExReq hits
system.l2c.ReadExReq_hits::total 151146 # number of ReadExReq hits
system.l2c.ReadCleanReq_hits::cpu0.inst 833751 # number of ReadCleanReq hits
system.l2c.ReadCleanReq_hits::cpu1.inst 847665 # number of ReadCleanReq hits
system.l2c.ReadCleanReq_hits::total 1681416 # number of ReadCleanReq hits
system.l2c.ReadSharedReq_hits::cpu0.data 246350 # number of ReadSharedReq hits
system.l2c.ReadSharedReq_hits::cpu1.data 259095 # number of ReadSharedReq hits
system.l2c.ReadSharedReq_hits::total 505445 # number of ReadSharedReq hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.demand_hits::cpu0.dtb.walker 4700 # number of demand (read+write) hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_hits::cpu0.itb.walker 2287 # number of demand (read+write) hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_hits::cpu0.inst 833751 # number of demand (read+write) hits
system.l2c.demand_hits::cpu0.data 318865 # number of demand (read+write) hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.demand_hits::cpu1.dtb.walker 5001 # number of demand (read+write) hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_hits::cpu1.itb.walker 2453 # number of demand (read+write) hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_hits::cpu1.inst 847665 # number of demand (read+write) hits
system.l2c.demand_hits::cpu1.data 337726 # number of demand (read+write) hits
system.l2c.demand_hits::total 2352448 # number of demand (read+write) hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.overall_hits::cpu0.dtb.walker 4700 # number of overall hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_hits::cpu0.itb.walker 2287 # number of overall hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_hits::cpu0.inst 833751 # number of overall hits
system.l2c.overall_hits::cpu0.data 318865 # number of overall hits
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.overall_hits::cpu1.dtb.walker 5001 # number of overall hits
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_hits::cpu1.itb.walker 2453 # number of overall hits
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_hits::cpu1.inst 847665 # number of overall hits
system.l2c.overall_hits::cpu1.data 337726 # number of overall hits
system.l2c.overall_hits::total 2352448 # number of overall hits
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.ReadReq_misses::cpu0.dtb.walker 5 # number of ReadReq misses
system.l2c.ReadReq_misses::cpu0.itb.walker 1 # number of ReadReq misses
system.l2c.ReadReq_misses::cpu1.dtb.walker 2 # number of ReadReq misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadReq_misses::total 8 # number of ReadReq misses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.UpgradeReq_misses::cpu0.data 1249 # number of UpgradeReq misses
system.l2c.UpgradeReq_misses::cpu1.data 1479 # number of UpgradeReq misses
system.l2c.UpgradeReq_misses::total 2728 # number of UpgradeReq misses
system.l2c.SCUpgradeReq_misses::cpu1.data 2 # number of SCUpgradeReq misses
system.l2c.SCUpgradeReq_misses::total 2 # number of SCUpgradeReq misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadExReq_misses::cpu0.data 63964 # number of ReadExReq misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadExReq_misses::cpu1.data 83812 # number of ReadExReq misses
system.l2c.ReadExReq_misses::total 147776 # number of ReadExReq misses
system.l2c.ReadCleanReq_misses::cpu0.inst 10779 # number of ReadCleanReq misses
system.l2c.ReadCleanReq_misses::cpu1.inst 7519 # number of ReadCleanReq misses
system.l2c.ReadCleanReq_misses::total 18298 # number of ReadCleanReq misses
system.l2c.ReadSharedReq_misses::cpu0.data 9778 # number of ReadSharedReq misses
system.l2c.ReadSharedReq_misses::cpu1.data 5785 # number of ReadSharedReq misses
system.l2c.ReadSharedReq_misses::total 15563 # number of ReadSharedReq misses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.demand_misses::cpu0.dtb.walker 5 # number of demand (read+write) misses
system.l2c.demand_misses::cpu0.itb.walker 1 # number of demand (read+write) misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_misses::cpu0.inst 10779 # number of demand (read+write) misses
system.l2c.demand_misses::cpu0.data 73742 # number of demand (read+write) misses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.demand_misses::cpu1.dtb.walker 2 # number of demand (read+write) misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_misses::cpu1.inst 7519 # number of demand (read+write) misses
system.l2c.demand_misses::cpu1.data 89597 # number of demand (read+write) misses
system.l2c.demand_misses::total 181645 # number of demand (read+write) misses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.overall_misses::cpu0.dtb.walker 5 # number of overall misses
system.l2c.overall_misses::cpu0.itb.walker 1 # number of overall misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_misses::cpu0.inst 10779 # number of overall misses
system.l2c.overall_misses::cpu0.data 73742 # number of overall misses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.overall_misses::cpu1.dtb.walker 2 # number of overall misses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_misses::cpu1.inst 7519 # number of overall misses
system.l2c.overall_misses::cpu1.data 89597 # number of overall misses
system.l2c.overall_misses::total 181645 # number of overall misses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadReq_accesses::cpu0.dtb.walker 4705 # number of ReadReq accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_accesses::cpu0.itb.walker 2288 # number of ReadReq accesses(hits+misses)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadReq_accesses::cpu1.dtb.walker 5003 # number of ReadReq accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_accesses::cpu1.itb.walker 2453 # number of ReadReq accesses(hits+misses)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadReq_accesses::total 14449 # number of ReadReq accesses(hits+misses)
system.l2c.Writeback_accesses::writebacks 682264 # number of Writeback accesses(hits+misses)
system.l2c.Writeback_accesses::total 682264 # number of Writeback accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.UpgradeReq_accesses::cpu0.data 1262 # number of UpgradeReq accesses(hits+misses)
system.l2c.UpgradeReq_accesses::cpu1.data 1494 # number of UpgradeReq accesses(hits+misses)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.UpgradeReq_accesses::total 2756 # number of UpgradeReq accesses(hits+misses)
system.l2c.SCUpgradeReq_accesses::cpu1.data 2 # number of SCUpgradeReq accesses(hits+misses)
system.l2c.SCUpgradeReq_accesses::total 2 # number of SCUpgradeReq accesses(hits+misses)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadExReq_accesses::cpu0.data 136479 # number of ReadExReq accesses(hits+misses)
system.l2c.ReadExReq_accesses::cpu1.data 162443 # number of ReadExReq accesses(hits+misses)
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadExReq_accesses::total 298922 # number of ReadExReq accesses(hits+misses)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadCleanReq_accesses::cpu0.inst 844530 # number of ReadCleanReq accesses(hits+misses)
system.l2c.ReadCleanReq_accesses::cpu1.inst 855184 # number of ReadCleanReq accesses(hits+misses)
system.l2c.ReadCleanReq_accesses::total 1699714 # number of ReadCleanReq accesses(hits+misses)
system.l2c.ReadSharedReq_accesses::cpu0.data 256128 # number of ReadSharedReq accesses(hits+misses)
system.l2c.ReadSharedReq_accesses::cpu1.data 264880 # number of ReadSharedReq accesses(hits+misses)
system.l2c.ReadSharedReq_accesses::total 521008 # number of ReadSharedReq accesses(hits+misses)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.demand_accesses::cpu0.dtb.walker 4705 # number of demand (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_accesses::cpu0.itb.walker 2288 # number of demand (read+write) accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.demand_accesses::cpu0.inst 844530 # number of demand (read+write) accesses
system.l2c.demand_accesses::cpu0.data 392607 # number of demand (read+write) accesses
system.l2c.demand_accesses::cpu1.dtb.walker 5003 # number of demand (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_accesses::cpu1.itb.walker 2453 # number of demand (read+write) accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.demand_accesses::cpu1.inst 855184 # number of demand (read+write) accesses
system.l2c.demand_accesses::cpu1.data 427323 # number of demand (read+write) accesses
system.l2c.demand_accesses::total 2534093 # number of demand (read+write) accesses
system.l2c.overall_accesses::cpu0.dtb.walker 4705 # number of overall (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_accesses::cpu0.itb.walker 2288 # number of overall (read+write) accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.overall_accesses::cpu0.inst 844530 # number of overall (read+write) accesses
system.l2c.overall_accesses::cpu0.data 392607 # number of overall (read+write) accesses
system.l2c.overall_accesses::cpu1.dtb.walker 5003 # number of overall (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_accesses::cpu1.itb.walker 2453 # number of overall (read+write) accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.overall_accesses::cpu1.inst 855184 # number of overall (read+write) accesses
system.l2c.overall_accesses::cpu1.data 427323 # number of overall (read+write) accesses
system.l2c.overall_accesses::total 2534093 # number of overall (read+write) accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_miss_rate::cpu0.dtb.walker 0.001063 # miss rate for ReadReq accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.ReadReq_miss_rate::cpu0.itb.walker 0.000437 # miss rate for ReadReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.ReadReq_miss_rate::cpu1.dtb.walker 0.000400 # miss rate for ReadReq accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadReq_miss_rate::total 0.000554 # miss rate for ReadReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.UpgradeReq_miss_rate::cpu0.data 0.989699 # miss rate for UpgradeReq accesses
system.l2c.UpgradeReq_miss_rate::cpu1.data 0.989960 # miss rate for UpgradeReq accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.UpgradeReq_miss_rate::total 0.989840 # miss rate for UpgradeReq accesses
system.l2c.SCUpgradeReq_miss_rate::cpu1.data 1 # miss rate for SCUpgradeReq accesses
system.l2c.SCUpgradeReq_miss_rate::total 1 # miss rate for SCUpgradeReq accesses
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.l2c.ReadExReq_miss_rate::cpu0.data 0.468673 # miss rate for ReadExReq accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.ReadExReq_miss_rate::cpu1.data 0.515947 # miss rate for ReadExReq accesses
system.l2c.ReadExReq_miss_rate::total 0.494363 # miss rate for ReadExReq accesses
system.l2c.ReadCleanReq_miss_rate::cpu0.inst 0.012763 # miss rate for ReadCleanReq accesses
system.l2c.ReadCleanReq_miss_rate::cpu1.inst 0.008792 # miss rate for ReadCleanReq accesses
system.l2c.ReadCleanReq_miss_rate::total 0.010765 # miss rate for ReadCleanReq accesses
system.l2c.ReadSharedReq_miss_rate::cpu0.data 0.038176 # miss rate for ReadSharedReq accesses
system.l2c.ReadSharedReq_miss_rate::cpu1.data 0.021840 # miss rate for ReadSharedReq accesses
system.l2c.ReadSharedReq_miss_rate::total 0.029871 # miss rate for ReadSharedReq accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_miss_rate::cpu0.dtb.walker 0.001063 # miss rate for demand accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.demand_miss_rate::cpu0.itb.walker 0.000437 # miss rate for demand accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_miss_rate::cpu0.inst 0.012763 # miss rate for demand accesses
system.l2c.demand_miss_rate::cpu0.data 0.187827 # miss rate for demand accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.demand_miss_rate::cpu1.dtb.walker 0.000400 # miss rate for demand accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.demand_miss_rate::cpu1.inst 0.008792 # miss rate for demand accesses
system.l2c.demand_miss_rate::cpu1.data 0.209670 # miss rate for demand accesses
system.l2c.demand_miss_rate::total 0.071680 # miss rate for demand accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_miss_rate::cpu0.dtb.walker 0.001063 # miss rate for overall accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.overall_miss_rate::cpu0.itb.walker 0.000437 # miss rate for overall accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_miss_rate::cpu0.inst 0.012763 # miss rate for overall accesses
system.l2c.overall_miss_rate::cpu0.data 0.187827 # miss rate for overall accesses
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.l2c.overall_miss_rate::cpu1.dtb.walker 0.000400 # miss rate for overall accesses
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.overall_miss_rate::cpu1.inst 0.008792 # miss rate for overall accesses
system.l2c.overall_miss_rate::cpu1.data 0.209670 # miss rate for overall accesses
system.l2c.overall_miss_rate::total 0.071680 # miss rate for overall accesses
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
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.blocked::no_mshrs 0 # number of cycles access was blocked
system.l2c.blocked::no_targets 0 # number of cycles access was blocked
system.l2c.avg_blocked_cycles::no_mshrs nan # average number of cycles each access was blocked
system.l2c.avg_blocked_cycles::no_targets nan # average number of cycles each access was blocked
system.l2c.fast_writes 0 # number of fast writes performed
system.l2c.cache_copies 0 # number of cache copies performed
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.l2c.writebacks::writebacks 101943 # number of writebacks
system.l2c.writebacks::total 101943 # number of writebacks
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.l2c.no_allocate_misses 0 # Number of misses that were no-allocate
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.trans_dist::ReadReq 40087 # Transaction distribution
system.membus.trans_dist::ReadResp 74196 # Transaction distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.membus.trans_dist::WriteReq 27546 # Transaction distribution
system.membus.trans_dist::WriteResp 27546 # Transaction distribution
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.trans_dist::Writeback 138133 # Transaction distribution
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.membus.trans_dist::CleanEvict 7977 # Transaction distribution
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.trans_dist::UpgradeReq 4507 # Transaction distribution
system.membus.trans_dist::SCUpgradeReq 2 # Transaction distribution
system.membus.trans_dist::UpgradeResp 4509 # Transaction distribution
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.trans_dist::ReadExReq 145997 # Transaction distribution
system.membus.trans_dist::ReadExResp 145997 # Transaction distribution
system.membus.trans_dist::ReadSharedReq 34109 # Transaction distribution
system.membus.trans_dist::InvalidateReq 36224 # Transaction distribution
system.membus.trans_dist::InvalidateResp 36224 # Transaction distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.membus.pkt_count_system.l2c.mem_side::system.bridge.slave 105404 # Packet count per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.pkt_count_system.l2c.mem_side::system.realview.nvmem.port 10 # Packet count per connected master and slave (bytes)
system.membus.pkt_count_system.l2c.mem_side::system.realview.gic.pio 1946 # Packet count per connected master and slave (bytes)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.pkt_count_system.l2c.mem_side::system.physmem.port 506563 # Packet count per connected master and slave (bytes)
system.membus.pkt_count_system.l2c.mem_side::total 613923 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.membus.pkt_count_system.iocache.mem_side::system.physmem.port 109131 # Packet count per connected master and slave (bytes)
system.membus.pkt_count_system.iocache.mem_side::total 109131 # Packet count per connected master and slave (bytes)
system.membus.pkt_count::total 723054 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.membus.pkt_size_system.l2c.mem_side::system.bridge.slave 159061 # Cumulative packet size per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.pkt_size_system.l2c.mem_side::system.realview.nvmem.port 20 # Cumulative packet size per connected master and slave (bytes)
system.membus.pkt_size_system.l2c.mem_side::system.realview.gic.pio 3892 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.pkt_size_system.l2c.mem_side::system.physmem.port 18091644 # Cumulative packet size per connected master and slave (bytes)
system.membus.pkt_size_system.l2c.mem_side::total 18254617 # Cumulative packet size per connected master and slave (bytes)
system.membus.pkt_size_system.iocache.mem_side::system.physmem.port 2331520 # Cumulative packet size per connected master and slave (bytes)
system.membus.pkt_size_system.iocache.mem_side::total 2331520 # Cumulative packet size per connected master and slave (bytes)
system.membus.pkt_size::total 20586137 # Cumulative packet size per connected master and slave (bytes)
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.snoops 0 # Total snoops (count)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.snoop_fanout::samples 434809 # Request fanout histogram
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.snoop_fanout::mean 1 # Request fanout histogram
system.membus.snoop_fanout::stdev 0 # Request fanout histogram
system.membus.snoop_fanout::underflows 0 0.00% 0.00% # Request fanout histogram
system.membus.snoop_fanout::0 0 0.00% 0.00% # Request fanout histogram
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.snoop_fanout::1 434809 100.00% 100.00% # Request fanout histogram
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.membus.snoop_fanout::2 0 0.00% 100.00% # Request fanout histogram
system.membus.snoop_fanout::overflows 0 0.00% 100.00% # Request fanout histogram
system.membus.snoop_fanout::min_value 1 # Request fanout histogram
system.membus.snoop_fanout::max_value 1 # Request fanout histogram
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.membus.snoop_fanout::total 434809 # Request fanout histogram
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.realview.ethernet.descDMAReads 0 # Number of descriptors the device read w/ DMA
system.realview.ethernet.descDMAWrites 0 # Number of descriptors the device wrote w/ DMA
system.realview.ethernet.descDmaReadBytes 0 # number of descriptor bytes read w/ DMA
system.realview.ethernet.descDmaWriteBytes 0 # number of descriptor bytes write w/ DMA
system.realview.ethernet.postedSwi 0 # number of software interrupts posted to CPU
system.realview.ethernet.coalescedSwi nan # average number of Swi's coalesced into each post
system.realview.ethernet.totalSwi 0 # total number of Swi written to ISR
system.realview.ethernet.postedRxIdle 0 # number of rxIdle interrupts posted to CPU
system.realview.ethernet.coalescedRxIdle nan # average number of RxIdle's coalesced into each post
system.realview.ethernet.totalRxIdle 0 # total number of RxIdle written to ISR
system.realview.ethernet.postedRxOk 0 # number of RxOk interrupts posted to CPU
system.realview.ethernet.coalescedRxOk nan # average number of RxOk's coalesced into each post
system.realview.ethernet.totalRxOk 0 # total number of RxOk written to ISR
system.realview.ethernet.postedRxDesc 0 # number of RxDesc interrupts posted to CPU
system.realview.ethernet.coalescedRxDesc nan # average number of RxDesc's coalesced into each post
system.realview.ethernet.totalRxDesc 0 # total number of RxDesc written to ISR
system.realview.ethernet.postedTxOk 0 # number of TxOk interrupts posted to CPU
system.realview.ethernet.coalescedTxOk nan # average number of TxOk's coalesced into each post
system.realview.ethernet.totalTxOk 0 # total number of TxOk written to ISR
system.realview.ethernet.postedTxIdle 0 # number of TxIdle interrupts posted to CPU
system.realview.ethernet.coalescedTxIdle nan # average number of TxIdle's coalesced into each post
system.realview.ethernet.totalTxIdle 0 # total number of TxIdle written to ISR
system.realview.ethernet.postedTxDesc 0 # number of TxDesc interrupts posted to CPU
system.realview.ethernet.coalescedTxDesc nan # average number of TxDesc's coalesced into each post
system.realview.ethernet.totalTxDesc 0 # total number of TxDesc written to ISR
system.realview.ethernet.postedRxOrn 0 # number of RxOrn posted to CPU
system.realview.ethernet.coalescedRxOrn nan # average number of RxOrn's coalesced into each post
system.realview.ethernet.totalRxOrn 0 # total number of RxOrn written to ISR
system.realview.ethernet.coalescedTotal nan # average number of interrupts coalesced into each post
system.realview.ethernet.postedInterrupts 0 # number of posts to CPU
system.realview.ethernet.droppedPackets 0 # number of packets dropped
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.realview.realview_io.osc_pxl.clock 42105 # Clock period in ticks
stats: Update ARM stats to include programmable oscillators
2015-08-07 16:39:17 +02:00
system.realview.realview_io.osc_clcd.clock 42105 # Clock period in ticks
system.realview.realview_io.osc_cpu.clock 16667 # Clock period in ticks
system.realview.realview_io.osc_ddr.clock 25000 # Clock period in ticks
system.realview.realview_io.osc_hsbm.clock 25000 # Clock period in ticks
system.realview.realview_io.osc_mcc.clock 20000 # Clock period in ticks
system.realview.realview_io.osc_peripheral.clock 41667 # Clock period in ticks
system.realview.realview_io.osc_smb.clock 20000 # Clock period in ticks
system.realview.realview_io.osc_sys.clock 16667 # Clock period in ticks
system.realview.realview_io.osc_system_bus.clock 41667 # Clock period in ticks
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.snoop_filter.tot_requests 5060706 # Total number of requests made to the snoop filter.
system.toL2Bus.snoop_filter.hit_single_requests 2541063 # Number of requests hitting in the snoop filter with a single holder of the requested data.
system.toL2Bus.snoop_filter.hit_multi_requests 39274 # Number of requests hitting in the snoop filter with multiple (>1) holders of the requested data.
system.toL2Bus.snoop_filter.tot_snoops 420 # Total number of snoops made to the snoop filter.
system.toL2Bus.snoop_filter.hit_single_snoops 420 # Number of snoops hitting in the snoop filter with a single holder of the requested data.
system.toL2Bus.snoop_filter.hit_multi_snoops 0 # Number of snoops hitting in the snoop filter with multiple (>1) holders of the requested data.
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.toL2Bus.trans_dist::ReadReq 71244 # Transaction distribution
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.toL2Bus.trans_dist::ReadResp 2291984 # Transaction distribution
system.toL2Bus.trans_dist::WriteReq 27546 # Transaction distribution
system.toL2Bus.trans_dist::WriteResp 27546 # Transaction distribution
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.toL2Bus.trans_dist::Writeback 682264 # Transaction distribution
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.trans_dist::CleanEvict 1797078 # Transaction distribution
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.toL2Bus.trans_dist::UpgradeReq 2756 # Transaction distribution
system.toL2Bus.trans_dist::SCUpgradeReq 2 # Transaction distribution
system.toL2Bus.trans_dist::UpgradeResp 2758 # Transaction distribution
stats: Bump stats for fixes, mostly TLB and WriteInvalidate
2014-12-02 12:08:25 +01:00
system.toL2Bus.trans_dist::ReadExReq 298922 # Transaction distribution
system.toL2Bus.trans_dist::ReadExResp 298922 # Transaction distribution
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.toL2Bus.trans_dist::ReadCleanReq 1699732 # Transaction distribution
system.toL2Bus.trans_dist::ReadSharedReq 521008 # Transaction distribution
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.pkt_count_system.cpu0.icache.mem_side::system.l2c.cpu_side 5084714 # Packet count per connected master and slave (bytes)
system.toL2Bus.pkt_count_system.cpu0.dcache.mem_side::system.l2c.cpu_side 2574734 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.toL2Bus.pkt_count_system.cpu0.itb.walker.dma::system.l2c.cpu_side 20804 # Packet count per connected master and slave (bytes)
system.toL2Bus.pkt_count_system.cpu0.dtb.walker.dma::system.l2c.cpu_side 41510 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.pkt_count::total 7721762 # Packet count per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.toL2Bus.pkt_size_system.cpu0.icache.mem_side::system.l2c.cpu_side 108818936 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.toL2Bus.pkt_size_system.cpu0.dcache.mem_side::system.l2c.cpu_side 96323169 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats to reflect cache and interconnect changes This is a bulk update of stats to match the changes to cache timing, interconnect timing, and a few minor changes to the o3 CPU.
2015-03-02 11:04:20 +01:00
system.toL2Bus.pkt_size_system.cpu0.itb.walker.dma::system.l2c.cpu_side 41608 # Cumulative packet size per connected master and slave (bytes)
system.toL2Bus.pkt_size_system.cpu0.dtb.walker.dma::system.l2c.cpu_side 83020 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats for cache, crossbar and DRAM changes This update includes the changes to whole-line writes, the refinement of Read to ReadClean and ReadShared, the introduction of CleanEvict for snoop-filter tracking, and updates to the DRAM command scheduler for bank-group-aware scheduling. Needless to say, almost every regression is affected.
2015-07-03 16:15:03 +02:00
system.toL2Bus.pkt_size::total 205266733 # Cumulative packet size per connected master and slave (bytes)
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.snoops 182968 # Total snoops (count)
system.toL2Bus.snoop_fanout::samples 5322627 # Request fanout histogram
system.toL2Bus.snoop_fanout::mean 0.018535 # Request fanout histogram
system.toL2Bus.snoop_fanout::stdev 0.134877 # Request fanout histogram
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.toL2Bus.snoop_fanout::underflows 0 0.00% 0.00% # Request fanout histogram
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.snoop_fanout::0 5223970 98.15% 98.15% # Request fanout histogram
system.toL2Bus.snoop_fanout::1 98657 1.85% 100.00% # Request fanout histogram
system.toL2Bus.snoop_fanout::2 0 0.00% 100.00% # Request fanout histogram
stats: Bump regressions to match latest changes Updates after timezone hick-up and sorting of dictionary items in the SimObject.
2014-11-12 15:05:25 +01:00
system.toL2Bus.snoop_fanout::overflows 0 0.00% 100.00% # Request fanout histogram
stats: Update stats to reflect snoop-filter changes
2015-09-25 13:27:03 +02:00
system.toL2Bus.snoop_fanout::min_value 0 # Request fanout histogram
system.toL2Bus.snoop_fanout::max_value 1 # Request fanout histogram
system.toL2Bus.snoop_fanout::total 5322627 # Request fanout histogram
tests: Add CPU switching tests This changeset adds a set of tests that stress the CPU switching code. It adds the following test configurations: * tsunami-switcheroo-full -- Alpha system (atomic, timing, O3) * realview-switcheroo-atomic -- ARM system (atomic<->atomic) * realview-switcheroo-timing -- ARM system (timing<->timing) * realview-switcheroo-o3 -- ARM system (O3<->O3) * realview-switcheroo-full -- ARM system (atomic, timing, O3) Reference data is provided for the 10.linux-boot test case. All of the tests trigger a CPU switch once per millisecond during the boot process. The in-order CPU model was not included in any of the tests as it does not support CPU handover.
2013-01-07 19:05:52 +01:00
---------- End Simulation Statistics ----------
Reference in a new issue Copy permalink