By: Ian Ameline (ian.ameline.delete@this.(NoSpam).gmail.com), April 18, 2011 4:55 pm
Room: Moderated Discussions
Groo (charlie@semiaccurate.com) on 4/17/11 wrote:
---------------------------
>EduardoS (no@spam.com) on 4/17/11 wrote:
>---------------------------
>>>Here is another thing we don't know about gpgpu. How *reliable* are results calculated by gpgpu?
>>
>>If your code relies on 1+1=2 then it's very reliable.
>>
>>GPUs are deterministic, all integer operations will give the same results a CPU
>>would, fp operations may differ from CPU results, but the same input will always
>>return the same result up to (I hope for a doc quoting the value) a given precision,
>>if you don't rely on the bits beyond this point it's reliable.
>>
>I know the Evergreen (5xxx and 6000-6899) and NI/SI (6900-6999) shaders are currently
>fully IEEE FP compliant with one exception, and that is a certain type of interrupt
>handling. For numerical stuff, it is complete, for the programming side, that is the one problem.
Really?
*Fully* compliant? As in <= 1/2 ULP precision guarantees for add, subtract, divide, multiply *and* sqrt?
Denormal support?
+-0 and +- infinity correctly generated and handled?
I'm very skeptical.
-- Ian.
---------------------------
>EduardoS (no@spam.com) on 4/17/11 wrote:
>---------------------------
>>>Here is another thing we don't know about gpgpu. How *reliable* are results calculated by gpgpu?
>>
>>If your code relies on 1+1=2 then it's very reliable.
>>
>>GPUs are deterministic, all integer operations will give the same results a CPU
>>would, fp operations may differ from CPU results, but the same input will always
>>return the same result up to (I hope for a doc quoting the value) a given precision,
>>if you don't rely on the bits beyond this point it's reliable.
>>
>I know the Evergreen (5xxx and 6000-6899) and NI/SI (6900-6999) shaders are currently
>fully IEEE FP compliant with one exception, and that is a certain type of interrupt
>handling. For numerical stuff, it is complete, for the programming side, that is the one problem.
Really?
*Fully* compliant? As in <= 1/2 ULP precision guarantees for add, subtract, divide, multiply *and* sqrt?
Denormal support?
+-0 and +- infinity correctly generated and handled?
I'm very skeptical.
-- Ian.
Topic | Posted By | Date |
---|---|---|
New Article: Predicting GPU Performance for AMD and Nvidia | David Kanter | 2011/04/12 12:55 AM |
Graph is not red-green colorblind friendly (NT) | RatherNotSay | 2011/04/12 04:51 AM |
Fixed | David Kanter | 2011/04/12 09:46 AM |
New Article: Predicting GPU Performance for AMD and Nvidia | James | 2011/04/12 01:30 PM |
New Article: Predicting GPU Performance for AMD and Nvidia | David Kanter | 2011/04/12 03:51 PM |
Try HD6450 or HD6850 | EduardoS | 2011/04/12 04:31 PM |
Try HD6450 or HD6850 | David Kanter | 2011/04/13 11:25 AM |
Try HD6450 or HD6850 | EduardoS | 2011/04/13 04:20 PM |
of cause | Moritz | 2011/04/14 09:03 AM |
of cause | EduardoS | 2011/04/14 02:55 PM |
Barts = 5D | Moritz | 2011/04/14 10:26 PM |
Barts = 5D | Antti-Ville Tuunainen | 2011/04/15 01:38 AM |
Limiting fixed function units | Moritz | 2011/04/15 05:28 AM |
Limiting fixed function units | Vincent Diepeveen | 2011/04/20 03:38 AM |
lack of detail | Moritz | 2011/04/20 10:24 AM |
lack of detail | EduardoS | 2011/04/20 12:45 PM |
gpgpu | Vincent Diepeveen | 2011/04/16 03:10 AM |
gpgpu | EduardoS | 2011/04/17 01:31 PM |
gpgpu | Groo | 2011/04/17 01:58 PM |
gpgpu | EduardoS | 2011/04/17 02:08 PM |
gpgpu | Ian Ameline | 2011/04/18 04:55 PM |
gpgpu | Ping-Che Chen | 2011/04/19 01:59 AM |
GPU numerical compliance | Sylvain Collange | 2011/04/19 12:38 PM |
GPU numerical compliance | Vincent Diepeveen | 2011/04/20 03:17 AM |
gpgpu | Vincent Diepeveen | 2011/04/20 03:02 AM |
gpgpu and core counts | Heikki Kultala | 2011/04/20 05:41 AM |
gpgpu and core counts | Vincent Diepeveen | 2011/04/20 06:52 AM |
gpgpu and core counts | none | 2011/04/20 08:05 AM |
gpgpu and core counts | EduardoS | 2011/04/20 12:36 PM |
gpgpu and core counts | Heikki Kultala | 2011/04/20 11:16 AM |
gpgpu and core counts | EduardoS | 2011/04/20 12:34 PM |
gpgpu and core counts | Heikki Kultala | 2011/04/20 08:24 PM |
gpgpu and core counts | EduardoS | 2011/04/20 09:55 PM |
gpgpu and core counts | Heikki Kultala | 2011/04/21 07:48 AM |
gpgpu and core counts | EduardoS | 2011/04/22 02:41 PM |
AMD Compute and Texture Fetch | David Kanter | 2011/04/21 11:42 AM |
AMD Compute and Texture Fetch | Vincent Diepeveen | 2011/04/22 02:14 AM |
AMD Compute and Texture Fetch | David Kanter | 2011/04/22 11:53 AM |
AMD Compute and Texture Fetch | EduardoS | 2011/04/22 02:46 PM |
AMD Compute and Texture Fetch | David Kanter | 2011/04/22 03:02 PM |
AMD Compute and Texture Fetch | EduardoS | 2011/04/22 03:18 PM |
AMD Compute and Texture Fetch | anon | 2011/04/22 04:30 PM |
AMD Compute and Texture Fetch | David Kanter | 2011/04/22 10:17 PM |
gpgpu and core counts | Vincent Diepeveen | 2011/04/20 01:12 PM |
gpgpu and core counts | Heikki Kultala | 2011/04/21 11:23 AM |
gpgpu and core counts | Vincent Diepeveen | 2011/04/22 03:11 AM |
Keep the crazy politics out of this | David Kanter | 2011/04/22 09:39 AM |
Keep the crazy politics out of this | Vincent Diepeveen | 2011/04/22 10:12 AM |
Keep the crazy politics out of this | David Kanter | 2011/04/22 11:44 AM |
gpgpu and core counts | Jouni Osmala | 2011/04/22 12:06 PM |
gpgpu | EduardoS | 2011/04/20 12:59 PM |
gpgpu | Vincent Diepeveen | 2011/04/20 01:37 PM |
gpgpu | EduardoS | 2011/04/20 06:27 PM |
gpgpu | Vincent Diepeveen | 2011/04/21 03:06 AM |
gpgpu | EduardoS | 2011/04/22 03:00 PM |
New Article: Predicting GPU Performance for AMD and Nvidia | PiedPiper | 2011/04/12 11:05 PM |
New Article: Predicting GPU Performance for AMD and Nvidia | David Kanter | 2011/04/12 11:42 PM |
New Article: Predicting GPU Performance for AMD and Nvidia | MS | 2011/04/15 06:04 AM |
New Article: Predicting GPU Performance for AMD and Nvidia | Kevin G | 2011/04/16 03:25 AM |
New Article: Predicting GPU Performance for AMD and Nvidia | David Kanter | 2011/04/16 09:42 AM |
New Article: Predicting GPU Performance for AMD and Nvidia | Vincent Diepeveen | 2011/04/20 03:20 AM |
memory | Moritz | 2011/04/14 10:03 PM |
memory - more | Moritz | 2011/04/16 12:11 AM |
New Article: Predicting GPU Performance for AMD and Nvidia | Kevin G | 2011/04/14 12:30 PM |