mersenneforum.org - Perpetual benchmark thread...

mersenneforum.org (https://www.mersenneforum.org/index.php)

- Hardware (https://www.mersenneforum.org/forumdisplay.php?f=9)

- - Perpetual benchmark thread... (https://www.mersenneforum.org/showthread.php?t=59)

Thanks, I finally ended up going with a Q6600. I knew that this was a well tested processor, and would be stable.
I did, however decide to buy [B]DDR3[/B]!

DDR3 is not currently any faster than DDR2. Mine is 1066, and it is actually supposed to be slower than 1066 DDR2, and it's a lot more expensive.
I knew this before buying, but I know the next computer I build will use DDR3, and I don't want to be stuck with old DDR2.
The other benefit to DDR3 is that it is more power efficient. Of course, if I was that concerned about power, I wouldn't be running mprime!

Processor: [B]Q6600[/B]
Motherboard: [B]ASUS P5K3 Deluxe[/B]
OS: [B]XP 64-bit[/B]
Memory: [B]2GB DDR3[/B]
mprime: [B]24.14 mprime 64-bit[/B]

The first results here are with just one core running (the other 3 are idle):
[code]
Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
CPU speed: 2404.88 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 64-bit version 24.14, RdtscTiming=1
Best time for 512K FFT length: 10.552 ms.
Best time for 640K FFT length: 14.150 ms.
Best time for 768K FFT length: 17.456 ms.
Best time for 896K FFT length: 20.819 ms.
Best time for 1024K FFT length: 23.112 ms.
Best time for 1280K FFT length: 29.214 ms.
Best time for 1536K FFT length: 35.793 ms.
Best time for 1792K FFT length: 42.666 ms.
Best time for 2048K FFT length: 47.319 ms.
Best time for 2560K FFT length: 62.204 ms.
Best time for 3072K FFT length: 76.466 ms.
Best time for 3584K FFT length: 91.892 ms.
Best time for 4096K FFT length: 103.070 ms.
Best time for 58 bit trial factors: 3.728 ms.
Best time for 59 bit trial factors: 3.658 ms.
Best time for 60 bit trial factors: 4.221 ms.
Best time for 61 bit trial factors: 4.265 ms.
Best time for 62 bit trial factors: 5.034 ms.
Best time for 63 bit trial factors: 6.314 ms.
Best time for 64 bit trial factors: 6.651 ms.
Best time for 65 bit trial factors: 7.299 ms.
Best time for 66 bit trial factors: 7.229 ms.
Best time for 67 bit trial factors: 7.220 ms.[/code]And here is the results when the other 3 cores are also running mprime:
[code]
Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
CPU speed: 2404.96 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 64-bit version 24.14, RdtscTiming=1
Best time for 512K FFT length: 11.066 ms.
Best time for 640K FFT length: 15.205 ms.
Best time for 768K FFT length: 20.778 ms.
Best time for 896K FFT length: 24.465 ms.
Best time for 1024K FFT length: 27.068 ms.
Best time for 1280K FFT length: 34.283 ms.
Best time for 1536K FFT length: 41.638 ms.
Best time for 1792K FFT length: 49.605 ms.
Best time for 2048K FFT length: 55.883 ms.
Best time for 2560K FFT length: 74.161 ms.
Best time for 3072K FFT length: 91.740 ms.
Best time for 3584K FFT length: 109.236 ms.
Best time for 4096K FFT length: 122.833 ms.
Best time for 58 bit trial factors: 3.824 ms.
Best time for 59 bit trial factors: 3.785 ms.
Best time for 60 bit trial factors: 4.152 ms.
Best time for 61 bit trial factors: 4.300 ms.
Best time for 62 bit trial factors: 5.085 ms.
Best time for 63 bit trial factors: 6.359 ms.
Best time for 64 bit trial factors: 6.705 ms.
Best time for 65 bit trial factors: 7.355 ms.
Best time for 66 bit trial factors: 7.332 ms.
Best time for 67 bit trial factors: 7.294 ms.
[/code]The first day after setting up the computer, my heatsink wasn't seated right. I ran the benchmarks then, and the single core marks were about the same, but marks with all cores running were terrible.
Even though the computer claimed it was full speed, I think that something was running slower because of the heat.
After placing the heatsink again, I was very pleased :)

Harpertown 2x 4 cores 3 GHz

Here are the result of Prime95 v25.6 on a [B]2x 4cores Harpertown 3 GHz.[/B]
[B]8 threads : 10 iterations at 8192K FFT length. Best time: 53.507 ms.[/B]
Quite faste !
But the sacalability is bad...
Tony

[CODE]
Timing 46 iterations at 768K FFT length. Best time: 14.790 ms.
Timing 40 iterations at 896K FFT length. Best time: 17.875 ms.
Timing 35 iterations at 1024K FFT length. Best time: 20.150 ms.
Timing 28 iterations at 1280K FFT length. Best time: 25.699 ms.
Timing 23 iterations at 1536K FFT length. Best time: 31.663 ms.
Timing 20 iterations at 1792K FFT length. Best time: 37.815 ms.
Timing 17 iterations at 2048K FFT length. Best time: 42.110 ms.
Timing 14 iterations at 2560K FFT length. Best time: 55.411 ms.
Timing 11 iterations at 3072K FFT length. Best time: 67.829 ms.
Timing 10 iterations at 3584K FFT length. Best time: 80.792 ms.
Timing 10 iterations at 4096K FFT length. Best time: 90.441 ms.
Timing 10 iterations at 5120K FFT length. Best time: 114.871 ms.
Timing 10 iterations at 6144K FFT length. Best time: 139.089 ms.
Timing 10 iterations at 7168K FFT length. Best time: 168.121 ms.
Timing 10 iterations at 8192K FFT length. Best time: 184.219 ms.
Timing FFTs using 2 threads.
Timing 46 iterations at 768K FFT length. Best time: 11.824 ms.
Timing 40 iterations at 896K FFT length. Best time: 13.567 ms.
Timing 35 iterations at 1024K FFT length. Best time: 17.818 ms.
Timing 28 iterations at 1280K FFT length. Best time: 17.564 ms.
Timing 23 iterations at 1536K FFT length. Best time: 21.023 ms.
Timing 20 iterations at 1792K FFT length. Best time: 24.737 ms.
Timing 17 iterations at 2048K FFT length. Best time: 27.571 ms.
Timing 14 iterations at 2560K FFT length. Best time: 35.670 ms.
Timing 11 iterations at 3072K FFT length. Best time: 43.497 ms.
Timing 10 iterations at 3584K FFT length. Best time: 51.217 ms.
Timing 10 iterations at 4096K FFT length. Best time: 57.611 ms.
Timing 10 iterations at 5120K FFT length. Best time: 72.203 ms.
Timing 10 iterations at 6144K FFT length. Best time: 87.038 ms.
Timing 10 iterations at 7168K FFT length. Best time: 104.010 ms.
Timing 10 iterations at 8192K FFT length. Best time: 115.174 ms.
Timing FFTs using 3 threads.
Timing 46 iterations at 768K FFT length. Best time: 9.450 ms.
Timing 40 iterations at 896K FFT length. Best time: 10.031 ms.
Timing 35 iterations at 1024K FFT length. Best time: 16.658 ms.
Timing 28 iterations at 1280K FFT length. Best time: 12.628 ms.
Timing 23 iterations at 1536K FFT length. Best time: 15.108 ms.
Timing 20 iterations at 1792K FFT length. Best time: 17.742 ms.
Timing 17 iterations at 2048K FFT length. Best time: 19.906 ms.
Timing 14 iterations at 2560K FFT length. Best time: 25.712 ms.
Timing 11 iterations at 3072K FFT length. Best time: 31.276 ms.
Timing 10 iterations at 3584K FFT length. Best time: 36.661 ms.
Timing 10 iterations at 4096K FFT length. Best time: 41.356 ms.
Timing 10 iterations at 5120K FFT length. Best time: 51.443 ms.
Timing 10 iterations at 6144K FFT length. Best time: 62.442 ms.
Timing 10 iterations at 7168K FFT length. Best time: 74.284 ms.
Timing 10 iterations at 8192K FFT length. Best time: 82.750 ms.
Timing FFTs using 4 threads.
Timing 46 iterations at 768K FFT length. Best time: 10.110 ms.
Timing 40 iterations at 896K FFT length. Best time: 11.184 ms.
Timing 35 iterations at 1024K FFT length. Best time: 17.847 ms.
Timing 28 iterations at 1280K FFT length. Best time: 11.596 ms.
Timing 23 iterations at 1536K FFT length. Best time: 13.311 ms.
Timing 20 iterations at 1792K FFT length. Best time: 15.079 ms.
Timing 17 iterations at 2048K FFT length. Best time: 16.794 ms.
Timing 14 iterations at 2560K FFT length. Best time: 20.420 ms.
Timing 11 iterations at 3072K FFT length. Best time: 24.718 ms.
Timing 10 iterations at 3584K FFT length. Best time: 28.857 ms.
Timing 10 iterations at 4096K FFT length. Best time: 32.858 ms.
Timing 10 iterations at 5120K FFT length. Best time: 40.663 ms.
Timing 10 iterations at 6144K FFT length. Best time: 49.474 ms.
Timing 10 iterations at 7168K FFT length. Best time: 59.282 ms.
Timing 10 iterations at 8192K FFT length. Best time: 66.128 ms.
Timing FFTs using 5 threads.
Timing 46 iterations at 768K FFT length. Best time: 9.597 ms.
Timing 40 iterations at 896K FFT length. Best time: 10.611 ms.
Timing 35 iterations at 1024K FFT length. Best time: 16.974 ms.
Timing 28 iterations at 1280K FFT length. Best time: 10.699 ms.
Timing 23 iterations at 1536K FFT length. Best time: 12.479 ms.
Timing 20 iterations at 1792K FFT length. Best time: 14.353 ms.
Timing 17 iterations at 2048K FFT length. Best time: 16.156 ms.
Timing 14 iterations at 2560K FFT length. Best time: 19.853 ms.
Timing 11 iterations at 3072K FFT length. Best time: 23.339 ms.
Timing 10 iterations at 3584K FFT length. Best time: 26.746 ms.
Timing 10 iterations at 4096K FFT length. Best time: 30.161 ms.
Timing 10 iterations at 5120K FFT length. Best time: 36.786 ms.
Timing 10 iterations at 6144K FFT length. Best time: 43.890 ms.
Timing 10 iterations at 7168K FFT length. Best time: 51.553 ms.
Timing 10 iterations at 8192K FFT length. Best time: 58.241 ms.
Timing FFTs using 6 threads.
Timing 46 iterations at 768K FFT length. Best time: 9.717 ms.
Timing 40 iterations at 896K FFT length. Best time: 10.817 ms.
Timing 35 iterations at 1024K FFT length. Best time: 17.346 ms.
Timing 28 iterations at 1280K FFT length. Best time: 10.876 ms.
Timing 23 iterations at 1536K FFT length. Best time: 12.451 ms.
Timing 20 iterations at 1792K FFT length. Best time: 14.058 ms.
Timing 17 iterations at 2048K FFT length. Best time: 15.570 ms.
Timing 14 iterations at 2560K FFT length. Best time: 18.771 ms.
Timing 11 iterations at 3072K FFT length. Best time: 22.162 ms.
Timing 10 iterations at 3584K FFT length. Best time: 25.561 ms.
Timing 10 iterations at 4096K FFT length. Best time: 28.934 ms.
Timing 10 iterations at 5120K FFT length. Best time: 35.466 ms.
Timing 10 iterations at 6144K FFT length. Best time: 42.173 ms.
Timing 10 iterations at 7168K FFT length. Best time: 49.475 ms.
Timing 10 iterations at 8192K FFT length. Best time: 55.877 ms.
Timing FFTs using 7 threads.
Timing 46 iterations at 768K FFT length. Best time: 9.207 ms.
Timing 40 iterations at 896K FFT length. Best time: 10.159 ms.
Timing 35 iterations at 1024K FFT length. Best time: 16.613 ms.
Timing 28 iterations at 1280K FFT length. Best time: 10.212 ms.
Timing 23 iterations at 1536K FFT length. Best time: 11.783 ms.
Timing 20 iterations at 1792K FFT length. Best time: 13.438 ms.
Timing 17 iterations at 2048K FFT length. Best time: 15.042 ms.
Timing 14 iterations at 2560K FFT length. Best time: 18.366 ms.
Timing 11 iterations at 3072K FFT length. Best time: 21.488 ms.
Timing 10 iterations at 3584K FFT length. Best time: 24.684 ms.
Timing 10 iterations at 4096K FFT length. Best time: 27.880 ms.
Timing 10 iterations at 5120K FFT length. Best time: 34.184 ms.
Timing 10 iterations at 6144K FFT length. Best time: 40.641 ms.
Timing 10 iterations at 7168K FFT length. Best time: 47.332 ms.
Timing 10 iterations at 8192K FFT length. Best time: 53.701 ms.
Timing FFTs using 8 threads.
Timing 46 iterations at 768K FFT length. Best time: 9.289 ms.
Timing 40 iterations at 896K FFT length. Best time: 10.281 ms.
Timing 35 iterations at 1024K FFT length. Best time: 16.780 ms.
Timing 28 iterations at 1280K FFT length. Best time: 10.208 ms.
Timing 23 iterations at 1536K FFT length. Best time: 11.738 ms.
Timing 20 iterations at 1792K FFT length. Best time: 13.221 ms.
Timing 17 iterations at 2048K FFT length. Best time: 14.675 ms.
Timing 14 iterations at 2560K FFT length. Best time: 17.682 ms.
Timing 11 iterations at 3072K FFT length. Best time: 20.911 ms.
Timing 10 iterations at 3584K FFT length. Best time: 24.236 ms.
Timing 10 iterations at 4096K FFT length. Best time: 27.492 ms.
Timing 10 iterations at 5120K FFT length. Best time: 33.691 ms.
Timing 10 iterations at 6144K FFT length. Best time: 40.195 ms.
Timing 10 iterations at 7168K FFT length. Best time: 47.360 ms.
Timing 10 iterations at 8192K FFT length. Best time: 53.507 ms.
[Timing trial factoring of M35000011 with 58 bit length factors. Best time: 3.035 ms.
Timing trial factoring of M35000011 with 59 bit length factors. Best time: 3.026 ms.
Timing trial factoring of M35000011 with 60 bit length factors. Best time: 3.352 ms.
Timing trial factoring of M35000011 with 61 bit length factors. Best time: 3.660 ms.
Timing trial factoring of M35000011 with 62 bit length factors. Best time: 4.166 ms.
Timing trial factoring of M35000011 with 63 bit length factors. Best time: 5.368 ms.
Timing trial factoring of M35000011 with 64 bit length factors. Best time: 5.726 ms.
Timing trial factoring of M35000011 with 65 bit length factors. Best time: 6.116 ms.
Timing trial factoring of M35000011 with 66 bit length factors. Best time: 6.075 ms.
Timing trial factoring of M35000011 with 67 bit length factors. Best time: 6.031 ms.[/CODE]

[quote=T.Rex;142322]Here are the result of Prime95 v25.6 on a [B]2x 4cores Harpertown 3 GHz.[/B]
[B]8 threads : 10 iterations at 8192K FFT length. Best time: 53.507 ms.[/B]
Quite faste !
But the sacalability is bad...
Tony[/quote]

How do you think that v25.6 would scale across [URL="http://www.techchee.com/2008/09/04/blue-waters-worlds-first-petascale-supercomputer-with-processor-of-200000-cores-and-cost-around-208-million/"]200,00 cores?[/URL]

That computer is being built here in my town, and I have some friends that work at NCSA. I should ask them about the possibility of giving mprime a test when Blue Waters comes online in 2011, although I kind of doubt any of them would have any say in that. :grin:

[QUOTE=uigrad;142335]How do you think that v25.6 would scale across [URL="http://www.techchee.com/2008/09/04/blue-waters-worlds-first-petascale-supercomputer-with-processor-of-200000-cores-and-cost-around-208-million/"]200,000 cores?[/URL] [/QUOTE]

The performance would be terrible! Each iteration requires intercore communication thus any latency becomes a real problem. Even the addition of 1ms would be enough to wreck the parallelism gains of any extra cores. Only SMP systems or limited hop NUMA systems are going to be of any use based on the current programs. The chunks of work simply aren't of sufficient duration to perform outside of the box.

The good news is there are plenty of eight core CPUs coming out over then next few years so there'll be plenty of 16 or 32 active threads with single hop options for us to toy with.

It seems we will have to wait until at least H2 2009 before 8-core chips become publicly available. Intel isn't releasing its "Beckton" (also called "Nehalem-EX") processor until then, and I don't think any other company is releasing an 8-core chip earlier than that. Even so, the "Beckton" chip is intended for servers, and we will probably have to wait several more months before the desktop versions become available.

[quote=ixfd64;142460]It seems we will have to wait until at least H2 2009 before 8-core chips become publicly available. Intel isn't releasing its "Beckton" (also called "Nehalem-EX") processor until then, and I don't think any other company is releasing an 8-core chip earlier than that. Even so, the "Beckton" chip is intended for servers, and we will probably have to wait several more months before the desktop versions become available.[/quote]

I was actually looking into this today also. If you search online for "penryn v8", you'll find lots of articles showing benchmarks from this mythical 8-core processor that would be out by the end of 2007. Apparently, it never did come out, and has been dropped altogether, since I can't find any recent references to it.

I did find [URL="http://news.google.com/news/url?sa=t&ct=us/0-0&fp=48cdc6b27e92f2c7&ei=K8jNSP3xMJe0_AGWrtjSBA&url=http%3A//www.tgdaily.com/content/view/39285/135/&cid=0&usg=AFQjCNHtsH3N-c4lXK6ot711ATmI6IXvbA"]an article[/URL] from last Friday saying that the last of the Penryn line is a 6-core Xeon, and it could be available starting this week.

According to [URL="http://en.wikipedia.org/wiki/Intel_Nehalem_%28microarchitecture%29#Variants"]Wikipedia,[/URL] you're right about Beckton. It will be the only 8-core variant of the Nehalem core, although it looks like Westmere (the desktop variant) may be available with 6 cores.

I also found articles saying that AMD has scrapped their 6-core and 8-core designs, because they decided that 12-core would be the better choice. Their 12-core processors will be available in 2010.

[QUOTE=T.Rex;142322]Here are the result of Prime95 v25.6 on a [B]2x 4cores Harpertown 3 GHz.[/B]
[B]8 threads : 10 iterations at 8192K FFT length. Best time: 53.507 ms.[/B]
Quite faste ![/QUOTE]

Wow my new Q9550 seems to be faster up to 4 threads.

Processor: [B]Q9550[/B] @ 2.8 GHz (default)
Motherboard: [B]ASUS Maximus II Formula[/B]
OS: [B]Vista 64-bit[/B]
Memory: [B]4GB DDR2-1066[/B]
mprime: [B]25.6 build 6 Prime95 Windows64
[/B]
[CODE][Sep 15 13:16] Work thread starting
[Sep 15 13:16] Timing 47 iterations at 768K FFT length. Best time: 14.619 ms.
[Sep 15 13:16] Timing 40 iterations at 896K FFT length. Best time: 17.400 ms.
[Sep 15 13:16] Timing 35 iterations at 1024K FFT length. Best time: 19.552 ms.
[Sep 15 13:16] Timing 28 iterations at 1280K FFT length. Best time: 24.744 ms.
[Sep 15 13:16] Timing 23 iterations at 1536K FFT length. Best time: 30.460 ms.
[Sep 15 13:16] Timing 20 iterations at 1792K FFT length. Best time: 36.310 ms.
[Sep 15 13:16] Timing 17 iterations at 2048K FFT length. Best time: 40.351 ms.
[Sep 15 13:16] Timing 14 iterations at 2560K FFT length. Best time: 53.098 ms.
[Sep 15 13:16] Timing 11 iterations at 3072K FFT length. Best time: 64.987 ms.
[Sep 15 13:16] Timing 10 iterations at 3584K FFT length. Best time: 77.483 ms.
[Sep 15 13:16] Timing 10 iterations at 4096K FFT length. Best time: 86.537 ms.
[Sep 15 13:16] Timing 10 iterations at 5120K FFT length. Best time: 110.288 ms.
[Sep 15 13:17] Timing 10 iterations at 6144K FFT length. Best time: 133.817 ms.
[Sep 15 13:17] Timing 10 iterations at 7168K FFT length. Best time: 161.889 ms.
[Sep 15 13:17] Timing 10 iterations at 8192K FFT length. Best time: 177.320 ms.
[Sep 15 13:17] Timing FFTs using 2 threads.
[Sep 15 13:17] Timing 47 iterations at 768K FFT length. Best time: 7.665 ms.
[Sep 15 13:17] Timing 40 iterations at 896K FFT length. Best time: 9.111 ms.
[Sep 15 13:17] Timing 35 iterations at 1024K FFT length. Best time: 10.611 ms.
[Sep 15 13:17] Timing 28 iterations at 1280K FFT length. Best time: 12.808 ms.
[Sep 15 13:17] Timing 23 iterations at 1536K FFT length. Best time: 15.765 ms.
[Sep 15 13:17] Timing 20 iterations at 1792K FFT length. Best time: 18.697 ms.
[Sep 15 13:17] Timing 17 iterations at 2048K FFT length. Best time: 20.978 ms.
[Sep 15 13:17] Timing 14 iterations at 2560K FFT length. Best time: 27.518 ms.
[Sep 15 13:17] Timing 11 iterations at 3072K FFT length. Best time: 33.695 ms.
[Sep 15 13:17] Timing 10 iterations at 3584K FFT length. Best time: 40.027 ms.
[Sep 15 13:17] Timing 10 iterations at 4096K FFT length. Best time: 45.125 ms.
[Sep 15 13:17] Timing 10 iterations at 5120K FFT length. Best time: 57.322 ms.
[Sep 15 13:17] Timing 10 iterations at 6144K FFT length. Best time: 69.978 ms.
[Sep 15 13:17] Timing 10 iterations at 7168K FFT length. Best time: 84.188 ms.
[Sep 15 13:17] Timing 10 iterations at 8192K FFT length. Best time: 92.995 ms.
[Sep 15 13:17] Timing FFTs using 3 threads.
[Sep 15 13:17] Timing 47 iterations at 768K FFT length. Best time: 10.490 ms.
[Sep 15 13:17] Timing 40 iterations at 896K FFT length. Best time: 11.163 ms.
[Sep 15 13:17] Timing 35 iterations at 1024K FFT length. Best time: 21.138 ms.
[Sep 15 13:17] Timing 28 iterations at 1280K FFT length. Best time: 10.789 ms.
[Sep 15 13:17] Timing 23 iterations at 1536K FFT length. Best time: 13.007 ms.
[Sep 15 13:17] Timing 20 iterations at 1792K FFT length. Best time: 15.421 ms.
[Sep 15 13:17] Timing 17 iterations at 2048K FFT length. Best time: 17.380 ms.
[Sep 15 13:17] Timing 14 iterations at 2560K FFT length. Best time: 22.768 ms.
[Sep 15 13:17] Timing 11 iterations at 3072K FFT length. Best time: 27.786 ms.
[Sep 15 13:17] Timing 10 iterations at 3584K FFT length. Best time: 32.633 ms.
[Sep 15 13:17] Timing 10 iterations at 4096K FFT length. Best time: 36.812 ms.
[Sep 15 13:17] Timing 10 iterations at 5120K FFT length. Best time: 45.142 ms.
[Sep 15 13:18] Timing 10 iterations at 6144K FFT length. Best time: 54.674 ms.
[Sep 15 13:18] Timing 10 iterations at 7168K FFT length. Best time: 65.281 ms.
[Sep 15 13:18] Timing 10 iterations at 8192K FFT length. Best time: 72.479 ms.
[Sep 15 13:18] Timing FFTs using 4 threads.
[Sep 15 13:18] Timing 47 iterations at 768K FFT length. Best time: 10.458 ms.
[Sep 15 13:18] Timing 40 iterations at 896K FFT length. Best time: 11.251 ms.
[Sep 15 13:18] Timing 35 iterations at 1024K FFT length. Best time: 18.421 ms.
[Sep 15 13:18] Timing 28 iterations at 1280K FFT length. Best time: 10.221 ms.
[Sep 15 13:18] Timing 23 iterations at 1536K FFT length. Best time: 11.019 ms.
[Sep 15 13:18] Timing 20 iterations at 1792K FFT length. Best time: 12.822 ms.
[Sep 15 13:18] Timing 17 iterations at 2048K FFT length. Best time: 14.430 ms.
[Sep 15 13:18] Timing 14 iterations at 2560K FFT length. Best time: 18.441 ms.
[Sep 15 13:18] Timing 11 iterations at 3072K FFT length. Best time: 22.207 ms.
[Sep 15 13:18] Timing 10 iterations at 3584K FFT length. Best time: 26.273 ms.
[Sep 15 13:18] Timing 10 iterations at 4096K FFT length. Best time: 29.661 ms.
[Sep 15 13:18] Timing 10 iterations at 5120K FFT length. Best time: 36.771 ms.
[Sep 15 13:18] Timing 10 iterations at 6144K FFT length. Best time: 44.114 ms.
[Sep 15 13:18] Timing 10 iterations at 7168K FFT length. Best time: 52.754 ms.
[Sep 15 13:18] Timing 10 iterations at 8192K FFT length. Best time: 58.039 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 58 bit length factors. Best time: 3.009 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 59 bit length factors. Best time: 3.011 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 60 bit length factors. Best time: 3.439 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 61 bit length factors. Best time: 3.621 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 62 bit length factors. Best time: 4.113 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 63 bit length factors. Best time: 5.262 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 64 bit length factors. Best time: 5.710 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 65 bit length factors. Best time: 6.347 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 66 bit length factors. Best time: 6.284 ms.
[Sep 15 13:18] Timing trial factoring of M35000011 with 67 bit length factors. Best time: 6.240 ms.
[Sep 15 13:18] Benchmark complete.
[Sep 15 13:18] Work thread stopped.
[/CODE]

[QUOTE=Jeff Gilchrist;142570]Wow my new Q9550 seems to be faster up to 4 threads.[/QUOTE]Yes. But, probably that, with 2x 4 cores and with 4 threads for Prime95, these 4 threads are not put on the same set of 4 cores. So there is time lost, and your 4 core is faster. My hypothesis....
T.

Wow, that is pretty impressive!

Anyone with an overclocked QX9770 want to weigh in?

Below is a "fullbench" comparison of Q9450 and QX6700, both running on the same platform @ 3.2GHz. What is interesting is that "2 threads results" are much worse on Q9450. It seems that there is some issue with affinity on 45nm quad-core CPU... most likely instead of choosing core0+core1, Prime95 chooses core0+core2...
Attached is an XLS spreadsheet to play with :wink:
[code][URL="http://valid.x86-secret.com/show_oc.php?id=419637"]Intel(R) Core(TM)2 Quad CPU Q9450 @ 2.66GHz[/URL]
CPU speed: 3200.05 MHz, 4 cores
CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2
L1 cache size: 32 KB
L2 cache size: 6144 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 256
Prime95 32-bit version 25.6, RdtscTiming=1
Best time for 4K FFT length: 0.040 ms.
Best time for 5K FFT length: 0.060 ms.
Best time for 6K FFT length: 0.071 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.125 ms.
Best time for 12K FFT length: 0.154 ms.
Best time for 14K FFT length: 0.185 ms.
Best time for 16K FFT length: 0.195 ms.
Best time for 20K FFT length: 0.263 ms.
Best time for 24K FFT length: 0.319 ms.
Best time for 28K FFT length: 0.396 ms.
Best time for 32K FFT length: 0.413 ms.
Best time for 40K FFT length: 0.541 ms.
Best time for 48K FFT length: 0.654 ms.
Best time for 56K FFT length: 0.800 ms.
Best time for 64K FFT length: 0.855 ms.
Best time for 80K FFT length: 1.203 ms.
Best time for 96K FFT length: 1.465 ms.
Best time for 112K FFT length: 1.765 ms.
Best time for 128K FFT length: 1.879 ms.
Best time for 160K FFT length: 2.307 ms.
Best time for 192K FFT length: 2.837 ms.
Best time for 224K FFT length: 3.383 ms.
Best time for 256K FFT length: 3.747 ms.
Best time for 320K FFT length: 4.790 ms.
Best time for 384K FFT length: 5.849 ms.
Best time for 448K FFT length: 6.994 ms.
Best time for 512K FFT length: 7.750 ms.
Best time for 640K FFT length: 10.232 ms.
Best time for 768K FFT length: 12.721 ms.
Best time for 896K FFT length: 15.369 ms.
Best time for 1024K FFT length: 17.562 ms.
Best time for 1280K FFT length: 22.023 ms.
Best time for 1536K FFT length: 26.961 ms.
Best time for 1792K FFT length: 32.042 ms.
Best time for 2048K FFT length: 35.595 ms.
Best time for 2560K FFT length: 47.072 ms.
Best time for 3072K FFT length: 57.486 ms.
Best time for 3584K FFT length: 68.392 ms.
Best time for 4096K FFT length: 76.507 ms.
Best time for 5120K FFT length: 97.955 ms.
Best time for 6144K FFT length: 117.908 ms.
Best time for 7168K FFT length: 142.988 ms.
Best time for 8192K FFT length: 156.089 ms.
Best time for 10240K FFT length: 210.475 ms.
Best time for 12288K FFT length: 253.347 ms.
Best time for 14336K FFT length: 306.970 ms.
Best time for 16384K FFT length: 335.265 ms.
Best time for 20480K FFT length: 466.348 ms.
Best time for 24576K FFT length: 568.889 ms.
Best time for 28672K FFT length: 677.463 ms.
Best time for 32768K FFT length: 738.596 ms.
Timing FFTs using 2 threads.
Best time for 4K FFT length: 0.041 ms.
Best time for 5K FFT length: 0.060 ms.
Best time for 6K FFT length: 0.071 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.132 ms.
Best time for 12K FFT length: 0.160 ms.
Best time for 14K FFT length: 0.182 ms.
Best time for 16K FFT length: 0.200 ms.
Best time for 20K FFT length: 0.244 ms.
Best time for 24K FFT length: 0.292 ms.
Best time for 28K FFT length: 0.357 ms.
Best time for 32K FFT length: 0.394 ms.
Best time for 40K FFT length: 0.873 ms.
Best time for 48K FFT length: 0.908 ms.
Best time for 56K FFT length: 1.036 ms.
Best time for 64K FFT length: 1.079 ms.
Best time for 80K FFT length: 1.082 ms.
Best time for 96K FFT length: 1.279 ms.
Best time for 112K FFT length: 1.463 ms.
Best time for 128K FFT length: 1.615 ms.
Best time for 160K FFT length: 1.699 ms.
Best time for 192K FFT length: 1.859 ms.
Best time for 224K FFT length: 2.192 ms.
Best time for 256K FFT length: 2.436 ms.
Best time for 320K FFT length: 3.087 ms.
Best time for 384K FFT length: 3.756 ms.
Best time for 448K FFT length: 4.473 ms.
Best time for 512K FFT length: 4.980 ms.
Best time for 640K FFT length: 7.406 ms.
Best time for 768K FFT length: 8.852 ms.
Best time for 896K FFT length: 10.322 ms.
Best time for 1024K FFT length: 15.082 ms.
Best time for 1280K FFT length: 13.588 ms.
Best time for 1536K FFT length: 16.499 ms.
Best time for 1792K FFT length: 19.433 ms.
Best time for 2048K FFT length: 21.719 ms.
Best time for 2560K FFT length: 28.048 ms.
Best time for 3072K FFT length: 34.145 ms.
Best time for 3584K FFT length: 39.986 ms.
Best time for 4096K FFT length: 45.122 ms.
Best time for 5120K FFT length: 56.865 ms.
Best time for 6144K FFT length: 68.388 ms.
Best time for 7168K FFT length: 81.936 ms.
Best time for 8192K FFT length: 90.731 ms.
Best time for 10240K FFT length: 120.744 ms.
Best time for 12288K FFT length: 145.243 ms.
Best time for 14336K FFT length: 173.740 ms.
Best time for 16384K FFT length: 192.342 ms.
Best time for 20480K FFT length: 268.490 ms.
Best time for 24576K FFT length: 325.746 ms.
Best time for 28672K FFT length: 385.901 ms.
Best time for 32768K FFT length: 426.150 ms.
Timing FFTs using 3 threads.
Best time for 4K FFT length: 0.041 ms.
Best time for 5K FFT length: 0.060 ms.
Best time for 6K FFT length: 0.071 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.142 ms.
Best time for 12K FFT length: 0.157 ms.
Best time for 14K FFT length: 0.174 ms.
Best time for 16K FFT length: 0.188 ms.
Best time for 20K FFT length: 0.222 ms.
Best time for 24K FFT length: 0.255 ms.
Best time for 28K FFT length: 0.295 ms.
Best time for 32K FFT length: 0.320 ms.
Best time for 40K FFT length: 0.720 ms.
Best time for 48K FFT length: 0.744 ms.
Best time for 56K FFT length: 0.848 ms.
Best time for 64K FFT length: 0.881 ms.
Best time for 80K FFT length: 1.059 ms.
Best time for 96K FFT length: 1.142 ms.
Best time for 112K FFT length: 1.292 ms.
Best time for 128K FFT length: 1.442 ms.
Best time for 160K FFT length: 1.465 ms.
Best time for 192K FFT length: 1.298 ms.
Best time for 224K FFT length: 1.503 ms.
Best time for 256K FFT length: 1.677 ms.
Best time for 320K FFT length: 2.121 ms.
Best time for 384K FFT length: 2.546 ms.
Best time for 448K FFT length: 3.056 ms.
Best time for 512K FFT length: 3.448 ms.
Best time for 640K FFT length: 6.331 ms.
Best time for 768K FFT length: 7.296 ms.
Best time for 896K FFT length: 8.317 ms.
Best time for 1024K FFT length: 12.164 ms.
Best time for 1280K FFT length: 9.732 ms.
Best time for 1536K FFT length: 11.799 ms.
Best time for 1792K FFT length: 13.948 ms.
Best time for 2048K FFT length: 15.726 ms.
Best time for 2560K FFT length: 20.686 ms.
Best time for 3072K FFT length: 25.353 ms.
Best time for 3584K FFT length: 29.795 ms.
Best time for 4096K FFT length: 33.656 ms.
Best time for 5120K FFT length: 41.351 ms.
Best time for 6144K FFT length: 49.904 ms.
Best time for 7168K FFT length: 60.145 ms.
Best time for 8192K FFT length: 66.469 ms.
Best time for 10240K FFT length: 85.745 ms.
Best time for 12288K FFT length: 103.662 ms.
Best time for 14336K FFT length: 124.434 ms.
Best time for 16384K FFT length: 137.557 ms.
Best time for 20480K FFT length: 190.749 ms.
Best time for 24576K FFT length: 231.016 ms.
Best time for 28672K FFT length: 273.267 ms.
Best time for 32768K FFT length: 304.954 ms.
Timing FFTs using 4 threads.
Best time for 4K FFT length: 0.041 ms.
Best time for 5K FFT length: 0.060 ms.
Best time for 6K FFT length: 0.071 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.146 ms.
Best time for 12K FFT length: 0.151 ms.
Best time for 14K FFT length: 0.171 ms.
Best time for 16K FFT length: 0.178 ms.
Best time for 20K FFT length: 0.205 ms.
Best time for 24K FFT length: 0.233 ms.
Best time for 28K FFT length: 0.270 ms.
Best time for 32K FFT length: 0.293 ms.
Best time for 40K FFT length: 0.682 ms.
Best time for 48K FFT length: 0.737 ms.
Best time for 56K FFT length: 0.750 ms.
Best time for 64K FFT length: 0.775 ms.
Best time for 80K FFT length: 0.964 ms.
Best time for 96K FFT length: 1.004 ms.
Best time for 112K FFT length: 1.164 ms.
Best time for 128K FFT length: 1.227 ms.
Best time for 160K FFT length: 1.352 ms.
Best time for 192K FFT length: 1.200 ms.
Best time for 224K FFT length: 1.354 ms.
Best time for 256K FFT length: 1.518 ms.
Best time for 320K FFT length: 1.826 ms.
Best time for 384K FFT length: 2.131 ms.
Best time for 448K FFT length: 2.495 ms.
Best time for 512K FFT length: 2.840 ms.
Best time for 640K FFT length: 5.639 ms.
Best time for 768K FFT length: 6.576 ms.
Best time for 896K FFT length: 7.367 ms.
Best time for 1024K FFT length: 10.589 ms.
Best time for 1280K FFT length: 8.177 ms.
Best time for 1536K FFT length: 9.713 ms.
Best time for 1792K FFT length: 11.530 ms.
Best time for 2048K FFT length: 13.199 ms.
Best time for 2560K FFT length: 16.901 ms.
Best time for 3072K FFT length: 20.600 ms.
Best time for 3584K FFT length: 24.174 ms.
Best time for 4096K FFT length: 27.842 ms.
Best time for 5120K FFT length: 34.385 ms.
Best time for 6144K FFT length: 40.952 ms.
Best time for 7168K FFT length: 48.886 ms.
Best time for 8192K FFT length: 55.069 ms.
Best time for 10240K FFT length: 70.664 ms.
Best time for 12288K FFT length: 84.194 ms.
Best time for 14336K FFT length: 100.234 ms.
Best time for 16384K FFT length: 112.891 ms.
Best time for 20480K FFT length: 153.113 ms.
Best time for 24576K FFT length: 185.200 ms.
Best time for 28672K FFT length: 219.136 ms.
Best time for 32768K FFT length: 244.179 ms.
Best time for 58 bit trial factors: 3.254 ms.
Best time for 59 bit trial factors: 3.223 ms.
Best time for 60 bit trial factors: 3.219 ms.
Best time for 61 bit trial factors: 3.217 ms.
Best time for 62 bit trial factors: 5.480 ms.
Best time for 63 bit trial factors: 5.483 ms.
Best time for 64 bit trial factors: 5.070 ms.
Best time for 65 bit trial factors: 5.040 ms.
Best time for 66 bit trial factors: 5.040 ms.
Best time for 67 bit trial factors: 5.018 ms.[/code]
[code][URL="http://valid.x86-secret.com/show_oc.php?id=353473"]Intel(R) Core(TM)2 Quad CPU @ 2.66GHz[/URL]
CPU speed: 3200.05 MHz, 4 cores
CPU features: RDTSC, CMOV, Prefetch, MMX, SSE, SSE2
L1 cache size: 32 KB
L2 cache size: 4096 KB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 256
Prime95 32-bit version 25.6, RdtscTiming=1
Best time for 4K FFT length: 0.040 ms.
Best time for 5K FFT length: 0.060 ms.
Best time for 6K FFT length: 0.071 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.125 ms.
Best time for 12K FFT length: 0.153 ms.
Best time for 14K FFT length: 0.185 ms.
Best time for 16K FFT length: 0.196 ms.
Best time for 20K FFT length: 0.263 ms.
Best time for 24K FFT length: 0.319 ms.
Best time for 28K FFT length: 0.396 ms.
Best time for 32K FFT length: 0.412 ms.
Best time for 40K FFT length: 0.541 ms.
Best time for 48K FFT length: 0.654 ms.
Best time for 56K FFT length: 0.799 ms.
Best time for 64K FFT length: 0.855 ms.
Best time for 80K FFT length: 1.202 ms.
Best time for 96K FFT length: 1.463 ms.
Best time for 112K FFT length: 1.767 ms.
Best time for 128K FFT length: 1.874 ms.
Best time for 160K FFT length: 2.304 ms.
Best time for 192K FFT length: 2.831 ms.
Best time for 224K FFT length: 3.382 ms.
Best time for 256K FFT length: 3.740 ms.
Best time for 320K FFT length: 4.792 ms.
Best time for 384K FFT length: 5.883 ms.
Best time for 448K FFT length: 7.094 ms.
Best time for 512K FFT length: 7.921 ms.
Best time for 640K FFT length: 10.569 ms.
Best time for 768K FFT length: 13.114 ms.
Best time for 896K FFT length: 15.687 ms.
Best time for 1024K FFT length: 17.942 ms.
Best time for 1280K FFT length: 22.287 ms.
Best time for 1536K FFT length: 27.215 ms.
Best time for 1792K FFT length: 32.342 ms.
Best time for 2048K FFT length: 35.923 ms.
Best time for 2560K FFT length: 47.402 ms.
Best time for 3072K FFT length: 57.756 ms.
Best time for 3584K FFT length: 68.787 ms.
Best time for 4096K FFT length: 76.808 ms.
Best time for 5120K FFT length: 98.559 ms.
Best time for 6144K FFT length: 118.833 ms.
Best time for 7168K FFT length: 144.560 ms.
Best time for 8192K FFT length: 158.428 ms.
Best time for 10240K FFT length: 211.289 ms.
Best time for 12288K FFT length: 255.096 ms.
Best time for 14336K FFT length: 309.596 ms.
Best time for 16384K FFT length: 339.978 ms.
Best time for 20480K FFT length: 468.734 ms.
Best time for 24576K FFT length: 572.562 ms.
Best time for 28672K FFT length: 685.606 ms.
Best time for 32768K FFT length: 751.616 ms.
Timing FFTs using 2 threads.
Best time for 4K FFT length: 0.042 ms.
Best time for 5K FFT length: 0.062 ms.
Best time for 6K FFT length: 0.074 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.112 ms.
Best time for 12K FFT length: 0.111 ms.
Best time for 14K FFT length: 0.122 ms.
Best time for 16K FFT length: 0.134 ms.
Best time for 20K FFT length: 0.161 ms.
Best time for 24K FFT length: 0.192 ms.
Best time for 28K FFT length: 0.230 ms.
Best time for 32K FFT length: 0.241 ms.
Best time for 40K FFT length: 0.658 ms.
Best time for 48K FFT length: 0.679 ms.
Best time for 56K FFT length: 0.771 ms.
Best time for 64K FFT length: 0.793 ms.
Best time for 80K FFT length: 0.908 ms.
Best time for 96K FFT length: 0.862 ms.
Best time for 112K FFT length: 1.015 ms.
Best time for 128K FFT length: 1.080 ms.
Best time for 160K FFT length: 1.276 ms.
Best time for 192K FFT length: 1.497 ms.
Best time for 224K FFT length: 1.779 ms.
Best time for 256K FFT length: 1.972 ms.
Best time for 320K FFT length: 2.512 ms.
Best time for 384K FFT length: 3.084 ms.
Best time for 448K FFT length: 3.727 ms.
Best time for 512K FFT length: 4.186 ms.
Best time for 640K FFT length: 5.793 ms.
Best time for 768K FFT length: 7.115 ms.
Best time for 896K FFT length: 8.467 ms.
Best time for 1024K FFT length: 10.524 ms.
Best time for 1280K FFT length: 11.792 ms.
Best time for 1536K FFT length: 14.373 ms.
Best time for 1792K FFT length: 17.009 ms.
Best time for 2048K FFT length: 19.121 ms.
Best time for 2560K FFT length: 25.072 ms.
Best time for 3072K FFT length: 30.427 ms.
Best time for 3584K FFT length: 36.230 ms.
Best time for 4096K FFT length: 40.592 ms.
Best time for 5120K FFT length: 52.184 ms.
Best time for 6144K FFT length: 64.317 ms.
Best time for 7168K FFT length: 77.523 ms.
Best time for 8192K FFT length: 87.386 ms.
Best time for 10240K FFT length: 110.394 ms.
Best time for 12288K FFT length: 135.483 ms.
Best time for 14336K FFT length: 163.099 ms.
Best time for 16384K FFT length: 182.988 ms.
Best time for 20480K FFT length: 246.006 ms.
Best time for 24576K FFT length: 301.290 ms.
Best time for 28672K FFT length: 360.940 ms.
Best time for 32768K FFT length: 400.087 ms.
Timing FFTs using 3 threads.
Best time for 4K FFT length: 0.042 ms.
Best time for 5K FFT length: 0.062 ms.
Best time for 6K FFT length: 0.074 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.154 ms.
Best time for 12K FFT length: 0.161 ms.
Best time for 14K FFT length: 0.176 ms.
Best time for 16K FFT length: 0.185 ms.
Best time for 20K FFT length: 0.223 ms.
Best time for 24K FFT length: 0.256 ms.
Best time for 28K FFT length: 0.288 ms.
Best time for 32K FFT length: 0.321 ms.
Best time for 40K FFT length: 0.735 ms.
Best time for 48K FFT length: 0.770 ms.
Best time for 56K FFT length: 0.852 ms.
Best time for 64K FFT length: 0.892 ms.
Best time for 80K FFT length: 1.057 ms.
Best time for 96K FFT length: 1.145 ms.
Best time for 112K FFT length: 1.299 ms.
Best time for 128K FFT length: 1.420 ms.
Best time for 160K FFT length: 1.466 ms.
Best time for 192K FFT length: 1.338 ms.
Best time for 224K FFT length: 1.493 ms.
Best time for 256K FFT length: 1.697 ms.
Best time for 320K FFT length: 2.120 ms.
Best time for 384K FFT length: 2.606 ms.
Best time for 448K FFT length: 3.130 ms.
Best time for 512K FFT length: 3.538 ms.
Best time for 640K FFT length: 6.714 ms.
Best time for 768K FFT length: 7.659 ms.
Best time for 896K FFT length: 8.755 ms.
Best time for 1024K FFT length: 12.506 ms.
Best time for 1280K FFT length: 9.783 ms.
Best time for 1536K FFT length: 11.855 ms.
Best time for 1792K FFT length: 13.996 ms.
Best time for 2048K FFT length: 15.757 ms.
Best time for 2560K FFT length: 20.637 ms.
Best time for 3072K FFT length: 25.277 ms.
Best time for 3584K FFT length: 29.810 ms.
Best time for 4096K FFT length: 33.879 ms.
Best time for 5120K FFT length: 42.126 ms.
Best time for 6144K FFT length: 51.378 ms.
Best time for 7168K FFT length: 62.665 ms.
Best time for 8192K FFT length: 70.647 ms.
Best time for 10240K FFT length: 87.550 ms.
Best time for 12288K FFT length: 106.561 ms.
Best time for 14336K FFT length: 129.046 ms.
Best time for 16384K FFT length: 145.164 ms.
Best time for 20480K FFT length: 196.270 ms.
Best time for 24576K FFT length: 240.590 ms.
Best time for 28672K FFT length: 288.997 ms.
Best time for 32768K FFT length: 325.989 ms.
Timing FFTs using 4 threads.
Best time for 4K FFT length: 0.042 ms.
Best time for 5K FFT length: 0.063 ms.
Best time for 6K FFT length: 0.074 ms.
Best time for 7K FFT length: 0.086 ms.
Best time for 8K FFT length: 0.089 ms.
Best time for 10K FFT length: 0.155 ms.
Best time for 12K FFT length: 0.160 ms.
Best time for 14K FFT length: 0.174 ms.
Best time for 16K FFT length: 0.181 ms.
Best time for 20K FFT length: 0.208 ms.
Best time for 24K FFT length: 0.230 ms.
Best time for 28K FFT length: 0.259 ms.
Best time for 32K FFT length: 0.280 ms.
Best time for 40K FFT length: 0.714 ms.
Best time for 48K FFT length: 0.759 ms.
Best time for 56K FFT length: 0.779 ms.
Best time for 64K FFT length: 0.812 ms.
Best time for 80K FFT length: 0.972 ms.
Best time for 96K FFT length: 1.030 ms.
Best time for 112K FFT length: 1.176 ms.
Best time for 128K FFT length: 1.246 ms.
Best time for 160K FFT length: 1.352 ms.
Best time for 192K FFT length: 1.204 ms.
Best time for 224K FFT length: 1.379 ms.
Best time for 256K FFT length: 1.541 ms.
Best time for 320K FFT length: 1.884 ms.
Best time for 384K FFT length: 2.230 ms.
Best time for 448K FFT length: 2.603 ms.
Best time for 512K FFT length: 2.973 ms.
Best time for 640K FFT length: 5.908 ms.
Best time for 768K FFT length: 6.822 ms.
Best time for 896K FFT length: 7.749 ms.
Best time for 1024K FFT length: 11.104 ms.
Best time for 1280K FFT length: 8.586 ms.
Best time for 1536K FFT length: 10.153 ms.
Best time for 1792K FFT length: 11.849 ms.
Best time for 2048K FFT length: 13.493 ms.
Best time for 2560K FFT length: 17.213 ms.
Best time for 3072K FFT length: 20.887 ms.
Best time for 3584K FFT length: 24.629 ms.
Best time for 4096K FFT length: 28.218 ms.
Best time for 5120K FFT length: 35.276 ms.
Best time for 6144K FFT length: 42.663 ms.
Best time for 7168K FFT length: 51.187 ms.
Best time for 8192K FFT length: 58.805 ms.
Best time for 10240K FFT length: 71.976 ms.
Best time for 12288K FFT length: 86.946 ms.
Best time for 14336K FFT length: 104.080 ms.
Best time for 16384K FFT length: 119.134 ms.
Best time for 20480K FFT length: 156.770 ms.
Best time for 24576K FFT length: 191.285 ms.
Best time for 28672K FFT length: 229.773 ms.
Best time for 32768K FFT length: 261.643 ms.
Best time for 58 bit trial factors: 3.514 ms.
Best time for 59 bit trial factors: 3.343 ms.
Best time for 60 bit trial factors: 3.343 ms.
Best time for 61 bit trial factors: 3.324 ms.
Best time for 62 bit trial factors: 5.561 ms.
Best time for 63 bit trial factors: 5.568 ms.
Best time for 64 bit trial factors: 5.391 ms.
Best time for 65 bit trial factors: 5.361 ms.
Best time for 66 bit trial factors: 5.355 ms.
Best time for 67 bit trial factors: 5.335 ms.[/code]