AMD COVID-19 HPC Fund
log in

Advanced search

Message boards : Science : AMD COVID-19 HPC Fund

1 · 2 · Next
Author Message
manalog
Send message
Joined: 5 Oct 15
Posts: 27
Credit: 344,243
RAC: 259
Italy
Message 1940 - Posted: 16 Sep 2020, 17:44:13 UTC

Great news for this project!
https://www.amd.com/en/corporate/hpc-fund
AMD is going to donate computing systems or cloud-based computing capacity as a part of the second round of its COVID-19 HPC Fund initiative.
University of Trento, with the project we are supporting here, Gene@Home, is involved:

“The computational resources that AMD is providing will be inserted in our on-going gene@home project that aims to discover the causal relationships between the expression of genes. In particular, we plan to speed-up specific inquiries about genes interacting with SARS-CoV-2 in collaboration with the medical researchers and students in the Laboratory of Biological Data Mining. The AMD initiative is very timely for us and we expect that it will also push us forward in making further analysis methods feasible“ commented Enrico Blanzieri, professor, Department of Information Engineering and Computer Science, University of Trento.

- Enrico Blanzieri, professor, Department of Information Engineering and Computer Science, University of Trento


I hope these contributions will help to speed the pace of the researches going on this beautiful Boinc project.

Valterc, could you give us some news and details of this operation?
Today the number of "tasks ready to send" is 0... will you get also a new server from AMD?
How is the research going?
Grazie

Jim1348
Send message
Joined: 29 Dec 16
Posts: 44
Credit: 7,094,852
RAC: 12,155
United States
Message 1941 - Posted: 16 Sep 2020, 20:01:38 UTC - in response to Message 1940.
Last modified: 16 Sep 2020, 20:02:28 UTC

Today the number of "tasks ready to send" is 0... will you get also a new server from AMD?

Thanks for posting. I had missed the part about University of Trento.
TN-Grid is one of my favorite projects, but if they can get their work done faster in-house, that is even better.

Falconet
Send message
Joined: 21 Dec 16
Posts: 31
Credit: 692,454
RAC: 660
Portugal
Message 1942 - Posted: 16 Sep 2020, 20:49:17 UTC - in response to Message 1940.
Last modified: 16 Sep 2020, 20:57:51 UTC

Nice!

Yes, an update on overall project status, this AMD donation, COVID-19 work we did several months ago, etc, would be very nice.
____________

manalog
Send message
Joined: 5 Oct 15
Posts: 27
Credit: 344,243
RAC: 259
Italy
Message 1943 - Posted: 16 Sep 2020, 20:59:02 UTC - in response to Message 1942.

I am from Italy too and Universities in my country are going to re-open next week, so perhaps we will have an update soon :)

Profile valterc
Project administrator
Project tester
Send message
Joined: 30 Oct 13
Posts: 465
Credit: 23,358,565
RAC: 9,817
Italy
Message 1944 - Posted: 16 Sep 2020, 22:31:08 UTC - in response to Message 1943.

I'm in vacation right now, actually... anyway, here are some details about the AMD grant (I will also put a note in the news page of the project).
Our gene@home project was chosen by AMD together with a dozen of prestigious institutions and we are very proud of this. We are a small group and our computational power relies basically on the volunteers contribution, without you we weren't able to do the work we did, thank you all.
The grant will give us access, for one year, to two AMD computational nodes, each one equipped with a AMD Epyc "Rome" and 8 AMD Radeon Instinct™ MI50 Accelerators.
This will not solve our well known server problem (it would be too complicated to transfer the server to the new machine and come back to the orginal one after one year) but it will give us a tremendous boost to our in-house computational power, also giving us the opportunity to explore Deep Learning algorithms.

A very brief update on what is going on right now:
A paper describing the results we got some time ago working on genes related to the colon cancer has been accepted by a IEEE journal (more details when it will be officially published, very soon)
We are also preparing another two papers, the first one (it will be submitted to Nature Scientific Data) about the COVID-19 related genes we analyzed a couple of months ago and another one (at a very early stage) about the OneGenE experiment we did on Vitis vinifera

We are continuing to analyze (expand) COVID-19 related genes, at the second level, ie expanding the genes that we found at the first ranking positions in the expansion list of the first batch of genes.

Aurum
Send message
Joined: 18 Jul 18
Posts: 18
Credit: 54,933,844
RAC: 315,127
United States
Message 1946 - Posted: 17 Sep 2020, 7:34:48 UTC - in response to Message 1940.

When I get older losing my hair
Many years from now
Will you still be sending me a Valentine
Birthday greetings bottle of wine
If I'd been out till quarter to three
Would you lock the door
Will you still need me, will you still feed me
When I'm sixty-four

Well 64 was a while back for me but I hope you'll still need us too.
Congratulations on the award!!!
____________

Profile adrianxw
Send message
Joined: 22 Dec 16
Posts: 23
Credit: 3,322,399
RAC: 4,240
Denmark
Message 1947 - Posted: 17 Sep 2020, 10:14:46 UTC

If your new computational resources are sufficient, don't feel the need to "make work" to keep crunchers happy, I have several "silent" projects on my machines, every now and then, one of them pushes a couple of weeks work, then goes silent again. Remember, the crunchers are trying to help you, they should never be a burden.
____________
Wave upon wave of demented avengers march cheerfully out of obscurity into the dream.

Falconet
Send message
Joined: 21 Dec 16
Posts: 31
Credit: 692,454
RAC: 660
Portugal
Message 1948 - Posted: 17 Sep 2020, 15:39:38 UTC - in response to Message 1944.

Thank you very much for this update.

Looking forward to reading those papers and congratulations on the AMD award.
____________

Profile bozz4science
Send message
Joined: 17 May 20
Posts: 10
Credit: 85,386
RAC: 231
Germany
Message 1949 - Posted: 17 Sep 2020, 16:34:41 UTC

Great accomplishment! Also looking forward to the mentioned papers!

Profile valterc
Project administrator
Project tester
Send message
Joined: 30 Oct 13
Posts: 465
Credit: 23,358,565
RAC: 9,817
Italy
Message 1950 - Posted: 17 Sep 2020, 21:57:57 UTC - in response to Message 1947.
Last modified: 17 Sep 2020, 21:59:09 UTC

If your new computational resources are sufficient, don't feel the need to "make work" to keep crunchers happy, I have several "silent" projects on my machines, every now and then, one of them pushes a couple of weeks work, then goes silent again. Remember, the crunchers are trying to help you, they should never be a burden.

The AMD grant is an important temporary boost to our computational resources that will hopefully help us to explore new scientific frontiers. The gene@home project doesn't have a deadline. Our algorithms are very "generic", they can easily be applied to other organisms, other datasets (differently built) of the same organism, not only in the biological field, they can be useful whenever you have a lot of variables, each one with different experimental values and you need to find causal relationships among them. The algorithm itself could also be improved, others may be added.
We will continue to move on, with your help.

Profile Bill F
Avatar
Send message
Joined: 3 Apr 17
Posts: 25
Credit: 416,357
RAC: 824
United States
Message 1951 - Posted: 18 Sep 2020, 2:32:28 UTC - in response to Message 1950.

If your new computational resources are sufficient, don't feel the need to "make work" to keep crunchers happy, I have several "silent" projects on my machines, every now and then, one of them pushes a couple of weeks work, then goes silent again. Remember, the crunchers are trying to help you, they should never be a burden.

The AMD grant is an important temporary boost to our computational resources that will hopefully help us to explore new scientific frontiers. The gene@home project doesn't have a deadline. Our algorithms are very "generic", they can easily be applied to other organisms, other datasets (differently built) of the same organism, not only in the biological field, they can be useful whenever you have a lot of variables, each one with different experimental values and you need to find causal relationships among them. The algorithm itself could also be improved, others may be added.
We will continue to move on, with your help.


Thank you for that last reply it gives us direction and reassurance that we will have a value moving forward.

Bill F
Dallas TX
____________

Profile [VENETO] boboviz
Send message
Joined: 12 Dec 13
Posts: 163
Credit: 2,317,244
RAC: 411
Italy
Message 1952 - Posted: 18 Sep 2020, 7:19:32 UTC - in response to Message 1944.

The grant will give us access, for one year, to two AMD computational nodes, each one equipped with a AMD Epyc "Rome" and 8 AMD Radeon Instinct™ MI50 Accelerators.

Mmm, smell like an OpenCl client.... :-P

Jim1348
Send message
Joined: 29 Dec 16
Posts: 44
Credit: 7,094,852
RAC: 12,155
United States
Message 1953 - Posted: 18 Sep 2020, 12:58:36 UTC - in response to Message 1952.

Mmm, smell like an OpenCl client.... :-P

It must have been San Zeno who interceded on your behalf, proving that science and religion mix just fine.

Falconet
Send message
Joined: 21 Dec 16
Posts: 31
Credit: 692,454
RAC: 660
Portugal
Message 1954 - Posted: 18 Sep 2020, 13:51:54 UTC

OpenCL, there was someone working on that but the last update was in April.


http://gene.disi.unitn.it/test/forum_thread.php?id=269&postid=1774#1774
____________

Profile bozz4science
Send message
Joined: 17 May 20
Posts: 10
Credit: 85,386
RAC: 231
Germany
Message 1973 - Posted: 30 Sep 2020, 10:15:02 UTC - in response to Message 1954.
Last modified: 30 Sep 2020, 10:21:19 UTC

Well, those AMD Radeon Instinct accelerators are real compute beasts! Those 8 will be doing more combined than the rest of us :) That should be a incredible speedup in WU turnover.

The dataset we are using right now is very big, a floating point matrix 87554x1829, it's size on the hard disk is ~0.5Gb and contains, for many genes, different isoforms/transcripts. The computational time for an algorithm's iteration, because of its 'complexity', is longer than the previous experiments.

Any single gene expansion is packed up into 294 workunits. Any workunit you receive has a name like this: 142041_Hs_T155402-MAP1B_wu-(1 to 294), a counter, Hs, an internal T code, a mnemonic for the gene/isoform. The T code is just a shortcut for the gene coordinates, for example T155402 is chr5:71403265..71403276,+


Considering the original announcement of the experiment back own 2018, if I am not mistaken the dataset is a floating point matrix. Not knowing exactly what precision is needed for those computations (F16/32/64 precision), with 8 x Radeon Instinct MI 50 accelerator compute units, the peak compute capability at F16 would be 212 TFLOPs, the min at F64 at 52.8 TFLOPs. (Data according to https://www.amd.com/en/products/professional-graphics/instinct-mi50-32gb)

As of today (09/30) on the server page:
16771.51 GFLOPs of all volunteers which translates to ~16.8 TFLOPs.

The ratio by which AMD's sponsored accelerators surpass the crunchers' current computing power is a whopping ~3.1 x (at the lower F64 end).

Hope there is no flaw in my quick calculations.... If this were true anyway, that would be awesome for TN-Grid!!

... and if there is sth to the rumour of a GPU client application to be eventually deployed on TN-Grid, even my ancient GTX 750 Ti could do wonders in terms of compute capability compared to the current CPU-only powered compute force of us crunchers.

By no means I want to reignite the whole GPU/CPU debate that I am well aware of, but rather highlight the awesome performance boost through AMD's sponsored hardware as well as color this bright future of what could become reality soon.... Who knows? :)
____________

Jozef J
Send message
Joined: 22 Jan 15
Posts: 1
Credit: 160,860
RAC: 0
China
Message 1978 - Posted: 4 Oct 2020, 10:19:17 UTC

still no test app for amd cards have many 7970 witch wait for app... realy i think there is not development,becouse not updating abotu booth, HPC and also covid gpu app for us-volunters
also that "amd 19 hpc" still not running..
what they waiting for?
or development for covid app i slowed with covid..)) they will make app after covid,,,lol

Falconet
Send message
Joined: 21 Dec 16
Posts: 31
Credit: 692,454
RAC: 660
Portugal
Message 1979 - Posted: 4 Oct 2020, 10:30:24 UTC - in response to Message 1978.

There is no GPU app available at TN-Grid.
____________

Peter Hucker
Send message
Joined: 29 Sep 17
Posts: 13
Credit: 114,262
RAC: 3,655
United Kingdom
Message 1987 - Posted: 10 Oct 2020, 11:06:29 UTC - in response to Message 1979.

There is no GPU app available at TN-Grid.


So what is running on the Radeons AMD lent you?

Peter Hucker
Send message
Joined: 29 Sep 17
Posts: 13
Credit: 114,262
RAC: 3,655
United Kingdom
Message 1990 - Posted: 10 Oct 2020, 12:25:46 UTC - in response to Message 1973.

Considering the original announcement of the experiment back own 2018, if I am not mistaken the dataset is a floating point matrix. Not knowing exactly what precision is needed for those computations (F16/32/64 precision), with 8 x Radeon Instinct MI 50 accelerator compute units, the peak compute capability at F16 would be 212 TFLOPs, the min at F64 at 52.8 TFLOPs. (Data according to https://www.amd.com/en/products/professional-graphics/instinct-mi50-32gb)

As of today (09/30) on the server page:
16771.51 GFLOPs of all volunteers which translates to ~16.8 TFLOPs.

The ratio by which AMD's sponsored accelerators surpass the crunchers' current computing power is a whopping ~3.1 x (at the lower F64 end).

Hope there is no flaw in my quick calculations.... If this were true anyway, that would be awesome for TN-Grid!!


TN Grid only has 683 users with recent credit. If it was publicised more, there would be more users. It's not in the list of projects to choose within Boinc, or here: https://boinc.berkeley.edu/projects.php I only heard about this project through a mention on another project's forum.

JaviF
Send message
Joined: 14 May 19
Posts: 29
Credit: 0
RAC: 0
Spain
Message 1991 - Posted: 10 Oct 2020, 15:16:32 UTC - in response to Message 1990.

They dont want to.
Server cant really produce enough WUs for more users

1 · 2 · Next
Post to thread

Message boards : Science : AMD COVID-19 HPC Fund


Main page · Your account · Message boards


Copyright © 2020 CNR-TN & UniTN