Hello All, I am using gem5 for simulation of *alpha architecture* and able to gets stats for sample example. Also able to convert gem5 stats into xml file using m5-mcpat-parse-se.py to the power.xml file which is used as input to McPat. However, power.xml is not generated correctly, not all stats are added in power.xml and also when I tried to provided it as input to McPat I getting following error. *"some value(s) of number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not correct!"*
I have tried to look into power.xml file and update it manually but issue is not resolved as suggested in some previous email chains and also followed the steps provided on the link : https://www.cl.cam.ac.uk/~acr31/sicsa/. I have attached the file which are generated by gem5, output.xml file and using the parser from github link : https://github.com/danielpalomino/mcpat-hotspot-parser. Please help how to to resolve this issue. If anybody have working script please share with me. Thanks, Bala
---------- Begin Simulation Statistics ---------- sim_seconds 0.002328 # Number of seconds simulated sim_ticks 2328346000 # Number of ticks simulated final_tick 2328346000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks host_inst_rate 1243770 # Simulator instruction rate (inst/s) host_op_rate 1243763 # Simulator op (including micro ops) rate (op/s) host_tick_rate 621881635 # Simulator tick rate (ticks/s) host_mem_usage 568276 # Number of bytes of host memory used host_seconds 3.74 # Real time elapsed on the host sim_insts 4656664 # Number of instructions simulated sim_ops 4656664 # Number of ops (including micro ops) simulated system.voltage_domain.voltage 1 # Voltage in Volts system.clk_domain.clock 1000 # Clock period in ticks system.mem_ctrls.bytes_read::cpu.inst 18626708 # Number of bytes read from this memory system.mem_ctrls.bytes_read::cpu.data 7488057 # Number of bytes read from this memory system.mem_ctrls.bytes_read::total 26114765 # Number of bytes read from this memory system.mem_ctrls.bytes_inst_read::cpu.inst 18626708 # Number of instructions bytes read from this memory system.mem_ctrls.bytes_inst_read::total 18626708 # Number of instructions bytes read from this memory system.mem_ctrls.bytes_written::cpu.data 2598932 # Number of bytes written to this memory system.mem_ctrls.bytes_written::total 2598932 # Number of bytes written to this memory system.mem_ctrls.num_reads::cpu.inst 4656677 # Number of read requests responded to by this memory system.mem_ctrls.num_reads::cpu.data 1613762 # Number of read requests responded to by this memory system.mem_ctrls.num_reads::total 6270439 # Number of read requests responded to by this memory system.mem_ctrls.num_writes::cpu.data 648938 # Number of write requests responded to by this memory system.mem_ctrls.num_writes::total 648938 # Number of write requests responded to by this memory system.mem_ctrls.bw_read::cpu.inst 7999974231 # Total read bandwidth from this memory (bytes/s) system.mem_ctrls.bw_read::cpu.data 3216041344 # Total read bandwidth from this memory (bytes/s) system.mem_ctrls.bw_read::total 11216015575 # Total read bandwidth from this memory (bytes/s) system.mem_ctrls.bw_inst_read::cpu.inst 7999974231 # Instruction read bandwidth from this memory (bytes/s) system.mem_ctrls.bw_inst_read::total 7999974231 # Instruction read bandwidth from this memory (bytes/s) system.mem_ctrls.bw_write::cpu.data 1116213827 # Write bandwidth from this memory (bytes/s) system.mem_ctrls.bw_write::total 1116213827 # Write bandwidth from this memory (bytes/s) system.mem_ctrls.bw_total::cpu.inst 7999974231 # Total bandwidth to/from this memory (bytes/s) system.mem_ctrls.bw_total::cpu.data 4332255172 # Total bandwidth to/from this memory (bytes/s) system.mem_ctrls.bw_total::total 12332229402 # Total bandwidth to/from this memory (bytes/s) system.mem_ctrls.readReqs 0 # Number of read requests accepted system.mem_ctrls.writeReqs 0 # Number of write requests accepted system.mem_ctrls.readBursts 0 # Number of DRAM read bursts, including those serviced by the write queue system.mem_ctrls.writeBursts 0 # Number of DRAM write bursts, including those merged in the write queue system.mem_ctrls.bytesReadDRAM 0 # Total number of bytes read from DRAM system.mem_ctrls.bytesReadWrQ 0 # Total number of bytes read from write queue system.mem_ctrls.bytesWritten 0 # Total number of bytes written to DRAM system.mem_ctrls.bytesReadSys 0 # Total read bytes from the system interface side system.mem_ctrls.bytesWrittenSys 0 # Total written bytes from the system interface side system.mem_ctrls.servicedByWrQ 0 # Number of DRAM read bursts serviced by the write queue system.mem_ctrls.mergedWrBursts 0 # Number of DRAM write bursts merged with an existing one system.mem_ctrls.neitherReadNorWriteReqs 0 # Number of requests that are neither read nor write system.mem_ctrls.perBankRdBursts::0 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::1 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::2 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::3 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::4 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::5 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::6 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::7 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::8 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::9 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::10 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::11 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::12 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::13 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::14 0 # Per bank write bursts system.mem_ctrls.perBankRdBursts::15 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::0 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::1 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::2 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::3 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::4 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::5 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::6 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::7 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::8 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::9 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::10 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::11 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::12 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::13 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::14 0 # Per bank write bursts system.mem_ctrls.perBankWrBursts::15 0 # Per bank write bursts system.mem_ctrls.numRdRetry 0 # Number of times read queue was full causing retry system.mem_ctrls.numWrRetry 0 # Number of times write queue was full causing retry system.mem_ctrls.totGap 0 # Total gap between requests system.mem_ctrls.readPktSize::0 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::1 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::2 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::3 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::4 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::5 0 # Read request sizes (log2) system.mem_ctrls.readPktSize::6 0 # Read request sizes (log2) system.mem_ctrls.writePktSize::0 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::1 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::2 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::3 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::4 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::5 0 # Write request sizes (log2) system.mem_ctrls.writePktSize::6 0 # Write request sizes (log2) system.mem_ctrls.rdQLenPdf::0 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::1 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::2 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::3 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::4 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::5 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::6 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::7 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::8 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::9 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::10 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::11 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::12 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::13 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::14 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::15 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::16 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::17 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::18 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::19 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::20 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::21 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::22 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::23 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::24 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::25 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::26 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::27 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::28 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::29 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::30 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::31 0 # What read queue length does an incoming req see system.mem_ctrls.wrQLenPdf::0 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::1 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::2 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::3 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::4 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::5 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::6 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::7 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::8 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::9 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::10 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::11 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::12 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::13 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::14 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::15 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::16 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::17 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::18 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::19 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::20 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::21 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::22 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::23 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::24 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::25 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::26 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::27 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::28 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::29 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::30 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::31 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::32 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::33 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::34 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::35 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::36 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::37 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::38 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::39 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::40 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::41 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::42 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::43 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::44 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::45 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::46 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::47 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::48 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::49 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::50 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::51 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::52 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::53 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::54 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::55 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::56 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::57 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::58 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::59 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::60 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::61 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::62 0 # What write queue length does an incoming req see system.mem_ctrls.wrQLenPdf::63 0 # What write queue length does an incoming req see system.mem_ctrls.totQLat 0 # Total ticks spent queuing system.mem_ctrls.totMemAccLat 0 # Total ticks spent from burst creation until serviced by the DRAM system.mem_ctrls.totBusLat 0 # Total ticks spent in databus transfers system.mem_ctrls.avgQLat 0 # Average queueing delay per DRAM burst system.mem_ctrls.avgBusLat 0 # Average bus latency per DRAM burst system.mem_ctrls.avgMemAccLat 0 # Average memory access latency per DRAM burst system.mem_ctrls.avgRdBW 0.00 # Average DRAM read bandwidth in MiByte/s system.mem_ctrls.avgWrBW 0.00 # Average achieved write bandwidth in MiByte/s system.mem_ctrls.avgRdBWSys 0.00 # Average system read bandwidth in MiByte/s system.mem_ctrls.avgWrBWSys 0.00 # Average system write bandwidth in MiByte/s system.mem_ctrls.peakBW 12800.00 # Theoretical peak bandwidth in MiByte/s system.mem_ctrls.busUtil 0.00 # Data bus utilization in percentage system.mem_ctrls.busUtilRead 0.00 # Data bus utilization in percentage for reads system.mem_ctrls.busUtilWrite 0.00 # Data bus utilization in percentage for writes system.mem_ctrls.avgRdQLen 0.00 # Average read queue length when enqueuing system.mem_ctrls.avgWrQLen 0.00 # Average write queue length when enqueuing system.mem_ctrls.readRowHits 0 # Number of row buffer hits during reads system.mem_ctrls.writeRowHits 0 # Number of row buffer hits during writes system.mem_ctrls.readRowHitRate 0 # Row buffer hit rate for reads system.mem_ctrls.writeRowHitRate 0 # Row buffer hit rate for writes system.mem_ctrls.avgGap 0 # Average gap between requests system.mem_ctrls.pageHitRate 0 # Row buffer hit rate, read and write combined system.mem_ctrls_0.actEnergy 0 # Energy for activate commands per rank (pJ) system.mem_ctrls_0.preEnergy 0 # Energy for precharge commands per rank (pJ) system.mem_ctrls_0.readEnergy 0 # Energy for read commands per rank (pJ) system.mem_ctrls_0.writeEnergy 0 # Energy for write commands per rank (pJ) system.mem_ctrls_0.refreshEnergy 0 # Energy for refresh commands per rank (pJ) system.mem_ctrls_0.actBackEnergy 0 # Energy for active background per rank (pJ) system.mem_ctrls_0.preBackEnergy 0 # Energy for precharge background per rank (pJ) system.mem_ctrls_0.totalEnergy 0 # Total energy per rank (pJ) system.mem_ctrls_0.averagePower 0 # Core power per rank (mW) system.mem_ctrls_0.memoryStateTime::IDLE 0 # Time in different power states system.mem_ctrls_0.memoryStateTime::REF 0 # Time in different power states system.mem_ctrls_0.memoryStateTime::PRE_PDN 0 # Time in different power states system.mem_ctrls_0.memoryStateTime::ACT 0 # Time in different power states system.mem_ctrls_0.memoryStateTime::ACT_PDN 0 # Time in different power states system.mem_ctrls_1.actEnergy 0 # Energy for activate commands per rank (pJ) system.mem_ctrls_1.preEnergy 0 # Energy for precharge commands per rank (pJ) system.mem_ctrls_1.readEnergy 0 # Energy for read commands per rank (pJ) system.mem_ctrls_1.writeEnergy 0 # Energy for write commands per rank (pJ) system.mem_ctrls_1.refreshEnergy 0 # Energy for refresh commands per rank (pJ) system.mem_ctrls_1.actBackEnergy 0 # Energy for active background per rank (pJ) system.mem_ctrls_1.preBackEnergy 0 # Energy for precharge background per rank (pJ) system.mem_ctrls_1.totalEnergy 0 # Total energy per rank (pJ) system.mem_ctrls_1.averagePower 0 # Core power per rank (mW) system.mem_ctrls_1.memoryStateTime::IDLE 0 # Time in different power states system.mem_ctrls_1.memoryStateTime::REF 0 # Time in different power states system.mem_ctrls_1.memoryStateTime::PRE_PDN 0 # Time in different power states system.mem_ctrls_1.memoryStateTime::ACT 0 # Time in different power states system.mem_ctrls_1.memoryStateTime::ACT_PDN 0 # Time in different power states system.cpu_voltage_domain.voltage 1 # Voltage in Volts system.cpu_clk_domain.clock 500 # Clock period in ticks system.cpu.dtb.fetch_hits 0 # ITB hits system.cpu.dtb.fetch_misses 0 # ITB misses system.cpu.dtb.fetch_acv 0 # ITB acv system.cpu.dtb.fetch_accesses 0 # ITB accesses system.cpu.dtb.read_hits 1613762 # DTB read hits system.cpu.dtb.read_misses 7 # DTB read misses system.cpu.dtb.read_acv 0 # DTB read access violations system.cpu.dtb.read_accesses 1613769 # DTB read accesses system.cpu.dtb.write_hits 648938 # DTB write hits system.cpu.dtb.write_misses 6 # DTB write misses system.cpu.dtb.write_acv 0 # DTB write access violations system.cpu.dtb.write_accesses 648944 # DTB write accesses system.cpu.dtb.data_hits 2262700 # DTB hits system.cpu.dtb.data_misses 13 # DTB misses system.cpu.dtb.data_acv 0 # DTB access violations system.cpu.dtb.data_accesses 2262713 # DTB accesses system.cpu.itb.fetch_hits 4656677 # ITB hits system.cpu.itb.fetch_misses 16 # ITB misses system.cpu.itb.fetch_acv 0 # ITB acv system.cpu.itb.fetch_accesses 4656693 # ITB accesses system.cpu.itb.read_hits 0 # DTB read hits system.cpu.itb.read_misses 0 # DTB read misses system.cpu.itb.read_acv 0 # DTB read access violations system.cpu.itb.read_accesses 0 # DTB read accesses system.cpu.itb.write_hits 0 # DTB write hits system.cpu.itb.write_misses 0 # DTB write misses system.cpu.itb.write_acv 0 # DTB write access violations system.cpu.itb.write_accesses 0 # DTB write accesses system.cpu.itb.data_hits 0 # DTB hits system.cpu.itb.data_misses 0 # DTB misses system.cpu.itb.data_acv 0 # DTB access violations system.cpu.itb.data_accesses 0 # DTB accesses system.cpu.workload.num_syscalls 9 # Number of system calls system.cpu.numCycles 4656693 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed system.cpu.committedInsts 4656664 # Number of instructions committed system.cpu.committedOps 4656664 # Number of ops (including micro ops) committed system.cpu.num_int_alu_accesses 4526712 # Number of integer alu accesses system.cpu.num_fp_alu_accesses 385657 # Number of float alu accesses system.cpu.num_func_calls 183 # number of times a function call or return occured system.cpu.num_conditional_control_insts 67923 # number of instructions that are conditional controls system.cpu.num_int_insts 4526712 # number of integer instructions system.cpu.num_fp_insts 385657 # number of float instructions system.cpu.num_int_register_reads 6398856 # number of times the integer registers were read system.cpu.num_int_register_writes 3617758 # number of times the integer registers were written system.cpu.num_fp_register_reads 321640 # number of times the floating registers were read system.cpu.num_fp_register_writes 320032 # number of times the floating registers were written system.cpu.num_mem_refs 2262713 # number of memory refs system.cpu.num_load_insts 1613769 # Number of load instructions system.cpu.num_store_insts 648944 # Number of store instructions system.cpu.num_idle_cycles 0.002000 # Number of idle cycles system.cpu.num_busy_cycles 4656692.998000 # Number of busy cycles system.cpu.not_idle_fraction 1.000000 # Percentage of non-idle cycles system.cpu.idle_fraction 0.000000 # Percentage of idle cycles system.cpu.Branches 69807 # Number of branches fetched system.cpu.op_class::No_OpClass 216 0.00% 0.00% # Class of executed instruction system.cpu.op_class::IntAlu 2265692 48.65% 48.66% # Class of executed instruction system.cpu.op_class::IntMult 4 0.00% 48.66% # Class of executed instruction system.cpu.op_class::IntDiv 0 0.00% 48.66% # Class of executed instruction system.cpu.op_class::FloatAdd 64017 1.37% 50.03% # Class of executed instruction system.cpu.op_class::FloatCmp 0 0.00% 50.03% # Class of executed instruction system.cpu.op_class::FloatCvt 11 0.00% 50.03% # Class of executed instruction system.cpu.op_class::FloatMult 64000 1.37% 51.41% # Class of executed instruction system.cpu.op_class::FloatDiv 3 0.00% 51.41% # Class of executed instruction system.cpu.op_class::FloatSqrt 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdAdd 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdAddAcc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdAlu 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdCmp 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdCvt 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdMisc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdMult 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdMultAcc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdShift 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdShiftAcc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdSqrt 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatAdd 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatAlu 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatCmp 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatCvt 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatDiv 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatMisc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatMult 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatMultAcc 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::SimdFloatSqrt 0 0.00% 51.41% # Class of executed instruction system.cpu.op_class::MemRead 1613789 34.66% 86.06% # Class of executed instruction system.cpu.op_class::MemWrite 648945 13.94% 100.00% # Class of executed instruction system.cpu.op_class::IprAccess 0 0.00% 100.00% # Class of executed instruction system.cpu.op_class::InstPrefetch 0 0.00% 100.00% # Class of executed instruction system.cpu.op_class::total 4656677 # Class of executed instruction system.membus.trans_dist::ReadReq 6270419 # Transaction distribution system.membus.trans_dist::ReadResp 6270439 # Transaction distribution system.membus.trans_dist::WriteReq 648918 # Transaction distribution system.membus.trans_dist::WriteResp 648918 # Transaction distribution system.membus.trans_dist::LoadLockedReq 20 # Transaction distribution system.membus.trans_dist::StoreCondReq 20 # Transaction distribution system.membus.trans_dist::StoreCondResp 20 # Transaction distribution system.membus.pkt_count_system.cpu.icache_port::system.mem_ctrls.port 9313354 # Packet count per connected master and slave (bytes) system.membus.pkt_count_system.cpu.dcache_port::system.mem_ctrls.port 4525400 # Packet count per connected master and slave (bytes) system.membus.pkt_count::total 13838754 # Packet count per connected master and slave (bytes) system.membus.pkt_size_system.cpu.icache_port::system.mem_ctrls.port 18626708 # Cumulative packet size per connected master and slave (bytes) system.membus.pkt_size_system.cpu.dcache_port::system.mem_ctrls.port 10086989 # Cumulative packet size per connected master and slave (bytes) system.membus.pkt_size::total 28713697 # Cumulative packet size per connected master and slave (bytes) system.membus.snoops 0 # Total snoops (count) system.membus.snoop_fanout::samples 6919377 # Request fanout histogram system.membus.snoop_fanout::mean 0.672991 # Request fanout histogram system.membus.snoop_fanout::stdev 0.469121 # Request fanout histogram system.membus.snoop_fanout::underflows 0 0.00% 0.00% # Request fanout histogram system.membus.snoop_fanout::0 2262700 32.70% 32.70% # Request fanout histogram system.membus.snoop_fanout::1 4656677 67.30% 100.00% # Request fanout histogram system.membus.snoop_fanout::overflows 0 0.00% 100.00% # Request fanout histogram system.membus.snoop_fanout::min_value 0 # Request fanout histogram system.membus.snoop_fanout::max_value 1 # Request fanout histogram system.membus.snoop_fanout::total 6919377 # Request fanout histogram ---------- End Simulation Statistics ----------
config.ini
Description: Binary data
<?xml version="1.0" ?>
<component id="root" name="root">
<component id="system" name="system">
<!--McPAT will skip the components if number is set to 0 -->
<param name="number_of_cores" value="2"/>
<param name="number_of_L1Directories" value="0"/>
<param name="number_of_L2Directories" value="1"/>
<param name="number_of_L2s" value="1"/> <!-- This number means how many L2 clusters in each cluster there can be multiple banks/ports -->
<param name="Private_L2" value="0"/><!--1 Private, 0 shared/coherent -->
<param name="number_of_L3s" value="0"/> <!-- This number means how many L3 clusters -->
<param name="number_of_NoCs" value="1"/>
<param name="homogeneous_cores" value="1"/><!--1 means homo -->
<param name="homogeneous_L2s" value="1"/>
<param name="homogeneous_L1Directorys" value="1"/>
<param name="homogeneous_L2Directorys" value="1"/>
<param name="homogeneous_L3s" value="1"/>
<param name="homogeneous_ccs" value="1"/><!--cache coherece hardware -->
<param name="homogeneous_NoCs" value="1"/>
<param name="core_tech_node" value="90"/><!-- nm -->
<param name="target_core_clockrate" value=""/><!--MHz -->
<param name="temperature" value="380"/> <!-- Kelvin -->
<param name="number_cache_levels" value="2"/>
<param name="interconnect_projection_type" value="0"/><!--0: agressive wire technology; 1: conservative wire technology -->
<param name="device_type" value="0"/><!--0: HP(High Performance Type); 1: LSTP(Low standby power) 2: LOP (Low Operating Power) -->
<param name="longer_channel_device" value="0"/><!-- 0 no use; 1 use when approperiate -->
<param name="machine_bits" value="64"/>
<param name="virtual_address_width" value="64"/>
<param name="physical_address_width" value="52"/>
<param name="virtual_memory_page_size" value="4096"/>
<!-- address width determins the tag_width in Cache, LSQ and buffers in cache controller
default value is machine_bits, if not set -->
<stat name="runtime_sec" value=""/>
<stat name="total_cycles" value="4656693"/>
<stat name="idle_cycles" value="0"/>
<stat name="busy_cycles" value="4656693"/>
<!--This page size(B) is complete different from the page size in Main memo secction. this page size is the size of
virtual memory from OS/Archi perspective; the page size in Main memo secction is the actuall physical line in a DRAM bank -->
<!-- *********************** cores ******************* -->
<component id="system.core0" name="core0">
<!-- Core property -->
<param name="clock_rate" value=""/>
<!-- for cores with unknow timing, set to 0 to force off the opt flag -->
<param name="opt_local" value="1"/>
<param name="instruction_length" value="32"/>
<param name="opcode_width" value="7"/>
<param name="x86" value="0"/>
<param name="micro_opcode_width" value="8"/>
<param name="machine_type" value="0"/>
<!-- inorder/OoO; 1 inorder; 0 OOO-->
<param name="number_hardware_threads" value="1"/>
<!-- number_instruction_fetch_ports(icache ports) is always 1 in single-thread processor,
it only may be more than one in SMT processors. BTB ports always equals to fetch ports since
branch information in consective branch instructions in the same fetch group can be read out from BTB once.-->
<param name="fetch_width" value=""/>
<!-- fetch_width determins the size of cachelines of L1 cache block -->
<param name="number_instruction_fetch_ports" value="1"/>
<param name="decode_width" value=""/>
<!-- decode_width determins the number of ports of the
renaming table (both RAM and CAM) scheme -->
<param name="issue_width" value=""/>
<param name="peak_issue_width" value=""/>
<!-- issue_width determins the number of ports of Issue window and other logic
as in the complexity effective proccessors paper; issue_width==dispatch_width -->
<param name="commit_width" value=""/>
<!-- commit_width determins the number of ports of register files -->
<param name="fp_issue_width" value="2"/>
<param name="prediction_width" value="1"/>
<!-- number of branch instructions can be predicted simultannouesl-->
<!-- Current version of McPAT does not distinguish int and floating point pipelines
Theses parameters are reserved for future use.-->
<param name="pipelines_per_core" value="1,1"/>
<!--integer_pipeline and floating_pipelines, if the floating_pipelines is 0, then the pipeline is shared-->
<param name="pipeline_depth" value="7,7"/>
<!-- pipeline depth of int and fp, if pipeline is shared, the second number is the average cycles of fp ops -->
<!-- issue and exe unit-->
<param name="ALU_per_core" value="4"/>
<!-- contains an adder, a shifter, and a logical unit -->
<param name="MUL_per_core" value="0"/>
<!-- For MUL and Div -->
<param name="FPU_per_core" value="1"/>
<!-- buffer between IF and ID stage -->
<param name="instruction_buffer_size" value="32"/>
<!-- buffer between ID and sche/exe stage -->
<param name="decoded_stream_buffer_size" value="16"/>
<param name="instruction_window_scheme" value="0"/><!-- 0 PHYREG based, 1 RSBASED-->
<!-- McPAT support 2 types of OoO cores, RS based and physical reg based-->
<param name="instruction_window_size" value=""/>
<param name="fp_instruction_window_size" value=""/>
<!-- the instruction issue Q as in Alpha 21264; The RS as in Intel P6 -->
<param name="ROB_size" value=""/>
<!-- each in-flight instruction has an entry in ROB -->
<!-- registers -->
<param name="archi_Regs_IRF_size" value="32"/>
<param name="archi_Regs_FRF_size" value="32"/>
<!-- if OoO processor, phy_reg number is needed for renaming logic,
renaming logic is for both integer and floating point insts. -->
<param name="phy_Regs_IRF_size" value=""/>
<param name="phy_Regs_FRF_size" value=""/>
<!-- rename logic -->
<param name="rename_scheme" value="1"/>
<!-- can be RAM based(0) or CAM based(1) rename scheme
RAM-based scheme will have free list, status table;
CAM-based scheme have the valid bit in the data field of the CAM
both RAM and CAM need RAM-based checkpoint table, checkpoint_depth=# of in_flight instructions;
Detailed RAT Implementation see TR -->
<param name="register_windows_size" value="0"/>
<!-- how many windows in the windowed register file, sun processors;
no register windowing is used when this number is 0 -->
<!-- In OoO cores, loads and stores can be issued whether inorder(Pentium Pro) or (OoO)out-of-order(Alpha),
They will always try to exeute out-of-order though. -->
<param name="LSU_order" value="OoO"/>
<param name="store_buffer_size" value=""/>
<!-- By default, in-order cores do not have load buffers -->
<param name="load_buffer_size" value=""/>
<!-- number of ports refer to sustainable concurrent memory accesses -->
<param name="memory_ports" value="2"/>
<!-- max_allowed_in_flight_memo_instructions determins the # of ports of load and store buffer
as well as the ports of Dcache which is connected to LSU -->
<!-- dual-pumped Dcache can be used to save the extra read/write ports -->
<param name="RAS_size" value=""/>
<!-- general stats, defines simulation periods;require total, idle, and busy cycles for senity check -->
<!-- please note: if target architecture is X86, then all the instrucions refer to (fused) micro-ops -->
<stat name="total_instructions" value="400000"/>
<stat name="int_instructions" value="200000"/>
<stat name="fp_instructions" value="100000"/>
<stat name="branch_instructions" value="100000"/>
<stat name="branch_mispredictions" value="0"/>
<stat name="load_instructions" value="0"/>
<stat name="store_instructions" value="50000"/>
<stat name="committed_instructions" value="400000"/>
<stat name="committed_int_instructions" value="200000"/>
<stat name="committed_fp_instructions" value="100000"/>
<stat name="pipeline_duty_cycle" value="1"/><!-- lteq 1, runtime_ipc/peak_ipc; averaged for all cores if homogenous -->
<!-- the following cycle stats are used for heterogeneouse cores only,
please ignore them if homogeneouse cores -->
<stat name="total_cycles" value="4656693"/>
<stat name="idle_cycles" value=""/>
<stat name="busy_cycles" value=""/>
<!-- instruction buffer stats -->
<!-- ROB stats, both RS and Phy based OoOs have ROB
performance simulator should capture the difference on accesses,
otherwise, McPAT has to guess based on number of commited instructions. -->
<stat name="ROB_reads" value=""/>
<stat name="ROB_writes" value=""/>
<!-- RAT accesses -->
<stat name="rename_reads" value=""/> <!--lookup in renaming logic -->
<stat name="rename_writes" value="0"/><!--update dest regs. renaming logic -->
<stat name="fp_rename_reads" value=""/>
<stat name="fp_rename_writes" value="0"/>
<!-- decode and rename stage use this, should be total ic - nop -->
<!-- Inst window stats -->
<stat name="inst_window_reads" value=""/>
<stat name="inst_window_writes" value=""/>
<stat name="inst_window_wakeup_accesses" value=""/>
<stat name="fp_inst_window_reads" value=""/>
<stat name="fp_inst_window_writes" value=""/>
<stat name="fp_inst_window_wakeup_accesses" value=""/>
<!-- RF accesses -->
<stat name="int_regfile_reads" value=""/>
<stat name="float_regfile_reads" value=""/>
<stat name="int_regfile_writes" value=""/>
<stat name="float_regfile_writes" value=""/>
<!-- accesses to the working reg -->
<stat name="function_calls" value=""/>
<stat name="context_switches" value="9"/>
<!-- Number of Windowes switches (number of function calls and returns)-->
<!-- Alu stats by default, the processor has one FPU that includes the divider and
multiplier. The fpu accesses should include accesses to multiplier and divider -->
<stat name="ialu_accesses" value=""/>
<stat name="fpu_accesses" value=""/>
<stat name="mul_accesses" value="0"/>
<stat name="cdb_alu_accesses" value="0"/>
<stat name="cdb_mul_accesses" value="0"/>
<stat name="cdb_fpu_accesses" value="0"/>
<!-- multiple cycle accesses should be counted multiple times,
otherwise, McPAT can use internal counter for different floating point instructions
to get final accesses. But that needs detailed info for floating point inst mix -->
<!-- currently the performance simulator should
make sure all the numbers are final numbers,
including the explicit read/write accesses,
and the implicite accesses such as replacements and etc.
Future versions of McPAT may be able to reason the implicite access
based on param and stats of last level cache
The same rule applies to all cache access stats too! -->
<!-- following is AF for max power computation.
Do not change them, unless you understand them-->
<stat name="IFU_duty_cycle" value="1"/>
<stat name="LSU_duty_cycle" value="1"/>
<stat name="MemManU_I_duty_cycle" value="1"/>
<stat name="MemManU_D_duty_cycle" value="1"/>
<stat name="ALU_duty_cycle" value="1"/>
<stat name="MUL_duty_cycle" value="0.3"/>
<stat name="FPU_duty_cycle" value="1"/>
<stat name="ALU_cdb_duty_cycle" value="1"/>
<stat name="MUL_cdb_duty_cycle" value="0.3"/>
<stat name="FPU_cdb_duty_cycle" value="1"/>
<param name="number_of_BPT" value="2"/>
<component id="system.core0.predictor" name="PBT">
<!-- branch predictor; tournament predictor see Alpha implementation -->
<param name="local_predictor_size" value="10,3"/>
<param name="local_predictor_entries" value="1024"/>
<param name="global_predictor_entries" value="4096"/>
<param name="global_predictor_bits" value="2"/>
<param name="chooser_predictor_entries" value="4096"/>
<param name="chooser_predictor_bits" value="2"/>
<!-- These parameters can be combined like below in next version
<param name="load_predictor" value="10,3,1024"/>
<param name="global_predictor" value="4096,2"/>
<param name="predictor_chooser" value="4096,2"/>
-->
</component>
<component id="system.core0.itlb" name="itlb">
<param name="number_entries" value="48"/>
<stat name="total_accesses" value="4656693"/>
<stat name="total_misses" value="16"/>
<stat name="conflicts" value="0"/><!-- TODO -->
<!-- there is no write requests to itlb although writes happen to itlb after miss,
which is actually a replacement -->
</component>
<component id="system.core0.icache" name="icache">
<!-- there is no write requests to itlb although writes happen to it after miss,
which is actually a replacement -->
<param name="icache_config" value=""/>
<!-- the parameters are capacity,block_width, associativity, bank, throughput w.r.t. core clock, latency w.r.t. core clock,output_width, cache policy, -->
<!-- cache_policy;//0 no write or write-though with non-write allocate;1 write-back with write-allocate -->
<param name="buffer_sizes" value=""/>
<!-- cache controller buffer sizes: miss_buffer_size(MSHR),fill_buffer_size,prefetch_buffer_size,wb_buffer_size-->
<stat name="read_accesses" value=""/>
<stat name="read_misses" value=""/>
<stat name="conflicts" value=""/>
</component>
<component id="system.core0.dtlb" name="dtlb">
<param name="number_entries" value="64"/><!--dual threads-->
<stat name="total_accesses" value="2262713"/>
<stat name="total_misses" value="13"/>
<stat name="conflicts" value="0"/><!-- TODO -->
</component>
<component id="system.core0.dcache" name="dcache">
<!-- all the buffer related are optional -->
<param name="dcache_config" value=""/>
<param name="buffer_sizes" value=""/>
<!-- cache controller buffer sizes: miss_buffer_size(MSHR),fill_buffer_size,prefetch_buffer_size,wb_buffer_size-->
<stat name="read_accesses" value=""/>
<stat name="write_accesses" value=""/>
<stat name="read_misses" value=""/>
<stat name="write_misses" value=""/>
<stat name="conflicts" value=""/>
</component>
<param name="number_of_BTB" value="2"/>
<component id="system.core0.BTB" name="BTB">
<!-- all the buffer related are optional -->
<param name="BTB_config" value="6144,4,2,1, 1,3"/> <!--48Kbits -->
<!-- the parameters are capacity,block_width,associativity,bank, throughput w.r.t. core clock, latency w.r.t. core clock,-->
<stat name="read_accesses" value=""/> <!--See IFU code for guideline -->
<stat name="write_accesses" value=""/>
</component>
</component>
<!-- This block is ignored because number_of_L1Directories = 0 but it still has to be here-->
<component id="system.L1Directory0" name="L1Directory0">
<param name="Directory_type" value="0"/>
<!--0 cam based shadowed tag. 1 directory cache -->
<param name="Dir_config" value="4096,2,0,1,100,100, 8"/>
<!-- the parameters are capacity,block_width, associativity,bank, throughput w.r.t. core clock, latency w.r.t. core clock,-->
<param name="buffer_sizes" value="8, 8, 8, 8"/>
<!-- all the buffer related are optional -->
<param name="clockrate" value="3400"/>
<param name="ports" value="1,1,1"/>
<!-- number of r, w, and rw search ports -->
<param name="device_type" value="0"/>
<!-- altough there are multiple access types,
Performance simulator needs to cast them into reads or writes
e.g. the invalidates can be considered as writes -->
<stat name="read_accesses" value="800000"/>
<stat name="write_accesses" value="27276"/>
<stat name="read_misses" value="1632"/>
<stat name="write_misses" value="183"/>
<stat name="conflicts" value="20"/>
</component>
<!-- This block is ignored because number_of_L2Directories = 0 but it still has to be here-->
<component id="system.L2Directory0" name="L2Directory0">
<param name="Directory_type" value="0"/>
<!--0 cam based shadowed tag. 1 directory cache -->
<param name="Dir_config" value="512,4,0,1,1, 1"/>
<!-- the parameters are capacity,block_width, associativity,bank, throughput w.r.t. core clock, latency w.r.t. core clock,-->
<param name="buffer_sizes" value="16, 16, 16, 16"/>
<!-- all the buffer related are optional -->
<param name="clockrate" value="1200"/>
<param name="ports" value="1,1,1"/>
<!-- number of r, w, and rw search ports -->
<param name="device_type" value="0"/>
<!-- altough there are multiple access types,
Performance simulator needs to cast them into reads or writes
e.g. the invalidates can be considered as writes -->
<stat name="read_accesses" value="58824"/>
<stat name="write_accesses" value="27276"/>
<stat name="read_misses" value="1632"/>
<stat name="write_misses" value="183"/>
<stat name="conflicts" value="100"/>
</component>
<component id="system.L20" name="L20">
<!-- all the buffer related are optional -->
<param name="L2_config" value=""/>
<!-- the parameters are capacity,block_width, associativity, bank, throughput w.r.t. core clock, latency w.r.t. core clock,output_width, cache policy -->
<param name="buffer_sizes" value=""/>
<!-- cache controller buffer sizes: miss_buffer_size(MSHR),fill_buffer_size,prefetch_buffer_size,wb_buffer_size-->
<param name="clockrate" value=""/>
<param name="ports" value="1,1,1"/>
<!-- number of r, w, and rw ports -->
<param name="device_type" value="0"/>
<stat name="read_accesses" value=""/>
<stat name="write_accesses" value=""/>
<stat name="read_misses" value=""/>
<stat name="write_misses" value=""/>
<stat name="conflicts" value=""/>
<stat name="duty_cycle" value="1.0"/>
</component>
<!--**********************************************************************-->
<!-- This block is ignored because number_of_L3s = 0 but you must have it here anyway -->
<component id="system.L30" name="L30">
<param name="L3_config" value="16777216,64,16, 16, 16, 100,1"/>
<!-- the parameters are capacity,block_width, associativity,bank, throughput w.r.t. core clock, latency w.r.t. core clock,-->
<param name="clockrate" value="850"/>
<param name="ports" value="1,1,1"/>
<!-- number of r, w, and rw ports -->
<param name="device_type" value="0"/>
<param name="buffer_sizes" value="16, 16, 16, 16"/>
<!-- cache controller buffer sizes: miss_buffer_size(MSHR),fill_buffer_size,prefetch_buffer_size,wb_buffer_size-->
<stat name="read_accesses" value="11824"/>
<stat name="write_accesses" value="11276"/>
<stat name="read_misses" value="1632"/>
<stat name="write_misses" value="183"/>
<stat name="conflicts" value="0"/>
<stat name="duty_cycle" value="1.0"/>
</component>
<!--**********************************************************************-->
<component id="system.NoC0" name="noc0">
<param name="clockrate" value="1200"/>
<param name="type" value="1"/>
<!--0:bus, 1:NoC , for bus no matter how many nodes sharing the bus
at each time only one node can send req -->
<param name="horizontal_nodes" value="1"/>
<param name="vertical_nodes" value="1"/>
<param name="has_global_link" value="1"/>
<!-- 1 has global link, 0 does not have global link -->
<param name="link_throughput" value="1"/><!--w.r.t clock -->
<param name="link_latency" value="1"/><!--w.r.t clock -->
<!-- througput >= latency -->
<!-- Router architecture -->
<param name="input_ports" value="8"/>
<param name="output_ports" value="7"/>
<!-- For bus the I/O ports should be 1 -->
<param name="virtual_channel_per_port" value="2"/>
<param name="input_buffer_entries_per_vc" value="128"/>
<param name="flit_bits" value="40"/>
<param name="chip_coverage" value="1"/>
<!-- When multiple NOC present, one NOC will cover part of the whole chip.
chip_coverage <=1 -->
<param name="link_routing_over_percentage" value="1.0"/>
<!-- Links can route over other components or occupy whole area.
by default, 50% of the NoC global links routes over other
components -->
<stat name="total_accesses" value="*main::2"/>
<!-- This is the number of total accesses within the whole network not for each router -->
<stat name="duty_cycle" value="1"/>
</component>
<!--**********************************************************************-->
<component id="system.mem" name="mem">
<!-- Main memory property -->
<param name="mem_tech_node" value="180"/>
<param name="device_clock" value=""/><!--MHz, this is clock rate of the actual memory device, not the FSB -->
<param name="peak_transfer_rate" value="*main::16"/><!--MB/S-->
<param name="internal_prefetch_of_DRAM_chip" value="4"/>
<!-- 2 for DDR, 4 for DDR2, 8 for DDR3...-->
<!-- the device clock, peak_transfer_rate, and the internal prefetch decide the DIMM property -->
<!-- above numbers can be easily found from Wikipedia -->
<param name="capacity_per_channel" value="4096"/> <!-- MB -->
<!-- capacity_per_Dram_chip=capacity_per_channel/number_of_dimms/number_ranks/Dram_chips_per_rank
Current McPAT assumes single DIMMs are used.-->
<param name="number_ranks" value="2"/>
<param name="num_banks_of_DRAM_chip" value="8"/>
<param name="Block_width_of_DRAM_chip" value="64"/> <!-- B -->
<param name="output_width_of_DRAM_chip" value="8"/>
<!--number of Dram_chips_per_rank= 72/output_width_of_DRAM_chip-->
<!--number of Dram_chips_per_rank= 72/output_width_of_DRAM_chip-->
<param name="page_size_of_DRAM_chip" value="8"/> <!-- 8 or 16 -->
<param name="burstlength_of_DRAM_chip" value="8"/>
<stat name="memory_accesses" value=""/>
<stat name="memory_reads" value=""/>
<stat name="memory_writes" value=""/>
</component>
<component id="system.mc" name="mc">
<!-- Memeory controllers are for DDR(2,3...) DIMMs -->
<!-- current version of McPAT uses published values for base parameters of memory controller
improvments on MC will be added in later versions. -->
<param name="type" value="0"/> <!-- 1: low power; 0 high performance -->
<param name="mc_clock" value="800"/><!--MHz-->
<param name="peak_transfer_rate" value="1600"/><!--MB/S-->
<param name="block_size" value="16"/><!--B-->
<param name="number_mcs" value="2"/>
<!-- current McPAT only supports homogeneous memory controllers -->
<param name="memory_channels_per_mc" value="2"/>
<param name="number_ranks" value="2"/>
<param name="withPHY" value="0"/>
<!-- # of ranks of each channel-->
<param name="req_window_size_per_channel" value="32"/>
<param name="IO_buffer_size_per_channel" value="32"/>
<param name="databus_width" value="32"/>
<param name="addressbus_width" value="32"/>
<!-- McPAT will add the control bus width to the addressbus width automatically -->
<stat name="memory_accesses" value=""/>
<stat name="memory_reads" value=""/>
<stat name="memory_writes" value=""/>
<!-- McPAT does not track individual mc, instead, it takes the total accesses and calculate
the average power per MC or per channel. This is sufficent for most application.
Further trackdown can be easily added in later versions. -->
</component>
<!--**********************************************************************-->
<component id="system.niu" name="niu">
<!-- On chip 10Gb Ethernet NIC, including XAUI Phy and MAC controller -->
<!-- For a minimum IP packet size of 84B at 10Gb/s, a new packet arrives every 67.2ns.
the low bound of clock rate of a 10Gb MAC is 150Mhz -->
<param name="type" value="0"/> <!-- 1: low power; 0 high performance -->
<param name="clockrate" value="350"/>
<param name="number_units" value="0"/> <!-- unlike PCIe and memory controllers, each Ethernet controller only have one port -->
<stat name="duty_cycle" value="1.0"/> <!-- achievable max load lteq 1.0 -->
<stat name="total_load_perc" value="0.7"/> <!-- ratio of total achived load to total achivable bandwidth -->
<!-- McPAT does not track individual nic, instead, it takes the total accesses and calculate
the average power per nic or per channel. This is sufficent for most application. -->
</component>
<!--**********************************************************************-->
<component id="system.pcie" name="pcie">
<!-- On chip PCIe controller, including Phy-->
<!-- For a minimum PCIe packet size of 84B at 8Gb/s per lane (PCIe 3.0), a new packet arrives every 84ns.
the low bound of clock rate of a PCIe per lane logic is 120Mhz -->
<param name="type" value="0"/> <!-- 1: low power; 0 high performance -->
<param name="withPHY" value="1"/>
<param name="clockrate" value="350"/>
<param name="number_units" value="0"/>
<param name="num_channels" value="8"/> <!-- 2 ,4 ,8 ,16 ,32 -->
<stat name="duty_cycle" value="1.0"/> <!-- achievable max load lteq 1.0 -->
<stat name="total_load_perc" value="0.7"/> <!-- Percentage of total achived load to total achivable bandwidth -->
<!-- McPAT does not track individual pcie controllers, instead, it takes the total accesses and calculate
the average power per pcie controller or per channel. This is sufficent for most application. -->
</component>
<!--**********************************************************************-->
<component id="system.flashc" name="flashc">
<param name="number_flashcs" value="0"/>
<param name="type" value="1"/> <!-- 1: low power; 0 high performance -->
<param name="withPHY" value="1"/>
<param name="peak_transfer_rate" value="200"/><!--Per controller sustainable reak rate MB/S -->
<stat name="duty_cycle" value="1.0"/> <!-- achievable max load lteq 1.0 -->
<stat name="total_load_perc" value="0.7"/> <!-- Percentage of total achived load to total achivable bandwidth -->
<!-- McPAT does not track individual flash controller, instead, it takes the total accesses and calculate
the average power per fc or per channel. This is sufficent for most application -->
</component>
<!--**********************************************************************-->
</component>
</component>
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
