mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > Hardware > GPU Computing

Reply
 
Thread Tools
Old 2009-11-26, 19:42   #111
frmky
 
frmky's Avatar
 
Jul 2003
So Cal

23×32×29 Posts
Default

Quote:
Originally Posted by TheJudger View Post
- choose some exponents which are not so close to the fft limit. I didn't dive into the CUFFTW docs, perhaps the rounding/rounding errors are not so accurate as the CPU versions of MaclucasFFTW and you need to lower the FFT boundaries?
We know the ones farther away from the boundaries work fine. The boundary is what I want to test.
frmky is offline   Reply With Quote
Old 2009-11-27, 16:59   #112
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2·5·61 Posts
Default

New GTX260 result.
M22748749
(Last 1 day with 4 x mprime.)
msft is offline   Reply With Quote
Old 2009-11-28, 07:47   #113
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2×5×61 Posts
Default

Hi,
Benchmark 1 x MacLucasFFTW + 4 x mprime on GTX260 & Q8400, same time same machine.
Quote:
[Nov 28 09:49] Iteration: 5420000 / 23284399 [23.27%]. Per iteration time: 0.037 sec.
[Nov 28 09:49] Iteration: 5420000 / 23284267 [23.27%]. Per iteration time: 0.038 sec.
[Work thread Nov 28 09:49] Iteration: 3490000 / 22759339 [15.33%]. Per iteration time: 0.033 sec.
[Work thread Nov 28 09:49] Iteration: 5550000 / 23287769 [23.83%]. Per iteration time: 0.033 sec.
$ time ./MacLucasFFTW 33333333
Iteration 10000 M( 33333333 )C, 0xd717246f501c7d94, n = 2097152, MacLucasFFTW v8.1 Ballester
M( 33333333 )C, 0xd717246f501c7d94, n = 2097152, MacLucasFFTW v8.1 Ballester

real 2m2.058s
user 0m2.652s
sys 0m0.776s

1028kFFT mprime 0.037 sec,0.038 sec,0.033 sec,0.033 sec
2048kFFT MacLucasFFTW 0.012 sec
Thank you,
msft is offline   Reply With Quote
Old 2009-11-28, 08:56   #114
msft
 
msft's Avatar
 
Jul 2009
Tokyo

61010 Posts
Default

Hi,

New Version "G", only delete -DTESRA code from Version "C".

Thank you,
Attached Files
File Type: gz MacLucasFFTW.cuda.G.tar.gz (31.9 KB, 108 views)
msft is offline   Reply With Quote
Old 2009-12-03, 06:19   #115
msft
 
msft's Avatar
 
Jul 2009
Tokyo

11428 Posts
Default

Quote:
Originally Posted by em99010pepe View Post
Can you test 4 numbers in parallel on your Q8400 and the exact 4 in series on your GTX260?
GTX260 result.(with 4x mprime LLD)
M36000113
msft is offline   Reply With Quote
Old 2009-12-05, 22:59   #116
Prime95
P90 years forever!
 
Prime95's Avatar
 
Aug 2002
Yeehaw, FL

7×1,069 Posts
Default

Exponent status web form will now display these CUDA residues properly
Prime95 is offline   Reply With Quote
Old 2009-12-06, 08:26   #117
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2·5·61 Posts
Default

Quote:
Originally Posted by Prime95 View Post
Exponent status web form will now display these CUDA residues properly
Hi, Prime95

Thank you,
msft is offline   Reply With Quote
Old 2009-12-29, 03:21   #118
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2×5×61 Posts
Default

Hi,
Version "H" at .0117 sec/iter for the 2048K FFT and .0221 sec/iter for the 4096K FFT on GTX260.
and GTX260 result.

M36000127
M36000521
M36010921
M36007753
Attached Files
File Type: gz MacLucasFFTW.cuda.H.tar.gz (31.6 KB, 112 views)
msft is offline   Reply With Quote
Old 2010-01-03, 09:25   #119
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2×5×61 Posts
Default

Hi,
Version "J" at .0107 sec/iter for the 2048K(This version support only 2048K) on GTX260.
Attached Files
File Type: gz MacLucasFFTW.cuda.J.tar.gz (31.5 KB, 109 views)
msft is offline   Reply With Quote
Old 2010-01-31, 17:19   #120
CADavis
 
CADavis's Avatar
 
Jul 2005
Des Moines, Iowa, USA

17010 Posts
Default

what do i need to be able to compile this on windows? i have access to microsoft technet if any non-free MS software is needed.
CADavis is offline   Reply With Quote
Old 2010-02-01, 00:14   #121
msft
 
msft's Avatar
 
Jul 2009
Tokyo

2×5×61 Posts
Default

Hi,CADavis
Quote:
Originally Posted by CADavis View Post
what do i need to be able to compile this on windows? i have access to microsoft technet if any non-free MS software is needed.
I don't have windows system.
I hope your review this program on windows system.

http://www.nvidia.com/object/cuda_develop.html
"CUDA 2.2 Quick Start Guide" is Install Guide.

Thank you,
msft is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
Don't DC/LL them with CudaLucas LaurV Data 131 2017-05-02 18:41
CUDALucas / cuFFT Performance on CUDA 7 / 7.5 / 8 Brain GPU Computing 13 2016-02-19 15:53
CUDALucas: which binary to use? Karl M Johnson GPU Computing 15 2015-10-13 04:44
settings for cudaLucas fairsky GPU Computing 11 2013-11-03 02:08
Trying to run CUDALucas on Windows 8 CP Rodrigo GPU Computing 12 2012-03-07 23:20

All times are UTC. The time now is 06:55.

Fri May 7 06:55:52 UTC 2021 up 29 days, 1:36, 0 users, load averages: 2.52, 2.46, 2.38

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.