|
E6600 at 3.4 GHz
This is an E6600 over-clocked to 3.4 GHz and memory running at 756
Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz CPU speed: 3405.69 MHz CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2 L1 cache size: 32 KB L2 cache size: unknown L1 cache line size: 64 bytes L2 cache line size: unknown Prime95 32-bit version 24.14, RdtscTiming=1 Best time for 512K FFT length: 7.493 ms. Best time for 640K FFT length: 10.170 ms. Best time for 768K FFT length: 12.538 ms. Best time for 896K FFT length: 14.989 ms. Best time for 1024K FFT length: 16.598 ms. Best time for 1280K FFT length: 21.167 ms. Best time for 1536K FFT length: 25.817 ms. Best time for 1792K FFT length: 30.717 ms. Best time for 2048K FFT length: 34.153 ms. Best time for 2560K FFT length: 45.048 ms. Best time for 3072K FFT length: 54.910 ms. Best time for 3584K FFT length: 66.383 ms. Best time for 4096K FFT length: 74.366 ms. Best time for 58 bit trial factors: 3.260 ms. Best time for 59 bit trial factors: 3.305 ms. Best time for 60 bit trial factors: 3.292 ms. Best time for 61 bit trial factors: 3.281 ms. Best time for 62 bit trial factors: 5.236 ms. Best time for 63 bit trial factors: 5.240 ms. Best time for 64 bit trial factors: 5.020 ms. Best time for 65 bit trial factors: 4.987 ms. Best time for 66 bit trial factors: 4.989 ms. Best time for 67 bit trial factors: 4.966 ms. |
A64 X2 Brisbane 4000+
2x 512MB DDR2-RAM 345 MHz 4-4-4-12 MSI K9A Linux x86 [CODE] AMD Athlon(tm) 64 X2 Dual Core Processor 4000+ CPU speed: 2758.66 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 32-bit version 24.14, RdtscTiming=1 Best time for 512K FFT length: 17.331 ms. Best time for 640K FFT length: 22.594 ms. Best time for 768K FFT length: 27.219 ms. Best time for 896K FFT length: 32.610 ms. Best time for 1024K FFT length: 37.174 ms. Best time for 1280K FFT length: 47.084 ms. Best time for 1536K FFT length: 56.963 ms. Best time for 1792K FFT length: 72.332 ms. Best time for 2048K FFT length: 78.394 ms. Best time for 2560K FFT length: 104.761 ms. Best time for 3072K FFT length: 127.795 ms. Best time for 3584K FFT length: 153.268 ms. Best time for 4096K FFT length: 174.397 ms. Best time for 58 bit trial factors: 4.128 ms. Best time for 59 bit trial factors: 4.127 ms. Best time for 60 bit trial factors: 4.123 ms. Best time for 61 bit trial factors: 4.130 ms. Best time for 62 bit trial factors: 7.792 ms. Best time for 63 bit trial factors: 7.799 ms. Best time for 64 bit trial factors: 10.101 ms. Best time for 65 bit trial factors: 9.983 ms. Best time for 66 bit trial factors: 10.029 ms. Best time for 67 bit trial factors: 9.947 ms. [/CODE] |
AMD Athlon(tm) 64 X2 Dual Core Processor 4000+
CPU speed: 2099.43 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 32-bit version 24.14, RdtscTiming=1 Best time for 512K FFT length: 22.858 ms. Best time for 640K FFT length: 29.512 ms. Best time for 768K FFT length: 35.708 ms. Best time for 896K FFT length: 42.833 ms. Best time for 1024K FFT length: 47.669 ms. Best time for 1280K FFT length: 60.634 ms. Best time for 1536K FFT length: 74.557 ms. Best time for 1792K FFT length: 90.509 ms. Best time for 2048K FFT length: 101.255 ms. Best time for 2560K FFT length: 134.332 ms. Best time for 3072K FFT length: 164.802 ms. Best time for 3584K FFT length: 199.418 ms. Best time for 4096K FFT length: 222.955 ms. Best time for 58 bit trial factors: 5.403 ms. Best time for 59 bit trial factors: 5.418 ms. Best time for 60 bit trial factors: 5.393 ms. Best time for 61 bit trial factors: 5.420 ms. Best time for 62 bit trial factors: 10.213 ms. Best time for 63 bit trial factors: 10.246 ms. Best time for 64 bit trial factors: 13.199 ms. Best time for 65 bit trial factors: 13.104 ms. Best time for 66 bit trial factors: 13.114 ms. Best time for 67 bit trial factors: 13.070 ms. |
Mac Mini (Core Duo), 1.83GHz, 1GB RAM, BootCamp with XP Pro SP2:
Genuine Intel(R) CPU 1400 @ 1.83GHz CPU speed: 1833.18 MHz CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2 L1 cache size: 32 KB L2 cache size: 2048 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes TLBS: 128 Prime95 32-bit version 24.14, RdtscTiming=1 Best time for 512K FFT length: 35.640 ms. Best time for 640K FFT length: 46.507 ms. Best time for 768K FFT length: 56.932 ms. Best time for 896K FFT length: 68.323 ms. Best time for 1024K FFT length: 75.902 ms. Best time for 1280K FFT length: 96.399 ms. Best time for 1536K FFT length: 117.667 ms. Best time for 1792K FFT length: 141.649 ms. Best time for 2048K FFT length: 157.615 ms. Best time for 2560K FFT length: 204.498 ms. Best time for 3072K FFT length: 248.543 ms. Best time for 3584K FFT length: 298.513 ms. Best time for 4096K FFT length: 333.532 ms. Best time for 58 bit trial factors: 7.162 ms. Best time for 59 bit trial factors: 7.273 ms. Best time for 60 bit trial factors: 7.262 ms. Best time for 61 bit trial factors: 7.163 ms. Best time for 62 bit trial factors: 10.152 ms. Best time for 63 bit trial factors: 10.238 ms. Best time for 64 bit trial factors: 17.466 ms. Best time for 65 bit trial factors: 17.303 ms. Best time for 66 bit trial factors: 17.335 ms. Best time for 67 bit trial factors: 17.393 ms. |
E6600 OC'd to 3.2G
CPU falsely detected 3.6GHz by Prime95. CPU-Z gives the right 3.2GHz
E6600 L627B005 at 3200MHz (8x400) G.Skill F2-6400CL4-1GBPK at 1:1 4-4-4-12 Asus P5B-Deluxe WinXP-32 Core temps between 60-65C under maximum load. [code]Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz CPU speed: 3599.98 MHz CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2 L1 cache size: 32 KB L2 cache size: unknown L1 cache line size: 64 bytes L2 cache line size: unknown Prime95 32-bit version 24.14, RdtscTiming=1 Best time for 512K FFT length: 7.948 ms. Best time for 640K FFT length: 10.768 ms. Best time for 768K FFT length: 13.249 ms. Best time for 896K FFT length: 15.855 ms. Best time for 1024K FFT length: 17.543 ms. Best time for 1280K FFT length: 22.340 ms. Best time for 1536K FFT length: 27.247 ms. Best time for 1792K FFT length: 32.355 ms. Best time for 2048K FFT length: 36.072 ms. Best time for 2560K FFT length: 47.538 ms. Best time for 3072K FFT length: 57.882 ms. Best time for 3584K FFT length: 70.023 ms. Best time for 4096K FFT length: 78.621 ms. Best time for 58 bit trial factors: 3.500 ms. Best time for 59 bit trial factors: 3.535 ms. Best time for 60 bit trial factors: 3.474 ms. Best time for 61 bit trial factors: 3.492 ms. Best time for 62 bit trial factors: 5.600 ms. Best time for 63 bit trial factors: 5.577 ms. Best time for 64 bit trial factors: 5.343 ms. Best time for 65 bit trial factors: 5.323 ms. Best time for 66 bit trial factors: 5.321 ms. Best time for 67 bit trial factors: 5.284 ms.[/code] |
AM2 3600+ (65nm), 2x512kB L2 cache, stock: 1900MHz
in various states of overclock: [code] AMD Athlon(tm) 64 X2 Dual Core Processor 3600+ CPU speed: 1908.76 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 64-bit version 24.14, RdtscTiming=1 Best time for 4K FFT length: 0.123 ms. Best time for 5K FFT length: 0.171 ms. Best time for 6K FFT length: 0.214 ms. Best time for 7K FFT length: 0.267 ms. Best time for 8K FFT length: 0.295 ms. Best time for 10K FFT length: 0.367 ms. Best time for 12K FFT length: 0.441 ms. Best time for 14K FFT length: 0.532 ms. Best time for 16K FFT length: 0.583 ms. Best time for 20K FFT length: 0.803 ms. Best time for 24K FFT length: 0.992 ms. Best time for 28K FFT length: 1.161 ms. Best time for 32K FFT length: 1.298 ms. Best time for 40K FFT length: 1.823 ms. Best time for 48K FFT length: 2.266 ms. Best time for 56K FFT length: 2.520 ms. Best time for 64K FFT length: 3.022 ms. Best time for 80K FFT length: 3.944 ms. Best time for 96K FFT length: 4.540 ms. Best time for 112K FFT length: 5.503 ms. Best time for 128K FFT length: 6.008 ms. Best time for 160K FFT length: 7.193 ms. Best time for 192K FFT length: 8.728 ms. Best time for 224K FFT length: 10.557 ms. Best time for 256K FFT length: 11.643 ms. Best time for 320K FFT length: 14.942 ms. Best time for 384K FFT length: 18.460 ms. Best time for 448K FFT length: 22.411 ms. Best time for 512K FFT length: 24.936 ms. Best time for 640K FFT length: 32.156 ms. Best time for 768K FFT length: 39.009 ms. Best time for 896K FFT length: 46.816 ms. Best time for 1024K FFT length: 52.002 ms. Best time for 1280K FFT length: 66.161 ms. Best time for 1536K FFT length: 81.412 ms. Best time for 1792K FFT length: 98.720 ms. Best time for 2048K FFT length: 110.033 ms. Best time for 2560K FFT length: 146.075 ms. Best time for 3072K FFT length: 179.702 ms. Best time for 3584K FFT length: 217.220 ms. Best time for 4096K FFT length: 241.674 ms. Best time for 5120K FFT length: 324.814 ms. Best time for 6144K FFT length: 397.984 ms. Best time for 7168K FFT length: 485.538 ms. Best time for 8192K FFT length: 556.949 ms. Best time for 10240K FFT length: 704.845 ms. Best time for 12288K FFT length: 864.885 ms. Best time for 14336K FFT length: 1047.672 ms. Best time for 16384K FFT length: 1197.928 ms. Best time for 20480K FFT length: 1612.652 ms. Best time for 24576K FFT length: 2013.053 ms. Best time for 28672K FFT length: 2463.071 ms. Best time for 32768K FFT length: 2833.110 ms. Best time for 58 bit trial factors: 3.986 ms. Best time for 59 bit trial factors: 3.985 ms. Best time for 60 bit trial factors: 4.235 ms. Best time for 61 bit trial factors: 4.372 ms. Best time for 62 bit trial factors: 5.181 ms. Best time for 63 bit trial factors: 5.575 ms. Best time for 64 bit trial factors: 7.194 ms. Best time for 65 bit trial factors: 8.505 ms. Best time for 66 bit trial factors: 8.460 ms. Best time for 67 bit trial factors: 8.444 ms. AMD Athlon(tm) 64 X2 Dual Core Processor 3600+ CPU speed: 2090.03 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 64-bit version 24.14, RdtscTiming=1 Best time for 4K FFT length: 0.112 ms. Best time for 5K FFT length: 0.156 ms. Best time for 6K FFT length: 0.193 ms. Best time for 7K FFT length: 0.244 ms. Best time for 8K FFT length: 0.270 ms. Best time for 10K FFT length: 0.333 ms. Best time for 12K FFT length: 0.403 ms. Best time for 14K FFT length: 0.491 ms. Best time for 16K FFT length: 0.532 ms. Best time for 20K FFT length: 0.735 ms. Best time for 24K FFT length: 0.904 ms. Best time for 28K FFT length: 1.059 ms. Best time for 32K FFT length: 1.183 ms. Best time for 40K FFT length: 1.666 ms. Best time for 48K FFT length: 2.073 ms. Best time for 56K FFT length: 2.308 ms. Best time for 64K FFT length: 2.762 ms. Best time for 80K FFT length: 3.605 ms. Best time for 96K FFT length: 4.143 ms. Best time for 112K FFT length: 5.052 ms. Best time for 128K FFT length: 5.897 ms. Best time for 160K FFT length: 6.537 ms. Best time for 192K FFT length: 7.969 ms. Best time for 224K FFT length: 9.621 ms. Best time for 256K FFT length: 10.632 ms. Best time for 320K FFT length: 13.641 ms. Best time for 384K FFT length: 16.868 ms. Best time for 448K FFT length: 20.470 ms. Best time for 512K FFT length: 22.794 ms. Best time for 640K FFT length: 29.422 ms. Best time for 768K FFT length: 35.677 ms. Best time for 896K FFT length: 42.761 ms. Best time for 1024K FFT length: 47.634 ms. Best time for 1280K FFT length: 60.563 ms. Best time for 1536K FFT length: 74.483 ms. Best time for 1792K FFT length: 90.322 ms. Best time for 2048K FFT length: 100.948 ms. Best time for 2560K FFT length: 133.724 ms. Best time for 3072K FFT length: 164.631 ms. Best time for 3584K FFT length: 198.673 ms. Best time for 4096K FFT length: 221.251 ms. Best time for 5120K FFT length: 297.774 ms. Best time for 6144K FFT length: 364.696 ms. Best time for 7168K FFT length: 444.786 ms. Best time for 8192K FFT length: 510.511 ms. Best time for 10240K FFT length: 645.568 ms. Best time for 12288K FFT length: 790.425 ms. Best time for 14336K FFT length: 959.701 ms. Best time for 16384K FFT length: 1098.557 ms. Best time for 20480K FFT length: 1476.747 ms. Best time for 24576K FFT length: 1841.349 ms. Best time for 28672K FFT length: 2261.181 ms. Best time for 32768K FFT length: 2595.958 ms. Best time for 58 bit trial factors: 3.652 ms. Best time for 59 bit trial factors: 3.645 ms. Best time for 60 bit trial factors: 3.876 ms. Best time for 61 bit trial factors: 3.996 ms. Best time for 62 bit trial factors: 4.732 ms. Best time for 63 bit trial factors: 5.103 ms. Best time for 64 bit trial factors: 6.583 ms. Best time for 65 bit trial factors: 7.806 ms. Best time for 66 bit trial factors: 7.749 ms. Best time for 67 bit trial factors: 7.718 ms. AMD Athlon(tm) 64 X2 Dual Core Processor 3600+ CPU speed: 2602.76 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 64-bit version 24.14, RdtscTiming=1 Best time for 4K FFT length: 0.091 ms. Best time for 5K FFT length: 0.125 ms. Best time for 6K FFT length: 0.157 ms. Best time for 7K FFT length: 0.197 ms. Best time for 8K FFT length: 0.217 ms. Best time for 10K FFT length: 0.269 ms. Best time for 12K FFT length: 0.324 ms. Best time for 14K FFT length: 0.390 ms. Best time for 16K FFT length: 0.427 ms. Best time for 20K FFT length: 0.606 ms. Best time for 24K FFT length: 0.711 ms. Best time for 28K FFT length: 0.852 ms. Best time for 32K FFT length: 0.950 ms. Best time for 40K FFT length: 1.339 ms. Best time for 48K FFT length: 1.673 ms. Best time for 56K FFT length: 1.863 ms. Best time for 64K FFT length: 2.235 ms. Best time for 80K FFT length: 2.928 ms. Best time for 96K FFT length: 3.385 ms. Best time for 112K FFT length: 4.134 ms. Best time for 128K FFT length: 4.523 ms. Best time for 160K FFT length: 5.291 ms. Best time for 192K FFT length: 6.435 ms. Best time for 224K FFT length: 7.774 ms. Best time for 256K FFT length: 8.582 ms. Best time for 320K FFT length: 11.002 ms. Best time for 384K FFT length: 13.632 ms. Best time for 448K FFT length: 16.538 ms. Best time for 512K FFT length: 18.420 ms. Best time for 640K FFT length: 23.777 ms. Best time for 768K FFT length: 28.788 ms. Best time for 896K FFT length: 34.564 ms. Best time for 1024K FFT length: 38.373 ms. Best time for 1280K FFT length: 48.797 ms. Best time for 1536K FFT length: 60.004 ms. Best time for 1792K FFT length: 72.760 ms. Best time for 2048K FFT length: 81.242 ms. Best time for 2560K FFT length: 108.669 ms. Best time for 3072K FFT length: 133.347 ms. Best time for 3584K FFT length: 161.308 ms. Best time for 4096K FFT length: 179.750 ms. Best time for 5120K FFT length: 240.675 ms. Best time for 6144K FFT length: 294.964 ms. Best time for 7168K FFT length: 360.931 ms. Best time for 8192K FFT length: 417.333 ms. Best time for 10240K FFT length: 525.032 ms. Best time for 12288K FFT length: 644.554 ms. Best time for 14336K FFT length: 781.722 ms. Best time for 16384K FFT length: 899.030 ms. Best time for 20480K FFT length: 1235.117 ms. Best time for 24576K FFT length: 1563.086 ms. Best time for 28672K FFT length: 1951.783 ms. Best time for 32768K FFT length: 2261.949 ms. Best time for 58 bit trial factors: 2.929 ms. Best time for 59 bit trial factors: 2.919 ms. Best time for 60 bit trial factors: 3.106 ms. Best time for 61 bit trial factors: 3.209 ms. Best time for 62 bit trial factors: 3.806 ms. Best time for 63 bit trial factors: 4.090 ms. Best time for 64 bit trial factors: 5.286 ms. Best time for 65 bit trial factors: 6.284 ms. Best time for 66 bit trial factors: 6.216 ms. Best time for 67 bit trial factors: 6.183 ms. AMD Athlon(tm) 64 X2 Dual Core Processor 3600+ CPU speed: 2697.76 MHz CPU features: RDTSC, CMOV, Prefetch, 3DNow!, MMX, SSE, SSE2 L1 cache size: 64 KB L2 cache size: 512 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes L1 TLBS: 32 L2 TLBS: 512 Prime95 64-bit version 24.14, RdtscTiming=1 Best time for 4K FFT length: 0.087 ms. Best time for 5K FFT length: 0.121 ms. Best time for 6K FFT length: 0.151 ms. Best time for 7K FFT length: 0.190 ms. Best time for 8K FFT length: 0.209 ms. Best time for 10K FFT length: 0.260 ms. Best time for 12K FFT length: 0.312 ms. Best time for 14K FFT length: 0.376 ms. Best time for 16K FFT length: 0.412 ms. Best time for 20K FFT length: 0.585 ms. Best time for 24K FFT length: 0.686 ms. Best time for 28K FFT length: 0.822 ms. Best time for 32K FFT length: 0.916 ms. Best time for 40K FFT length: 1.294 ms. Best time for 48K FFT length: 1.615 ms. Best time for 56K FFT length: 1.796 ms. Best time for 64K FFT length: 2.156 ms. Best time for 80K FFT length: 2.829 ms. Best time for 96K FFT length: 3.259 ms. Best time for 112K FFT length: 3.989 ms. Best time for 128K FFT length: 4.367 ms. Best time for 160K FFT length: 5.108 ms. Best time for 192K FFT length: 6.202 ms. Best time for 224K FFT length: 7.508 ms. Best time for 256K FFT length: 8.286 ms. Best time for 320K FFT length: 10.614 ms. Best time for 384K FFT length: 13.112 ms. Best time for 448K FFT length: 15.957 ms. Best time for 512K FFT length: 17.769 ms. Best time for 640K FFT length: 22.942 ms. Best time for 768K FFT length: 27.801 ms. Best time for 896K FFT length: 33.348 ms. Best time for 1024K FFT length: 36.994 ms. Best time for 1280K FFT length: 47.062 ms. Best time for 1536K FFT length: 57.893 ms. Best time for 1792K FFT length: 70.278 ms. Best time for 2048K FFT length: 78.441 ms. Best time for 2560K FFT length: 104.747 ms. Best time for 3072K FFT length: 128.548 ms. Best time for 3584K FFT length: 155.564 ms. Best time for 4096K FFT length: 173.504 ms. Best time for 5120K FFT length: 230.990 ms. Best time for 6144K FFT length: 284.428 ms. Best time for 7168K FFT length: 347.070 ms. Best time for 8192K FFT length: 402.924 ms. Best time for 10240K FFT length: 507.182 ms. Best time for 12288K FFT length: 621.027 ms. Best time for 14336K FFT length: 754.809 ms. Best time for 16384K FFT length: 869.236 ms. Best time for 20480K FFT length: 1190.467 ms. Best time for 24576K FFT length: 1508.291 ms. Best time for 28672K FFT length: 1880.352 ms. Best time for 32768K FFT length: 2180.548 ms. Best time for 58 bit trial factors: 2.826 ms. Best time for 59 bit trial factors: 2.819 ms. Best time for 60 bit trial factors: 2.999 ms. Best time for 61 bit trial factors: 3.090 ms. Best time for 62 bit trial factors: 3.661 ms. Best time for 63 bit trial factors: 3.947 ms. Best time for 64 bit trial factors: 5.089 ms. Best time for 65 bit trial factors: 6.062 ms. Best time for 66 bit trial factors: 5.988 ms. Best time for 67 bit trial factors: 5.997 ms. [/code] |
that chip can be purchased for 65usd now.
|
prime95 on a 8 cores Xeon 3 GHz machine. Problem w
Here are the performance results of prime95 25.2 on a IBM xSeries [URL="http://www-07.ibm.com/servers/eserver/sg/xseries/x460.html"]x460[/URL] 4 Chips 8 cores.
[B]It seems that prime95 does not correctly recognizes the 8 cores.[/B] I do not see 8 threads on 8 cores in the results. Why prime95 does not use the same number of threads as there are cores ? I've tried to say 8 "worker threads" and only 1 thread per core in the configuration (local.txt: WorkerThreads=8 ; ThreadsPerTest=1) but the benchmark does not seem to use it. Help ! :help: [COLOR="Red"]After first post:[/COLOR]Hum? Seems I was lost by prime95 saying n (1 to 4) physical CPUs though Linux talks of 8 processors. Is prime95 smart enough to see that there are 2 cores per CPU ? and then run 2 threads per CPU (meaning as many threads as used cores) ? Is prime95 able to handle machines with more than 2 cores ? [COLOR="Red"]Some more comment:[/COLOR]Also, prime95 talks about: "4 hyperthreaded cores" here below. There are 4 CPUs with 2 cores each. Not 4 cores with hyperthreading ! (I could run the machine with HT on and thus Linux should see 16 processors ....). If I have time, I'll try to build a graph. With a quick glance with FFT 4096 the scalability seems not bad. T. [CODE]Intel(R) Xeon(TM) CPU 3.00GHz CPU speed: 3002.34 MHz, 4 hyperthreaded cores CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2 L1 cache size: 16 KB L2 cache size: 2048 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes TLBS: 64 Prime95 32-bit version 25.2, RdtscTiming=1 Best time for 768K FFT length: 25.933 ms. Best time for 896K FFT length: 31.635 ms. Best time for 1024K FFT length: 35.682 ms. Best time for 1280K FFT length: 44.054 ms. Best time for 1536K FFT length: 53.208 ms. Best time for 1792K FFT length: 64.129 ms. Best time for 2048K FFT length: 72.330 ms. Best time for 2560K FFT length: 93.694 ms. Best time for 3072K FFT length: 112.738 ms. Best time for 3584K FFT length: 136.003 ms. Best time for 4096K FFT length: 151.340 ms. Best time for 5120K FFT length: 190.267 ms. Best time for 6144K FFT length: 236.435 ms. Best time for 7168K FFT length: 284.124 ms. Best time for 8192K FFT length: 313.464 ms. Timing FFTs using 2 threads on 1 physical CPUs. Best time for 768K FFT length: 15.987 ms. Best time for 896K FFT length: 18.237 ms. Best time for 1024K FFT length: 27.179 ms. Best time for 1280K FFT length: 23.619 ms. Best time for 1536K FFT length: 28.461 ms. Best time for 1792K FFT length: 33.976 ms. Best time for 2048K FFT length: 38.330 ms. Best time for 2560K FFT length: 49.889 ms. Best time for 3072K FFT length: 60.346 ms. Best time for 3584K FFT length: 72.050 ms. Best time for 4096K FFT length: 79.673 ms. Best time for 5120K FFT length: 100.437 ms. Best time for 6144K FFT length: 127.995 ms. Best time for 7168K FFT length: 154.474 ms. Best time for 8192K FFT length: 169.825 ms. Timing FFTs using 4 threads on 2 physical CPUs. Best time for 768K FFT length: 14.587 ms. Best time for 896K FFT length: 16.288 ms. Best time for 1024K FFT length: 24.645 ms. Best time for 1280K FFT length: 17.331 ms. Best time for 1536K FFT length: 20.287 ms. Best time for 1792K FFT length: 23.178 ms. Best time for 2048K FFT length: 25.840 ms. Best time for 2560K FFT length: 32.137 ms. Best time for 3072K FFT length: 38.339 ms. Best time for 3584K FFT length: 44.631 ms. Best time for 4096K FFT length: 50.332 ms. Best time for 5120K FFT length: 60.550 ms. Best time for 6144K FFT length: 80.565 ms. Best time for 7168K FFT length: 93.462 ms. Best time for 8192K FFT length: 105.859 ms. Timing FFTs using 6 threads on 3 physical CPUs. Best time for 768K FFT length: 14.769 ms. Best time for 896K FFT length: 15.717 ms. Best time for 1024K FFT length: 24.664 ms. Best time for 1280K FFT length: 16.923 ms. Best time for 1536K FFT length: 20.159 ms. Best time for 1792K FFT length: 22.701 ms. Best time for 2048K FFT length: 25.457 ms. Best time for 2560K FFT length: 31.355 ms. Best time for 3072K FFT length: 39.216 ms. Best time for 3584K FFT length: 51.312 ms. Best time for 4096K FFT length: 52.135 ms. Best time for 5120K FFT length: 63.983 ms. Best time for 6144K FFT length: 87.370 ms. Best time for 7168K FFT length: 94.171 ms. Best time for 8192K FFT length: 115.765 ms. Timing FFTs using 8 threads on 4 physical CPUs. Best time for 768K FFT length: 13.669 ms. Best time for 896K FFT length: 15.957 ms. Best time for 1024K FFT length: 25.093 ms. Best time for 1280K FFT length: 18.251 ms. Best time for 1536K FFT length: 20.589 ms. Best time for 1792K FFT length: 22.798 ms. Best time for 2048K FFT length: 29.553 ms. Best time for 2560K FFT length: 34.499 ms. Best time for 3072K FFT length: 41.285 ms. Best time for 3584K FFT length: 44.560 ms. Best time for 4096K FFT length: 45.899 ms. Best time for 5120K FFT length: 58.874 ms. Best time for 6144K FFT length: 78.755 ms. Best time for 7168K FFT length: 88.255 ms. Best time for 8192K FFT length: 103.105 ms. Best time for 58 bit trial factors: 9.167 ms. Best time for 59 bit trial factors: 9.145 ms. Best time for 60 bit trial factors: 9.134 ms. Best time for 61 bit trial factors: 9.071 ms. Best time for 62 bit trial factors: 12.832 ms. Best time for 63 bit trial factors: 12.860 ms. Best time for 64 bit trial factors: 15.039 ms. Best time for 65 bit trial factors: 14.950 ms. Best time for 66 bit trial factors: 14.869 ms. Best time for 67 bit trial factors: 14.814 ms.[/CODE] |
prime 25.3 on Linux ia32 with 8 cores Xeon 3GHz
Here are the results with prime 25.3 on the same machine as previously (8 fast Xeon cores). It's nearly the same as compared with prime 25.2 .
About scalability: - with 2 threads running on 1 CPUs (= 2 cores), the scalability is about 1.9 instead of the theoretical 2 . Quite good ! - with 4 threads running on 2 CPUs (= 4 cores), the scalability is about 3 instead of the theoretical 4 . Not so good. Using more of 4 threads is a wast of prower, since the scalability is ... about 3 instead of 6 or 8 ! T. Intel(R) Xeon(TM) CPU 3.00GHz CPU speed: 3001.30 MHz, 4 hyperthreaded cores CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2 L1 cache size: 16 KB L2 cache size: 2048 KB L1 cache line size: 64 bytes L2 cache line size: 64 bytes TLBS: 64 Prime95 32-bit version 25.3, RdtscTiming=1- Best time for 768K FFT length: 25.830 ms. Best time for 896K FFT length: 31.457 ms. Best time for 1024K FFT length: 35.662 ms. Best time for 1280K FFT length: 44.058 ms. Best time for 1536K FFT length: 53.176 ms. Best time for 1792K FFT length: 63.989 ms. Best time for 2048K FFT length: 70.696 ms. Best time for 2560K FFT length: 93.563 ms. Best time for 3072K FFT length: 112.445 ms. Best time for 3584K FFT length: 135.971 ms. Best time for 4096K FFT length: 151.438 ms. Best time for 5120K FFT length: 190.948 ms. Best time for 6144K FFT length: 236.563 ms. Best time for 7168K FFT length: 287.465 ms. Best time for 8192K FFT length: 314.891 ms. Timing FFTs using 2 threads on 1 physical CPUs. Best time for 768K FFT length: 15.969 ms. Best time for 896K FFT length: 18.335 ms. Best time for 1024K FFT length: 27.416 ms. Best time for 1280K FFT length: 23.626 ms. Best time for 1536K FFT length: 28.379 ms. Best time for 1792K FFT length: 33.963 ms. Best time for 2048K FFT length: 38.222 ms. Best time for 2560K FFT length: 50.059 ms. Best time for 3072K FFT length: 60.755 ms. Best time for 3584K FFT length: 73.396 ms. Best time for 4096K FFT length: 79.812 ms. Best time for 5120K FFT length: 100.480 ms. Best time for 6144K FFT length: 129.827 ms. Best time for 7168K FFT length: 153.948 ms. Best time for 8192K FFT length: 169.709 ms. Timing FFTs using 4 threads on 2 physical CPUs. Best time for 768K FFT length: 14.534 ms. Best time for 896K FFT length: 16.443 ms. Best time for 1024K FFT length: 24.933 ms. Best time for 1280K FFT length: 17.339 ms. Best time for 1536K FFT length: 20.363 ms. Best time for 1792K FFT length: 30.280 ms. Best time for 2048K FFT length: 25.979 ms. Best time for 2560K FFT length: 32.147 ms. Best time for 3072K FFT length: 38.287 ms. Best time for 3584K FFT length: 44.628 ms. Best time for 4096K FFT length: 50.379 ms. Best time for 5120K FFT length: 60.535 ms. Best time for 6144K FFT length: 80.425 ms. Best time for 7168K FFT length: 93.126 ms. Best time for 8192K FFT length: 105.730 ms. Timing FFTs using 6 threads on 3 physical CPUs. Best time for 768K FFT length: 14.756 ms. Best time for 896K FFT length: 19.971 ms. Best time for 1024K FFT length: 24.923 ms. Best time for 1280K FFT length: 16.992 ms. Best time for 1536K FFT length: 20.147 ms. Best time for 1792K FFT length: 22.643 ms. Best time for 2048K FFT length: 25.412 ms. Best time for 2560K FFT length: 31.385 ms. Best time for 3072K FFT length: 39.171 ms. Best time for 3584K FFT length: 46.995 ms. Best time for 4096K FFT length: 53.629 ms. Best time for 5120K FFT length: 63.910 ms. Best time for 6144K FFT length: 102.183 ms. Best time for 7168K FFT length: 94.961 ms. Best time for 8192K FFT length: 104.996 ms. Timing FFTs using 8 threads on 4 physical CPUs. Best time for 768K FFT length: 17.253 ms. Best time for 896K FFT length: 18.371 ms. Best time for 1024K FFT length: 25.337 ms. Best time for 1280K FFT length: 15.121 ms. Best time for 1536K FFT length: 19.383 ms. Best time for 1792K FFT length: 23.510 ms. Best time for 2048K FFT length: 26.952 ms. Best time for 2560K FFT length: 33.292 ms. Best time for 3072K FFT length: 34.955 ms. Best time for 3584K FFT length: 51.667 ms. Best time for 4096K FFT length: 49.697 ms. Best time for 5120K FFT length: 61.351 ms. Best time for 6144K FFT length: 78.580 ms. Best time for 7168K FFT length: 95.441 ms. Best time for 8192K FFT length: 106.943 ms. Best time for 58 bit trial factors: 9.162 ms. Best time for 59 bit trial factors: 9.085 ms. Best time for 60 bit trial factors: 9.066 ms. Best time for 61 bit trial factors: 9.060 ms. Best time for 62 bit trial factors: 12.926 ms. Best time for 63 bit trial factors: 12.936 ms. Best time for 64 bit trial factors: 15.043 ms. Best time for 65 bit trial factors: 14.929 ms. Best time for 66 bit trial factors: 15.200 ms. Best time for 67 bit trial factors: 15.039 ms. |
Comparison with Glucas
Here are data that enable to compare the scalability of prime95 with another multi-threaded FFT/LLT: Glucas.
Done with a >10Mdigits exponent. Between parenthesis: scalability compared to Glucas with no thread at all. With no thread, Glucas takes 0.1628 sec/iter . With 1 thread, Glucas takes 0.2091 sec/iter . Scalability is: 1 .(0.78) With 2 threads, Glucas takes 0.1086 sec/iter . Scalability is: 1.93 .(1.5) With 4 threads, Glucas takes 0.0651 sec/iter . Scalability is: 3.21 .(2.5) With 6 threads, Glucas takes 0.0501 sec/iter . Scalability is: 4.17 .(3.25) With 8 threads, Glucas takes 0.0415 sec/iter . Scalability is: 5.04 .(3.92) Conclusions: Glucas is more scalable than prime95 v25.3 . Mainly when using more that 4 cores. Compared to Glucas compiled with no thread at all, Glucas with 8 threads is only 4 times faster. Using 8 Glucas no-thread instead of 1 Glucas 8-threads is 2 times faster. When verifying a Mersenne prime candidate, it is worth to use Glucas multi-threaded, compared to prime95 multi-threaded. There is room for improvements for the multi-threading of prime95 ! T. |
Comparison with Glucas
Hum,
Maybe I'm not comparing the right things. I used 2 versions of Glucas: one compiled with Multi-Threading and one without M-T. But I used only one version of prime95 25.3 : about the prime95 benchmark, I don't know if the first measure is done with a library of prime95 that is Multi-Threaded or not ... If prime95 is able to use a non M-T library, then prime95 is faster than Glucas when using 4 threads on 4 cores (scalability of ~3 compared to 2.5) but slower when using 8 threads on 8 cores (scalability of ~3 compared to ~4). BTW, George, would it be possible to add the possibility to bind prime95 threads on a set of processors, in order to reduce the NUMA effect when using 4 cores about 8 ? T. |
| All times are UTC. The time now is 22:38. |
Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.