|
|
 Author
|
Topic: GPU client (Read 30611 times)
|
|
Devaster
|
i see that in some cases is GPU application better than stock app ....  interesting .... |
|
|
|
|
Logged
|
|
|
|
|
Radiohead
|
i see that in some cases is GPU application better than stock app .... interesting .... Hm... This is 8800GTX  |
|
|
|
|
Logged
|
|
|
|
|
guido.man
|
There are too many variables to make an accurate assessment of the true speedup of GPU client.
When I use default-515.exe as the reference client I also get Speedup Ratio greater than 1.00 for some WU's.
Devaster what source files are you using to base your GPU client on, and what optimizations are done?
If you compiled a reference client to be used against your GPU client then most of the variables would
be known.
|
|
|
|
« Last Edit: 16 Jan 2008, 12:25:24 pm by guido.man »
|
Logged
|
|
|
|
|
Devaster
|
at home by tests i am using latest optimized app from cruncher page and i have 8500GT only ....
remember , for now aren't in GPU code optimizations (shared mem usage ,memory coalescent access by read/write, optimal thread/block scheduling against core, ). used is only partial loop unroll ...
|
|
|
|
|
Logged
|
|
|
|
|
Devaster
|
last weekend i have downloaded GUI profiler for CUDA. It has showed many interesting things .... i will write more later - it would bigger ...
|
|
|
|
|
Logged
|
|
|
|
|
|
|
Devaster
|
SETI@HOME uses 1d FFT and this is batched naturally in CUFFT library ....
|
|
|
|
|
Logged
|
|
|
|
|
Gecko_R7
|
SETI@HOME uses 1d FFT and this is batched naturally in CUFFT library ....
SETI@HOME uses 1d FFT and this is batched naturally in CUFFT library ....
Sorry  . My inquiry/interest was related to the batching, not the 2d fft itself since as you pointed-out, Seti uses 1d fft single precision complex ^2. Didn't realize the batching was already done in the CUFFT library however. Just ignore "the little man from behind the curtain".....  |
|
|
|
« Last Edit: 21 Jan 2008, 08:09:44 pm by Gecko_R7 »
|
Logged
|
|
|
|
|
|
|
|
|
|
|
popandbob
|
my first run...
8600GTS
Cpu and vid card not OC'ed.
~BoB
|
|
|
|
Logged
|
|
|
|
|
Devaster
|
- changed data alignment to multiples of two (float2,float4) -some speedup
|
|
|
|
|
Logged
|
|
|
|
|
Devaster
|
my first run...
8600GTS
Cpu and vid card not OC'ed.
~BoB
more multiprocessors and more MHz as me and better results ... |
|
|
|
|
Logged
|
|
|
|
|
Batstat
|
My result, open attachment
Result : weakly similar.
Result : weakly similar.
Result : DIFFERENT.
Result : weakly similar.
Result : DIFFERENT.
Result : weakly similar.
Result : weakly similar.
Speedup: 5.88%, Ratio: 1.06 x
Speedup: 9.83%, Ratio: 1.11 x
Speedup: 11.48%, Ratio: 1.13 x
Speedup: -31.30%, Ratio: 0.76 x
Speedup: 10.21%, Ratio: 1.11 x
Speedup: 24.52%, Ratio: 1.32 x
Speedup: 28.01%, Ratio: 1.39 x
|
|
|
|
Logged
|
|
|
|
|
|
Quote!
If everything seems to be going well, you have obviously overlooked something.- Murphy's Law
|
 |  |  |
| |
| Site Statistics |
| Total Members: | 1,188 |
| Total Posts: | 12,412 |
| Total Topics: | 482 | | Downloads |
| Apps |
| Windows R-1.x | 25,177 |
| Windows R-2.0 | 20,387 |
| Windows R-2.2 | 36,768 |
| Linux 32bit 1.x | 6,589 |
| Linux 32bit 2.2 | 4,472 |
| Linux 64bit 2.2 | 1,839 |
| Alpha/IA64 | 216 |
| FreeBSD | 655 |
| HPUX | 355 |
| Subtotal: | 95,232 |
| Source packs: | 4,173 |
| Tool/WU packs: | 8,149 |
| Total: | 162,739 | | GBs dl'd: | 284.03 | | Pages served |
| Today: | 3,542 |
| Total: | 3,577,362 |
| (since 6/26/2006) |
| 173 Donations to S@H |
| U.S. Dollars: | 3,196.59 |
| Euros: | 863.90 |
| Last 24h: | $ 0.00 |
| Avg./24h: | $ 6.18 |
| Estim. total: | $ 4,319.66 |
Latest Member:
bdlandis |
| |
 | |  |
| | |
| |
Online users/last 15m
11 Guests, 4 Users
Raistmer, ThierryH, Maik, bdlandis
44 Members/last 24hRaistmer, ThierryH, Maik, bdlandis, Kiva, Archangel999, _heinz, [B^S] zioriga, jlongden, Gecko_R7, Herus, Geek@Play, Pizzadude, Haselgrove, Devaster, Josef W. Segur, Macbeth, dayo21, sunu, Jason G, corsair, The Grinch, Bluesilvergreen, Claggy, KarVi, ppppgabor, Arnulf, clk, Crunch3r, Yurik, Morten, tfp, hwddawg, WHRoeder, Urs Echternacht, Vyper, arkayn, Alex Kraft, ajs, Hiroharu, firefox, Garry W, Vol-Phil, phod
| |
| | |
|
sahcuda.rar