Message boards :
Sixtrack Application :
AVX/AVX2 support
Message board moderation
Author | Message |
---|---|
Send message Joined: 27 Sep 08 Posts: 805 Credit: 650,583,119 RAC: 265,713 |
Hello Eric, Is it possible, to add AVX support to the app, seems like it could offer a significant improvement in floating point calculations? Thanks |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Thanks, noted, will do soonest. now I can finally produce Windows executables again. Eric. |
Send message Joined: 23 Jan 17 Posts: 29 Credit: 375,570 RAC: 0 |
The test execs have and AVX version. From our initial testing there gain is rather small :( But let's see what happens when they are ran on more machines... |
Send message Joined: 27 Sep 08 Posts: 805 Credit: 650,583,119 RAC: 265,713 |
Sorry then, I assumed that this would be a good canditate, from these slides seems like it would need to vectorize well https://twiki.cern.ch/twiki/bin/view/Main/VinInn http://docplayer.net/22964956-Haswell-conundrum-avx-or-not-avx.html |
Send message Joined: 24 Oct 04 Posts: 1118 Credit: 49,728,983 RAC: 13,228 |
Sorry then, I assumed that this would be a good candidate, from these slides seems like it would need to vectorize well Yeah I was wondering about that myself since I have a few Sandybridge https://twiki.cern.ch/twiki/bin/view/LCG/VIAVXBenchMarks |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
I think Kyrre was misunderstood here. SSE2/SSE3 (or pni) gives about a factor of 2 speed up and should always be used when available, which I understand is not always true. I'll check with him as I think he means AVX doesn't give much more. Overall vectorisation/pipelining gives a factor of 2 speedup for SixTrack. (The code was vectorised many years ago for the Cray and IBM VF.) . Eric. |
Send message Joined: 2 May 07 Posts: 2090 Credit: 158,949,569 RAC: 124,837 |
(The code was vectorised many years ago for the Cray and IBM VF.) . Eric. We are so sad, to have this Computer not at home ;-). Or is it not true, because of the Flops of the Computer today? |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Well I think there is a CRAY in Lausanne Museum :-) Today even Cray is using massive parallelisation, with a multitude of "cheap" processors as we predicted many years ago! Mark you I am sure they are doing it very professionally in the great Cray tradition. Eric. |
Send message Joined: 24 Oct 04 Posts: 1118 Credit: 49,728,983 RAC: 13,228 |
These SixTrack tasks remind me of 2004 with these tasks that run about 60 seconds or less......when you watch them they look like a pni Error but when you check they are Valids.....but I did have a few that actually ran over 7 hours. Not much to see on the Stderr's but imagine running those multi-core Volunteer Mad Scientist For Life |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Well they may or may not be valid. We are looking very hard at this. It is just very complicated to rerun every "short" task and check whether it is valid or not! But we are trying. Eric. |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
...and sorry, I forgot to say that the files you downlaoded may no longer be on the server, we may no be able to access the user's files either. Hence I am concentrating on tasks/WUs with name wzero_jtbb2cm1....... If you ever spot a null zero length fort.10 I'd be very interested. Eric. |
Send message Joined: 2 May 07 Posts: 2090 Credit: 158,949,569 RAC: 124,837 |
Those finished are waiting for the second finished task. All with more than 40.000 seconds and wzero_jtbb2cm1... https://lhcathome.cern.ch/lhcathome/results.php?userid=75468&offset=0&show_names=0&state=2&appid=1 |
Send message Joined: 18 Dec 15 Posts: 1688 Credit: 103,129,915 RAC: 120,329 |
|
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Well this is actually about the "null" empty results. I have identified them and there are several different causes, platform independent. This will be fixed in our upcoming release. Eric. |
Send message Joined: 27 Sep 08 Posts: 805 Credit: 650,583,119 RAC: 265,713 |
Great news |
Send message Joined: 27 Sep 08 Posts: 805 Credit: 650,583,119 RAC: 265,713 |
Since the new Skylake chips have AVX-512, is this something that the app would benift from? |
Send message Joined: 25 Jan 17 Posts: 27 Credit: 3,258,853 RAC: 0 |
yes |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Yes, but we can't use FMA because of different rounding and numeric portability. Eric. (Since the new Skylake chips have AVX-512, is this something that the app would benefit from?) |
©2024 CERN