読者です 読者をやめる 読者になる 読者になる

だ・か・らっ、Dia“l”yだってばさ!

これは『戯れ言』です。また、“Diary”ではなく“Dialy”です。つまり、日記に似て非なるものです。 所謂『日記』ではありません。お間違えの無いようお願いします。(^^;A

v2.9106.513 (beta8)

[AMD64/CUDA-2.3]  	v2.9106.513 (beta8)   	2009-08-13
[x86/CUDA-2.2] 		v2.9106.513 (beta8)  	2009-08-13
[x86/CUDA-2.3] 		v2.9106.513 (beta8)  	2009-08-13
[AMD64/CUDA-2.2] 	v2.9105.512 (beta8)  	2009-07-26 

やっと32 bit版のbetaがでました。
因みに、http serverにはありましたが、ftp serverにはまだ載ってませんでした。

#CUDA-2.3だって。
#なんだそりゃ?
nVidiaに見に行ったけど、Linuxのところには無かったような・・・


で、9500GT on ubuntu 8.04 32 bitでのbenchです。

$ ./dnetc -bench rc5-72

distributed.net client for CUDA 2.2 on Linux Copyright 1997-2009, distributed.net
Please visit http://www.distributed.net/ for up-to-date contest information.
Start the client with '-help' for a list of valid command line options.


dnetc v2.9106-513-CTL-09081022-*dev* for CUDA 2.2 on Linux (Linux 2.6.24-24-generic).
Please provide the *entire* version descriptor when submitting bug reports.
The distributed.net bug report pages are at http://bugs.distributed.net/
Using email address (distributed.net ID) 'sr@hyper.cx'

[Aug 13 22:37:30 UTC] RC5-72: using core #0 (CUDA 1-pipe 64-thd).
[Aug 13 22:37:49 UTC] RC5-72: Benchmark for core #0 (CUDA 1-pipe 64-thd)
                      0.00:00:16.60 [38,829,698 keys/sec]
[Aug 13 22:37:49 UTC] RC5-72: using core #1 (CUDA 1-pipe 128-thd).
[Aug 13 22:38:08 UTC] RC5-72: Benchmark for core #1 (CUDA 1-pipe 128-thd)
                      0.00:00:16.17 [38,818,746 keys/sec]
[Aug 13 22:38:08 UTC] RC5-72: using core #2 (CUDA 1-pipe 256-thd).
[Aug 13 22:38:27 UTC] RC5-72: Benchmark for core #2 (CUDA 1-pipe 256-thd)
                      0.00:00:16.75 [38,437,030 keys/sec]
[Aug 13 22:38:27 UTC] RC5-72: using core #3 (CUDA 2-pipe 64-thd).
[Aug 13 22:38:46 UTC] RC5-72: Benchmark for core #3 (CUDA 2-pipe 64-thd)
                      0.00:00:16.17 [38,830,079 keys/sec]
[Aug 13 22:38:46 UTC] RC5-72: using core #4 (CUDA 2-pipe 128-thd).
[Aug 13 22:39:05 UTC] RC5-72: Benchmark for core #4 (CUDA 2-pipe 128-thd)
                      0.00:00:16.67 [34,365,066 keys/sec]
[Aug 13 22:39:05 UTC] RC5-72: using core #6 (CUDA 4-pipe 64-thd).
[Aug 13 22:39:24 UTC] RC5-72: Benchmark for core #6 (CUDA 4-pipe 64-thd)
                      0.00:00:16.46 [39,191,843 keys/sec]
[Aug 13 22:39:24 UTC] RC5-72: using core #7 (CUDA 4-pipe 128-thd).
[Aug 13 22:39:43 UTC] RC5-72: Benchmark for core #7 (CUDA 4-pipe 128-thd)
                      0.00:00:16.64 [34,431,984 keys/sec]
[Aug 13 22:39:43 UTC] RC5-72: using core #9 (CUDA 1-pipe 64-thd busy wait).
[Aug 13 22:40:03 UTC] RC5-72: Benchmark for core #9 (CUDA 1-pipe 64-thd busy wait)
                      0.00:00:16.52 [39,047,356 keys/sec]
[Aug 13 22:40:03 UTC] RC5-72: using core #10 (CUDA 1-pipe 64-thd sleep 100us).
[Aug 13 22:40:22 UTC] RC5-72: Benchmark for core #10 (CUDA 1-pipe 64-thd sleep 100us)
                      0.00:00:16.60 [38,829,114 keys/sec]
[Aug 13 22:40:22 UTC] RC5-72: using core #11 (CUDA 1-pipe 64-thd sleep dynamic).
[Aug 13 22:40:41 UTC] RC5-72: Benchmark for core #11 (CUDA 1-pipe 64-thd sleep dynamic)
                      0.00:00:16.51 [39,044,719 keys/sec]
[Aug 13 22:40:41 UTC] RC5-72 benchmark summary :
                      Default core : #0 (CUDA 1-pipe 64-thd)
                      Fastest core : #6 (CUDA 4-pipe 64-thd)
[Aug 13 22:40:41 UTC] Core #6 is marginally faster than the default core.
                      Testing variability might lead to pick one or the other.