x86 CPUID Tool v 0.1.8 --------------------------------------------------------------------------- Vender Identifier : GenuineIntel Vender Type : Intel Intel CPU Type : OEM Intel CPU Brand : Intel Pentium 4 Xeon processor Type/Family/Model/Stepping: 0/f/2/7 Max CPUID func(std/ext) : 2/4 CPU Serial No. : Not supported or disabled CPU Name String : Intel(R) Xeon(TM) CPU 2.00GHz CPU Detailed Type : Intel Pentium 4 .13 CLFLUSH Line Size : 64 Logical Processor Number : 2 Local APIC Physical ID : 0 L1 Instruction Cache : 12K, 0-way set associative L1 Data Cache : 8K, 4-way set associative L2 Cache : 512K, 8-way set associative --------------------------------------------------------------------------- CPU Feature Flags Value : bfebfbff/00000000 * FPU on chip * Virtual-8086 mode enhancement * Debugging extensions * Page size extensions (4M page) * Time stamp counter * Model specific registers * Physical address extension * Machine check exception * CMPXCHG8B instruction * Advanced programmable interrupt controller on chip * OS support SSE * SYSENTER/SYSEXIT * P6 Memory type range registers * PTE global flag * Machine check architecture * CMOV instructions * Page attribute table * Page size extension (exceed 4GB memory) Processor ID * CLFLUSH instruction * Extended MMX instructions * Debug trace & event monitor store * ACPI processor performance modulation registers * MMX instructions * FXSAVE/FXRSTOR instructions * SSE instructions * SSE2 instructions * Self snoop * Hyper-Threading Technology * Thermal Monitor supported Extended 3DNow! instructions 3DNow! instructions AMD SYSCALL/SYSRET K6 Memory type range registers Pentium FDIV bug * Denormals are zero * OS support SSE exceptions AMD multiprocessor support AMD temperature sensing diode AMD Frequency ID (FID) control AMD Voltage ID (VID) control --------------------------------------------------------------------------- (40) L3 cache : 0K, 0-way set associative, 0 byte line size (50) Instruction TLB : 4K/2M/4M Pages, fully associative, 64 entries (5b) Data TLB : 4K/4M Pages, fully associative, 64 entries (66) Data cache (Sec) : 8K, 4-way set associative, 64 byte line size (70) Trace cache : 12K uOP, 8-way set associative (Instruction) (7b) L2 cache (Sec) : 512K, 8-way set associative, 64 byte line size --------------------------------------------------------------------------- Detected CPU speed : 1977MHz --------------------------------------------------------------------------- CPU test end. Memory Subsystem Test 0.3.3 (experimental) -------------OS Brief Information------------------------------------------ OS Version: Windows NT 5.01 Build 2600 () OS Reported CPU: x86 15/2/7, Total 4, Active f Page Size: 4KB, Address Space: 00010000~7ffeffff, Alloc Granularity: 64KB Total Memory: 512MB, Current Available: 384MB Process Name ID Size(KB) Warning System Idle Process 0 20 System 4 284 smss.exe 516 376 csrss.exe 564 3692 winlogon.exe 592 1460 services.exe 636 2732 lsass.exe 648 1164 svchost.exe 832 3576 svchost.exe 880 15288 * svchost.exe 936 2956 svchost.exe 964 3252 spoolsv.exe 1016 3952 alg.exe 1124 3544 defwatch.exe 1148 1368 rtvscan.exe 1192 9420 * explorer.exe 1956 17744 * vptray.exe 260 2964 ctfmon.exe 268 1724 MSGSYS.EXE 288 2028 Bench.exe 1924 2664 Warning: Large process (marked as *) may affect test. -------------Performance Related to Function Start Offset------------------ (B/c) Read/2 Read/3 Write/2 Write/3 Copy/2 Copy/3 00 3.93610 3.80957 1.99231 2.05458 1.98606 1.99893 01 3.80824 3.81256 2.11325 2.05432 1.98378 1.99912 02 3.81234 3.80957 1.99043 2.05394 1.98498 1.99924 03 3.81023 3.81145 1.99028 2.05432 1.98651 1.99933 04 3.81156 3.80957 1.99071 2.05397 1.98594 1.99896 05 3.93421 3.80901 1.99049 2.05442 1.98784 1.99872 06 3.81311 3.80957 1.99128 2.05445 1.98447 1.99893 07 3.81068 3.78843 2.11342 2.05500 1.98450 1.99902 08 3.80968 3.80957 1.99119 2.05381 1.98971 1.99982 09 3.81012 3.80946 1.99040 2.11875 1.98501 1.99878 10 3.81223 3.78788 1.99401 2.05513 1.98775 2.00122 11 3.93102 3.81278 2.11338 2.05268 1.98405 2.00037 12 3.81134 3.80957 1.99204 2.05381 1.98588 1.99902 13 3.80824 3.78843 2.11318 2.05445 1.98462 1.99951 14 3.81234 3.80957 1.99055 2.05127 1.98465 1.99939 15 3.81079 3.81256 1.99071 2.05349 1.98465 2.00064 16 3.81212 3.80957 1.99122 2.05362 1.98483 1.99893 17 3.91003 3.80846 1.99104 2.05284 1.98582 1.99857 18 3.80968 3.78876 1.99040 2.05423 1.98829 1.99924 19 3.81023 3.93527 1.99031 2.05426 1.98363 1.99866 20 3.81245 3.80957 1.98986 2.05384 1.98735 1.99841 21 3.80735 3.81267 2.11287 2.05223 1.98423 1.99905 22 3.80968 3.81212 1.99083 2.05429 1.98615 1.99915 23 3.81212 3.80901 2.11335 2.05291 1.98678 1.99908 24 3.80957 3.81212 1.99152 2.05207 1.98483 1.99881 25 3.81300 3.80901 2.11451 2.05336 1.98642 1.99924 26 3.80957 3.80957 1.99113 2.05481 1.98447 1.99908 27 3.81300 3.81267 1.99022 2.05358 1.98255 1.99857 28 3.81167 3.78810 1.99077 2.05426 1.98636 1.99915 29 3.80824 3.81256 2.11328 2.05390 1.98281 1.99945 30 3.78525 3.81223 1.99104 2.05436 1.98612 1.99936 31 3.91003 3.81278 2.11301 2.05481 1.98534 1.99884 -------------Performance Difference with Loop Unroll----------------------- (%)RD/04 WR/04 CP/04 RD/08 WR/08 CP/08 RD/16 WR/16 CP/16 RL/04 CL/04 00 0.002 1.046 0.159 0.099 0.031 8.507 0.817 0.020 0.533 0.057 0.662 01 0.006 0.046 0.092 0.010 0.024 27.64 0.387 0.016 23.49 0.040 1.835 02 0.013 6.262 1.553 0.008 0.018 12.99 0.047 0.224 0.074 0.066 3.879 03 0.011 3.285 0.168 0.016 0.012 0.127 1.853 0.063 24.58 0.064 1.479 04 0.006 0.017 2.058 0.005 0.012 4.519 0.139 0.031 1.654 0.061 1.650 05 0.008 0.030 1.703 0.005 0.022 0.064 0.024 0.030 0.510 0.070 0.844 06 0.006 0.011 1.062 0.005 0.008 1.081 0.028 0.259 0.063 0.054 0.293 07 0.004 0.030 1.078 0.114 0.238 0.570 0.314 0.381 1.624 0.053 0.268 08 0.246 0.207 1.646 0.179 0.348 0.334 0.304 0.395 0.940 0.074 2.028 09 0.229 0.275 0.812 0.174 0.342 0.970 2.166 0.201 0.829 0.052 0.928 10 0.221 0.411 1.171 0.159 0.202 1.393 0.002 0.015 N/A 0.067 1.654 11 0.191 0.319 1.616 0.002 0.030 N/A N/A N/A N/A 0.019 1.269 ** 0 11 255 0 0 255 10 0 255 0 255 -------------Max Performance with Loop Unroll------------------------------ (B)RD/04 WR/04 CP/04 RD/08 WR/08 CP/08 RD/16 WR/16 CP/16 RL/04 CL/04 00 2.653 1.990 1.519 4.257 3.534 2.382 8.487 4.549 3.344 1.391 0.846 01 2.775 2.090 1.635 4.258 3.537 2.648 8.494 4.548 3.303 1.391 0.858 02 2.775 2.119 1.685 4.258 3.540 2.580 8.506 4.558 2.682 1.392 0.913 03 2.776 2.124 1.636 4.258 3.541 2.289 8.477 4.558 3.320 1.391 0.916 04 2.775 1.993 1.567 4.258 3.541 2.398 8.493 4.558 2.858 1.392 0.927 05 2.775 1.994 1.629 4.258 3.541 3.036 8.506 4.550 2.929 1.391 0.903 06 2.775 2.006 1.599 4.258 3.541 2.765 8.507 4.550 2.945 1.391 0.931 07 2.775 1.995 1.610 4.258 3.541 2.806 8.532 4.566 2.995 1.391 0.931 08 2.775 2.025 1.604 4.266 3.553 2.776 8.532 4.567 2.982 1.392 0.928 09 2.781 2.013 1.594 4.266 3.553 2.804 8.532 4.566 2.968 1.391 0.922 10 2.781 2.017 1.594 4.266 3.553 2.794 8.532 4.566 N/A 1.391 0.928 11 2.781 2.012 1.597 4.266 3.553 N/A N/A N/A N/A 1.391 0.925 -------------Address Mode Comparison--------------------------------------- (B/c) RD/IND RD/SIB RD/SIB4 WR/IND WR/SIB WR/SIB4 00 2.64141 2.64141 2.64141 1.98441 1.90895 1.90961 01 3.81223 3.80957 3.81278 2.08309 2.06020 2.06192 02 3.80957 3.78810 3.81289 1.99161 2.08246 2.08249 03 3.81201 3.81212 3.81245 2.11988 2.05477 2.05545 04 3.81134 3.81034 3.81034 1.98772 1.99198 2.04340 05 3.81567 3.81556 3.78854 1.98977 2.08481 2.08504 06 3.78482 3.78471 3.80901 2.00128 2.03620 2.03620 07 3.79117 3.76719 3.79106 1.99173 2.01126 2.01132 08 3.96635 3.81656 3.84184 2.03011 2.04207 2.04242 09 3.84150 3.83835 3.94107 2.01321 2.04308 2.04296 10 3.84049 3.84015 3.84060 2.01674 2.04366 2.04976 11 3.84150 3.84049 3.96479 2.00821 2.04331 2.04404 12 N/A N/A N/A N/A N/A N/A -------------L1 Size Test/L2 Size Estimate Step 1-------------------------- (B/c) Read04 Read08 Read16 4K 3.99732 7.99463 15.9893 8K 3.83835 7.38621 15.4881 16K 2.76839 4.26576 8.53153 32K 2.77777 4.25780 8.53125 64K 2.77936 4.26347 8.52127 128K 2.78084 4.26458 8.52321 256K 2.74711 4.18784 8.07703 512K 2.58247 3.83237 6.93553 1024K 0.77624 0.91342 1.16350 ***** Detected L1 D-Cache Size: 8KB, Estimated L2 Size: 512KB -------------L2 Size Estimate Step 2--------------------------------------- (B/c) Read04 Read08 Read16 512K 2.57393 3.79254 6.90466 576K 0.77866 0.91647 1.16642 640K 0.77640 0.91405 1.16142 704K 0.77678 0.91468 1.16235 768K 0.77687 0.91332 1.16142 832K 0.77688 0.91495 1.16304 896K 0.77701 0.91467 1.16194 960K 0.77623 0.91485 1.16346 1024K 0.77639 0.91372 1.16198 ***** Efficient L2 Size: 512KB -------------L1 Read Performance Test-------------------------------------- (Cycle) Read04 Read08 Read16 RL/04(Latency) 6 1.05106 1.04089 1.05255 2.08359 7 1.05594 1.08322 1.09079 2.08359 8 1.01514 1.08325 1.03024 2.03110 9 1.04233 1.09689 1.03024 2.08359 10 1.04233 1.02859 N/A 2.08359 11 1.04230 N/A N/A 2.08359 -------------L1 Write Performance Test------------------------------------- (Cycle) Write04 Write08 Write16 6 1.99869 2.26669 3.50430 7 2.00870 2.25198 3.50421 8 1.97018 2.25174 3.50388 9 1.98694 2.25159 3.50406 10 1.98346 2.25168 N/A 11 1.99176 N/A N/A -------------L1 Copy Performance Test-------------------------------------- (Cycle) Copy04 Copy08 Copy16 CL/04(Latency) 6 1.95407 2.25833 3.50415 3.00125 7 1.95584 2.25858 3.50409 3.00165 8 1.96146 2.25848 3.50424 3.00150 9 1.96423 2.27042 N/A 3.00165 10 1.96408 N/A N/A 3.00165 11 N/A N/A N/A N/A -------------L1 Block Size/Miss Penalty (with 256KB Memory)--------------- (Cycle) 4B 8B 16B 32B 64B 128B 256B Read04 1.45477 1.90937 1.97511 2.19887 2.43755 2.50018 2.28985 Read08 1.90865 1.91022 1.99707 2.23566 2.68355 2.70827 2.66350 Read16 1.97714 1.94598 1.97418 2.17859 2.55768 2.53076 2.61105 Latency 2.82973 2.91040 4.49280 11.0156 18.4769 18.4905 17.8586 HitRate 0.93750 0.87500 0.75000 0.50000 0.00000 0.00000 0.00000 Penalty 12.7782 7.03442 9.84680 17.9691 16.4458 16.4594 15.8275 ***** Detected Block Size: 64B -------------L2 Block Size/Miss Penalty (with 1024KB Memory)--------------- (Cycle) 4B 8B 16B 32B 64B 128B 256B Read04 5.14951 8.76287 13.6946 24.1878 51.7182 88.3223 90.2547 Read08 8.74701 8.75336 13.6733 24.1498 51.5503 88.2178 89.2472 Read16 13.7502 13.7508 13.7512 24.1197 51.4920 86.6080 87.7697 Latency 6.14019 10.9273 21.2166 41.4327 85.7592 335.957 332.453 HitRate 0.96875 0.93750 0.87500 0.75000 0.50000 0.00000 0.00000 Penalty 131.491 142.339 153.484 157.606 167.456 333.925 330.422 ***** Detected Block Size: 128B -------------L1 Association Estimate (LRU Only)---------------------------- (B/c) Read04 Read08 Read16 8.0K 3.15867 6.31733 14.9383 8.2K N/A N/A N/A 8.5K N/A N/A N/A 9.0K 2.30836 4.64816 10.1968 10.0K 1.88632 3.73293 7.63458 12.0K 1.76994 3.56313 7.14282 16.0K 1.88087 3.76503 7.58991 ***** Estimated L1 Association: 4 -------------L2 Association Estimate (LRU Only)---------------------------- (B/c) Read04 Read08 Read16 512.0K 0.86155 1.69857 3.47969 528.0K 0.14853 0.30207 0.60367 544.0K 0.08369 0.16506 0.33338 576.0K 0.04535 0.09055 0.18603 640.0K 0.04532 0.08795 0.18657 768.0K 0.04535 0.09301 0.18638 1024.0K 0.04613 0.09203 0.18423 ***** Estimated L2 Association: 8 -------------L1 Write Policy Test------------------------------------------ (Cycle) W-M W-H R-CH R-H-D R-M R-H 00 10.9688 10.9688 3.09375 1.78125 2.40625 1.78125 01 10.9688 10.9375 2.40625 1.78125 2.40625 1.78125 02 11.0312 11.0312 2.40625 1.78125 2.40625 1.78125 03 11.0312 10.9375 2.40625 1.78125 2.40625 1.78125 04 11.0312 10.9688 2.40625 1.78125 2.40625 1.78125 05 11.0938 10.9375 2.40625 1.78125 2.40625 1.78125 06 10.9375 11.0312 2.40625 1.78125 2.40625 1.78125 07 11.0312 10.9375 2.40625 1.78125 2.40625 1.78125 08 11.0312 10.9688 2.40625 1.78125 2.40625 1.78125 09 11.1875 10.9375 2.40625 1.78125 2.40625 1.78125 10 11.0312 10.9375 2.40625 1.78125 2.40625 1.78125 11 11.0312 10.9375 2.40625 1.78125 2.40625 1.78125 12 11.0312 10.9688 2.40625 1.78125 2.40625 1.78125 13 11.0312 10.9375 2.40625 1.78125 2.40625 2.31250 14 11.0312 10.9375 2.40625 1.78125 2.40625 1.78125 15 11.0312 11.0312 2.40625 1.78125 2.40625 2.31250 ***** Detected Write Policy: Write Through -------------L2 Write Policy Test------------------------------------------ (Cycle) W-M W-H R-CH R-H-D R-M R-H 00 106.461 11.9570 315.819 4.09668 86.7441 4.35547 01 106.450 11.9609 312.823 4.14941 86.6689 4.36035 02 106.354 11.9824 310.852 4.28125 86.7646 4.44238 03 106.397 11.9854 313.724 4.18066 86.8330 4.40234 04 106.335 11.9404 314.154 4.08203 86.8799 4.38574 05 106.367 11.9746 314.404 4.12500 86.7041 4.38379 06 106.372 11.9805 314.964 4.03809 86.7656 4.39648 07 106.496 11.9648 314.028 4.14648 86.9434 4.38672 08 106.364 11.9590 314.190 4.20898 86.9375 4.32715 09 106.429 11.9971 313.664 4.11914 86.7402 4.38379 10 106.447 11.9697 315.249 4.31250 86.7285 4.42188 11 106.558 11.9766 311.534 4.14551 86.7500 4.41406 12 106.479 11.9424 312.452 4.17090 86.7090 4.33105 13 106.352 11.9688 313.423 4.12598 86.7998 4.34277 14 106.463 11.9727 315.013 4.16406 86.7930 4.41992 15 106.281 11.9912 314.681 4.12500 86.8154 4.38770 ***** Detected Write Policy: Write Back (Miss Allocate) -------------L2 Cache Bandwidth Test (with 256K Memory)------------------- (B/c) Read04 Write04 Read08 Write08 Read16 Write16 RL/04(Latency) 08 26.1419 5.17623 26.9366 5.17542 26.3577 5.17696 18.3911 09 25.2771 5.17640 24.7701 5.17601 25.1557 5.17631 18.4705 10 26.4611 5.17643 25.1102 5.17580 25.2213 5.17640 18.4813 11 26.5425 5.17617 26.3114 5.17665 25.5029 5.17527 18.4131 12 25.1939 5.17612 N/A N/A N/A N/A 18.5069 -------------Memory Bandwidth Test (with 1024K Memory)------------------- (MB/s) Read04 Write04 Read08 Write08 Read16 Write16 RL/04(Latency) 08 2928.70 1212.97 2844.74 1112.72 2959.19 1075.66 334.584 09 2883.39 1119.84 2894.03 1085.90 2959.97 1097.32 335.854 10 2893.43 1186.87 2864.56 1199.41 2869.81 1227.57 335.682 11 2838.20 1202.40 2814.88 1177.58 2901.48 1179.54 335.227 12 N/A N/A N/A N/A N/A N/A 335.172 -------------Copy Speed Comparison (main memory)--------------------------- (MB/s) MOVSD Cross Block NTQ NTQI NTQpf NTQBlk NTQBlkI 00 516.043 470.082 470.507 737.489 708.881 767.648 1061.56 1065.01 01 523.521 473.996 470.625 740.522 711.604 766.473 1060.43 1066.18 02 524.683 470.972 469.886 742.055 710.233 765.839 1062.09 1064.33 03 524.814 472.460 466.007 741.526 710.237 765.179 1067.37 1064.95 04 516.879 470.699 469.563 737.820 711.253 765.034 1062.01 1065.26 05 523.943 471.663 468.989 740.249 710.689 768.597 1067.00 1066.76 06 523.725 471.665 468.565 740.191 711.814 769.700 1063.94 1066.24 07 521.088 470.926 465.831 735.703 709.110 766.923 1065.53 1065.04 08 522.699 469.016 468.071 740.336 707.454 766.240 1060.76 1068.18 09 521.817 470.969 468.555 744.127 706.555 767.426 1059.73 1065.83 10 521.252 471.030 469.578 741.386 708.427 766.264 1063.44 1065.52 11 520.812 470.647 466.482 741.522 709.407 766.690 1061.22 1063.03 12 522.848 469.154 468.337 744.117 709.436 765.689 1063.34 1066.01 13 522.831 470.438 467.571 737.986 707.834 766.472 1064.32 1066.07 14 524.464 472.790 468.369 736.572 714.690 767.259 1061.72 1066.03 15 522.825 471.876 465.837 742.049 707.900 766.412 1062.98 1066.18 *** Warning: Args of NTQBlk need adjust -------------Copy Speed Comparison (video memory)-------------------------- (MB/s) MOVSD Cross Block NTQ NTQI NTQpf NTQBlk NTQBlkI 00 141.527 150.800 151.558 151.516 151.249 151.543 152.697 152.724 01 141.419 150.827 151.303 151.725 151.245 151.521 152.746 152.724 02 141.200 150.847 151.248 151.661 150.989 151.535 152.730 152.790 03 141.276 150.803 151.581 151.621 151.008 151.544 152.855 152.804 04 141.145 150.854 151.338 151.479 151.031 151.548 152.797 152.837 05 141.268 150.810 151.489 151.398 151.254 151.514 152.828 152.851 06 140.997 150.859 151.454 151.394 151.255 151.432 152.719 152.649 07 141.588 150.909 151.492 151.446 151.166 151.497 152.732 152.764 08 141.415 150.797 151.127 151.410 151.261 151.580 152.728 152.813 09 141.055 150.966 151.487 151.640 151.300 151.568 152.785 152.688 10 141.512 150.869 151.630 151.525 151.099 151.647 152.710 152.699 11 140.904 150.807 151.420 151.587 151.265 151.462 152.787 152.757 12 141.672 150.896 151.796 151.700 151.241 151.589 152.767 152.556 13 141.693 150.869 151.756 148.378 120.726 151.586 152.725 152.748 14 141.393 150.973 151.390 151.706 151.275 151.475 152.636 152.720 15 141.378 150.742 151.230 151.536 151.041 151.523 152.714 152.776 *** Warning: Args of NTQBlk need adjust -------------Data TLB Test Step 1------------------------------------------ (Cycle) 0 2 4 6 8 2 1.00153 1.00122 1.00122 1.00122 1.00122 4 1.00116 1.00122 1.00122 1.00122 1.00122 8 1.00122 1.00122 1.00122 1.00122 1.00122 16 1.00122 1.00122 1.00122 1.00122 N/A 32 1.00122 1.00128 1.00128 1.00122 N/A 64 1.36145 1.34491 1.33563 N/A N/A 96 20.0645 20.0588 19.7943 N/A N/A ***** Estimated Data TLB entry: L1 64, L2 0 -------------L1 Data TLB Entry Test Step 2--------------------------------- (Cycle) 0 2 4 6 8 64 1.31378 1.31348 1.31360 N/A N/A 72 4.03022 4.41202 3.91884 N/A N/A 80 10.2304 10.4737 10.5122 N/A N/A 88 17.1905 17.3785 17.1997 N/A N/A ***** Detected L1 Data TLB Entry: 64 -------------L1 Data TLB Association Test---------------------------------- (Cycle) 0 2 4 6 8 64 1.33728 1.31232 1.31183 N/A N/A 65 1.49280 1.48278 1.47131 N/A N/A 66 1.60582 1.63777 1.82857 N/A N/A 68 2.33804 2.34105 2.27623 N/A N/A 72 4.02411 3.93325 4.02951 N/A N/A 80 10.5071 10.3075 10.3330 N/A N/A 96 20.0349 20.0964 19.9864 N/A N/A ***** Detected L1 Data TLB Association: 2 Warning: Too small L1, above value may be error. -------------Special Comparison: movups vs. movaps------------------------- (B/c) RD/ups RD/aps WR/ups WR/aps CP/ups CP/aps 4K 7.87397 15.9893 2.64235 4.56637 N/A N/A 16K 4.26608 8.53153 2.65103 4.56637 1.98144 2.95897 1024K 0.88498 1.16356 0.39739 0.41179 0.22590 0.23449 -------------Special Comparison: movdqu vs. movdqa------------------------- (B/c) RD/dqu RD/dqa WR/dqu WR/dqa CP/dqu CP/dqa 4K 7.87420 15.9893 1.99781 4.56601 N/A N/A 16K 4.26608 8.53153 1.99889 4.56637 1.58914 2.95899 1024K 0.88479 1.16315 0.35303 0.33281 0.21840 0.23996 -------------Special Comparison: movdqa vs. movaps------------------------- (B/c) RD/dqa RD/aps WR/dqa WR/aps CP/dqa CP/aps 4K 15.9893 15.9893 4.56593 4.56637 N/A N/A 16K 8.53153 8.53153 4.56613 4.56625 2.96037 2.96027 1024K 1.16368 1.16427 0.35871 0.39301 0.23163 0.22849 -------------Align Comparison Part 1: 32-Bit------------------------------- (B/c) Read/U Read/A Write/U Write/A Copy/U Copy/A 4KB 2.28767 3.99732 0.61814 2.02976 0.54279 2.04414 16KB 2.29846 2.76833 0.61957 2.02515 0.53235 1.59626 1024KB 0.73826 0.77618 0.40241 0.39340 0.21783 0.24041 -------------Align Comparison Part 2: 64-Bit------------------------------- (B/c) Read/U Read/A Write/U Write/A Copy/U Copy/A 4KB 3.08597 7.99463 0.67492 3.55281 0.69672 3.53375 16KB 2.38712 4.26576 0.67448 3.55266 0.56802 2.79287 1024KB 0.85159 0.91468 0.35888 0.35285 0.21442 0.21690 -------------Align Comparison Part 3: 128-Bit------------------------------ (B/c) Read/U Read/A Write/U Write/A Copy/U Copy/A 4KB 2.90120 15.9893 0.68424 4.56613 N/A N/A 16KB 2.21849 8.53153 0.68414 4.56601 0.64732 2.96113 1024KB 0.84002 1.16264 0.39891 0.37115 0.24626 0.25023 -------------Special Comparison: No Cache (video memory)------------------- (MB/s) Read/U Read/A Write/U Write/A Copy/U Copy/A 32Bit 3.13422 6.62720 149.165 148.691 2.51893 5.86410 64Bit 4.84286 9.23181 142.099 152.388 3.47264 7.34667 128Bit 4.84264 9.69522 142.997 147.212 4.18362 6.10400 *** Write combine for video memory: yes -------------Write Combine Buffer Test (experimental)---------------------- (MB/s) 8 16 32 64 128 256 512 1024 12 88.1221 88.1571 88.2258 152.136 151.996 152.070 152.099 152.181 11 90.5904 88.1828 88.2006 152.406 152.303 152.325 152.124 152.241 10 88.0671 88.0946 88.1563 152.585 151.865 151.868 151.895 151.754 9 88.0935 88.1234 88.1880 152.223 151.743 152.005 151.932 151.985 8 88.0585 88.0839 88.1353 151.064 151.607 151.741 151.761 151.891 7 94.8794 88.3697 88.1772 151.561 151.910 152.022 152.020 152.215 6 88.0700 88.1091 94.9761 152.035 151.867 151.965 152.034 152.155 5 88.1431 94.6306 95.9322 151.952 152.257 151.809 151.826 151.884 4 88.0582 88.0578 88.1341 150.488 151.263 151.789 151.983 151.714 3 115.602 126.340 134.757 152.269 152.141 151.784 152.893 151.945 2 88.0581 88.0690 88.0986 146.246 150.856 150.857 152.081 152.192 1 151.862 152.077 152.034 152.024 151.916 151.991 152.040 152.177 ** Estimated WC buffer: >= 3-Entry, 64B -------------Special Comparison: No Cache (main memory)-------------------- (MB/s) Read/U Read/A Write/U Write/A Copy/U Copy/A 32Bit 17.7422 19.5313 52.3600 78.6518 12.1211 14.1989 64Bit 32.6052 39.7091 78.5537 157.580 20.5109 27.7306 128Bit 32.5144 71.3990 78.5734 158.094 21.7389 44.2676 -------------Special Comparison: Register---------------------------------- (B/c) ALU Limit MMX Limit SSE2 Limit SSE Limit 00 2.99912 8.99741 5.33062 15.9919 10.6612 31.9839 10.6612 31.9839 01 5.33062 10.6612 7.99536 15.9907 15.9907 31.9815 15.9907 31.9815 02 7.99366 11.9906 7.99610 11.9941 15.9922 23.9883 15.9922 23.9883 03 7.99512 9.99396 7.99585 9.99481 15.9917 19.9896 15.9917 19.9896 04 10.6554 11.9874 7.99561 8.99509 15.9912 17.9902 15.9912 17.9902 05 10.6554 11.3214 7.99561 8.49538 15.9912 16.9908 15.9912 16.9908 06 11.6229 11.9862 7.99536 8.24527 15.9907 16.4905 15.9907 16.4905 07 11.6229 11.8046 7.99536 8.12031 15.9907 16.2406 15.9907 16.2406 08 11.8929 11.9859 7.99536 8.05785 15.9907 16.1157 15.9907 16.1157 09 11.6240 11.6695 7.99536 8.02664 15.9907 16.0533 15.9907 16.0533 10 11.6898 11.7127 7.99536 8.01100 15.9907 16.0220 15.9907 16.0220 11 11.6571 11.6685 7.99536 8.00318 15.9907 16.0064 15.9907 16.0064 12 11.6571 11.6628 7.99536 7.99933 N/A N/A 15.9907 15.9987 -------------Multiply By 10 Test: Latency---------------------------------- (Cycle) IMULC IMULR LEA2R2 LEA1R1 Add4R2 SHL1R1 SHL1 SHL3 07 14.0003 14.0003 5.00027 5.00024 2.00037 8.00026 4.00034 4.00034 08 14.0003 14.0003 5.00027 5.00026 2.00037 8.00026 4.00034 4.00034 09 14.0003 14.0003 5.00027 5.00026 2.00037 8.00026 4.00034 4.00034 10 14.0003 14.0003 5.00027 5.00024 2.02258 8.00026 4.00034 4.00034 Size 3 3 7 5 11 5 2 3 -------------Multiply By 10 Test: Throughput------------------------------- (Cycle) IMULC IMULR LEA2R2 LEA1R1 Add4R2 SHL1R1 SHL1 SHL3 07 4.66674 6.00006 2.02820 1.02555 1.71257 2.40007 1.00007 1.00007 08 4.66674 6.00006 2.02995 1.02759 1.72060 2.00046 1.00007 1.00007 09 4.66674 6.00006 N/A 1.03057 N/A 2.01340 1.00007 1.00007 10 4.66674 6.00006 N/A N/A N/A N/A 1.00007 1.00007 Size 15 15 35 25 55 25 10 15 -------------BTB Depth Test (with CMOVcc Instruction)---------------------- ***** Experimental Block Jcc Test (Cycle) Penalty N/Min N/Max Y/Min Y/Max 01 - 8.00146 8.00159 7.00159 8.00159 02 - 7.00159 9.00104 7.00238 9.00140 03 - 8.00122 9.33429 8.00153 8.66772 04 - 7.50159 8.50122 8.00153 8.50116 05 - 7.60126 14.6002 7.60327 14.6006 06 6.00769 9.00275 13.0007 12.6675 13.0008 07 23.9988 11.4299 12.2869 11.4299 12.2869 08 23.9961 11.0010 11.7508 11.0010 11.7508 09 21.9963 10.4455 11.3342 10.4455 11.3342 10 21.9971 10.2012 11.0009 10.7010 11.0010 11 19.9952 9.81921 10.7281 10.5463 10.7283 12 19.9980 9.66797 10.5010 9.66797 10.5012 13 17.9988 9.38599 10.3088 10.1550 10.3089 14 17.9982 9.28705 10.1440 9.92981 10.1441 15 15.9988 9.06805 10.0011 9.06812 10.0011 16 15.9922 9.00098 9.87579 9.00098 9.87585 17 13.9982 8.82489 9.76587 8.82489 9.76587 18 13.9922 8.77881 9.66748 8.77930 9.66754 19 11.9979 8.63293 9.58008 8.63330 9.58008 20 11.9922 8.60107 9.50092 8.60107 9.50098 ***** Detected BTB Depth: 5 -------------BTB Size/Block Test (with 2B Block) (experimental)----------- (C/L) 1 2 4 8 16 1024 6148.17 6724.69 6571.77 6435.52 6344.13 2048 6168.58 12926.0 9606.84 8095.73 7302.97 3072 6376.94 15532.7 13621.3 8863.22 7626.80 4096 12396.6 16963.3 15642.7 14786.5 13994.0 5120 12362.2 17039.1 16406.2 15667.9 15344.7 6144 12703.5 17198.6 16632.0 16373.3 16123.1 7168 12800.3 17409.2 16968.4 16618.5 16372.2 8192 12992.1 17433.9 17035.4 17016.8 16827.6 9216 12843.1 17145.2 16780.6 16579.6 16456.2 10240 12707.9 16863.7 16578.7 16229.0 16112.3 11264 12699.3 16918.7 16593.7 16288.9 16121.5 12288 12789.0 16717.1 16431.3 16258.4 16139.1 13312 12759.0 16514.2 16411.1 16362.2 16312.8 14336 12706.5 16288.7 16391.8 16451.0 16476.9 15360 13035.4 16157.4 16405.7 16533.9 16588.9 16384 13043.2 16016.9 16398.7 16580.6 16674.4 -------------BTB Size/Block Test (with 4B Block) (experimental)----------- (C/L) 1 2 4 8 16 1024 264.023 804.527 1049.79 683.899 416.139 2048 265.023 1043.29 675.175 574.883 505.771 3072 275.288 2562.41 1500.19 1015.26 769.765 4096 352.332 4625.38 2968.40 1651.69 1041.37 5120 283.564 5844.50 5445.81 3117.66 2103.85 6144 312.398 7107.82 6149.47 4111.89 2962.06 7168 336.795 8064.73 7860.20 7307.39 6928.24 8192 572.915 8497.09 9377.14 9617.83 10041.7 9216 461.967 8333.70 8259.12 8121.38 8700.50 10240 704.641 7910.84 7615.05 7521.36 7325.21 11264 1756.18 7732.84 7229.29 6753.19 6942.88 12288 2151.87 7556.41 6900.63 6337.65 6027.35 13312 2176.12 7182.51 7118.60 6665.34 6434.96 14336 2958.22 6675.56 7319.78 7349.85 7380.02 15360 2959.07 6378.97 7515.93 7963.89 8199.74 16384 3218.15 5948.47 7700.15 8507.74 8915.43 -------------BTB Size/Block Test (with 8B Block) (experimental)----------- (C/L) 1 2 4 8 16 1024 334.020 286.019 328.019 272.273 271.148 2048 195.524 348.521 336.067 348.808 353.995 3072 325.939 342.040 421.930 335.044 256.499 4096 329.021 429.988 628.298 387.841 351.054 5120 343.545 1039.80 764.566 594.762 511.029 6144 196.167 1456.37 1084.24 835.281 689.377 7168 383.642 1986.17 2271.48 1801.00 1688.45 8192 207.524 3524.37 3372.08 2852.12 2593.44 9216 388.161 3759.08 3490.91 2788.36 2287.43 10240 261.652 4047.62 3599.93 2713.29 2244.40 11264 263.583 4181.11 3576.63 2306.92 1515.79 12288 299.898 4275.50 3552.51 1863.27 1096.54 13312 388.859 4085.66 3812.55 3116.93 2654.71 14336 665.717 3931.19 4081.00 4008.71 3975.25 15360 985.604 3748.40 4205.59 4337.54 4400.93 16384 2930.83 3579.06 4298.42 4602.84 4751.62 -------------BTB Size/Block Test (with 16B Block) (experimental)----------- (C/L) 1 2 4 8 16 1024 231.027 345.106 324.024 295.024 280.524 2048 227.526 241.040 272.653 231.152 229.590 3072 226.304 376.858 232.964 229.542 227.964 4096 233.027 320.547 328.898 283.212 230.587 5120 257.962 456.907 324.518 277.552 256.007 6144 357.372 687.195 472.030 363.825 320.232 7168 354.511 698.793 687.104 700.051 615.861 8192 466.777 729.966 607.630 527.931 497.584 9216 392.153 854.050 743.818 671.988 557.794 10240 245.466 1446.26 1122.75 760.854 572.307 11264 286.290 1541.74 1454.46 993.569 723.246 12288 417.944 1602.32 1543.38 958.762 655.175 13312 323.637 2087.31 1948.49 1570.23 1286.32 14336 324.970 2171.81 2240.90 2140.51 2003.37 15360 580.497 1978.55 2309.21 2336.96 2309.20 16384 466.789 1976.65 2386.33 2510.22 2572.17 -------------BTB Depth Test (with CMOVcc Instruction)---------------------- (Cycle) Penalty N/Min N/Max Y/Min Y/Max 01 - 7.16766 7.16846 7.16785 7.16968 02 - 7.16760 7.16956 7.16779 7.16882 03 - 7.16766 7.16882 7.16760 7.16766 04 - 7.16772 7.16888 7.16760 7.16937 05 - 7.16766 7.16876 7.16766 7.16876 06 - 7.16772 7.16821 7.16772 7.16821 07 - 7.16766 7.16864 7.16766 7.16925 08 - 7.16772 7.16772 7.16772 7.16931 09 - 7.16809 7.16815 7.16815 10.2796 10 - 7.16858 10.4006 7.16882 10.4006 11 30.7656 9.96454 10.1821 10.0915 10.0916 12 32.9971 9.91742 9.91742 9.83423 9.91742 13 30.8345 9.53955 9.53955 9.53955 9.69324 14 32.6638 9.50079 9.50079 9.35876 9.50159 15 31.5060 9.26807 9.46741 9.26746 9.37537 16 32.3320 9.18842 9.18872 9.12604 9.18878 17 30.8343 8.98145 8.98145 8.98138 8.98145 18 32.9919 9.00055 9.00055 8.94501 9.00055 19 28.8421 8.68567 8.84302 8.68518 8.84302 20 28.6646 8.60089 8.80066 8.60089 8.80219 ***** Detected BTB Depth: 10 -------------Return Address Stack Test------------------------------------- (Cycle) Time Penalty 01 8.00049 - 02 8.00049 - 03 8.00049 - 04 8.00049 - 05 8.00049 - 06 8.00049 - 07 8.00049 - 08 8.00049 - 09 8.00049 - 10 8.00049 - 11 8.00049 - 12 8.00049 - 13 8.00049 - 14 8.00049 - 15 8.00049 - 16 8.00049 - 17 9.17696 20.0000 18 10.2227 20.0000 19 11.1584 20.0000 20 12.0005 20.0000 21 12.7624 20.0000 22 13.4550 20.0000 23 14.0874 20.0000 24 14.6672 20.0000 ** RAS Depth: 16 -------------Memory Bandwidth Status--------------------------------------- PC100 PC133 PC800 PC2100 PC2700 i850 nForce Theory (MB/s) 800 1064 1600 2128 2656 3200 4256 This (%) 370.00 278.19 185.00 139.10 111.44 92.50 69.55 -------------Video Memory Bandwidth Status--------------------------------- PCI AGP 1x AGP 2x AGP 4x AGP 8x Theory (MB/s) 133 266 533 1064 2128 This (%) 114.58 57.29 28.59 14.32 7.16 -------------Memory Subsystem Brief Report--------------------------------- ******************** Cache Brief Information ******************** Capacity Line Size Way Policy L1 D-Cache 8KB 64-Byte 4 W-Through L2 Cache 512KB 128-Byte 8 W-Alloc L1 Data TLB 64-Entry (4KB Page) 2 - L2 Data TLB 0-Entry (4KB Page) 0 - BTB 10-History - - - RAS 16-Entry - - - ******************** L1 D-Cache Performance ********************* (Cycle) Read Write Copy Throughput 1.0151 1.9702 1.9541 Latency 2.0311 N/A 3.0013 ******************** L2 & Memory Performance ******************** Read Write Latency L2 Cache 26.937(B/c) 5.177(B/c) 18.3911(Cycle) Memory 2959.97(MB/s) 1227.57(MB/s) 169.24(ns) -------------Memory Test End-----------------------------------------------