· @dcz
324 followers · 1941 posts · Server fosstodon.org

+ works with ! The dictionary mode at least.

Trying to use brute force fails on the self test.

Still better than clover, which makes the GPU hang up so badly I can't even turn off the computer.

This is awesome cause this ( 2400G) is not supported by . Rusticl is the best I can get right now.

#Rusticl #radeonsi #hashcat #apu #ryzen #rocm #opencl

Last updated 1 year ago

Dr. Moritz Lehmann · @ProjectPhysX
252 followers · 90 posts · Server mast.hpc.social

🧵10/9
On PVC (4x GPU Max 1100), P2P transfer does not work either. Both the implicit and explicit buffer migration variants cut performance in half compared to when sending buffers over the CPU. ❌

#opencl

Last updated 1 year ago

Pekka Jääskeläinen · @pekka
28 followers · 34 posts · Server fosstodon.org

@ProjectPhysX making a massive scaling experiment on LUMI using only (no MPI) is still on our bucket list. Let us know when/if the code base might be more ready for that.

#opencl

Last updated 1 year ago

loic_fejoz · @loic_fejoz
59 followers · 284 posts · Server mastodon.gougere.fr

So deceiving that AI 64 does not support ! Or does it? There is a libOpenCL.so but did not manage to compile anything to use it...🫤
Will have to look now into with but already so few documentation...

#beaglebone #opencl #dsp #c66x

Last updated 1 year ago

Man2Dev :idle: · @Man2Dev
16 followers · 123 posts · Server fosstodon.org

@karolherbst congratulations this is an amazing achievement :blobcatcheer: . I remmber hearing about this on @BrodieOnLinux video and getting so hyped for it :ablobcatattention: .
P.s link to the video: youtube.com/watch?v=Xbb_ytPRip

#mesa #opencl #rust #rustlang #dev #developer

Last updated 1 year ago

athas · @athas
90 followers · 184 posts · Server freeradical.zone

@karolherbst Well, this gave me the motivation to hack my codegen so it doesn't ask for 64-bit atomics unless actually needed (and available). And... rusticl works! At least for some programs (the important visualisation ones), alhough I seem to get NaNs for others (the boring numerical ones). Thanks for your work; now I can finally use again on my AMD laptop.

#opencl

Last updated 1 year ago

Pekka Jääskeläinen · @pekka
24 followers · 29 posts · Server fosstodon.org

chipStar 1.0 released! It's a tool for compiling and running CUDA/HIP applications on SPIR-V-supported OpenCL or LevelZero platforms. v1.0 can already run various HPC applications correctly. See: github.com/CHIP-SPV/chipStar/r

#opencl #levelzero #spirv #cuda #hip

Last updated 1 year ago

Felix LeClair (waiting on HR) · @fclc
442 followers · 1587 posts · Server mast.hpc.social

Another Place could be super useful is for the media server users of the world.

RN migrating to from based on an old discussion with @geerlingguy.

JellyFin seems quite good, works mostly OOTB, with the only issue being the /#Cuda requirement for .

Since I'm running JF as a docker container on a TrueNAS SCALE box, there's no OOTB OpenCL/CUDA support.

The machine in question is running a 12100 and an rx5600xt, with VAAPI working fine

#rusticl #jellyfin #plex #opencl #hdr #tonemaping

Last updated 1 year ago

Sriram Ramkrishna · @sri
87 followers · 328 posts · Server mast.hpc.social

For those who have waited eagerly for the recording of our meetup with @karolherbst - here it is! youtu.be/KUze0JbPSy8
- if you are interested in joining our oneAPI meetup - feel free to subscribe here - meetup.com/oneapi-community-us

Next time we will be meeting with Stephano Cetola who will be talking about RISC-V, onAPI, and other things.

#oneapi #sycl #opencl #rustlang

Last updated 1 year ago

claude · @mathr
318 followers · 3207 posts · Server post.lurk.org

The multidimensional library supports only via (no backend that I could find), and it seems abandoned (doesn't work with GHC newer than 8.10.7, docs mention LLVM 9).

The Haskell multidimensional data parallel array library doesn't support GPU at all as far as I can tell.

I prefer Accelerate's architecture, but Repa seems more maintained.

Repa seems to allow operations:

```
$ ghci -package repa
ghci> :m + Data.Array.Repa
ghci> toList . extract (Z :. 10000000) (Z :. 100) . computeUnboxedS . fromFunction (Z :. (1 :: Int)) $ const (0 :: Int)
[Segmentation fault
$
```

This crash is an out of bounds read, trying to access index 10000000 of an array with one element.

So I started coding a repa-sized wrapper library (I checked Hackage and couldn't find any existing one), that statically ensures things are safe at compilation time. For example, trying to reshape a 3,3 matrix to 5,5 now gives a type error (can't match 9 with 25) instead of a runtime error that the sizes don't match.

#haskell #data #parallel #array #accelerate #gpu #cuda #opencl #repa #unsafe

Last updated 1 year ago

claude · @mathr
318 followers · 3207 posts · Server post.lurk.org

I wrote up some notes on two projects inspired by block diagram algebra progamming language.

One from 2009 (typesafe embedding of FAuSt semantics) that I abandoned shortly afterwards.

One vague idea (FAuSt + + = some kind of video processing thing) that I haven't started work on implementing (and might never), just in the what if thinking stage.

mathr.co.uk/web/faust.html

#faust #dsp #haskell #gridflow #opencl

Last updated 1 year ago

Dr. Moritz Lehmann · @ProjectPhysX
223 followers · 75 posts · Server mast.hpc.social

My ChEESE CoE webinar talk on programming for applications is now uploaded to my YouTube channel and provided with timestamps. Enjoy! 🖖😎🧀
👉 youtu.be/w4HEwdpdTns

#opencl #gpu #hpc

Last updated 1 year ago

AskUbuntu · @askubuntu
142 followers · 1906 posts · Server ubuntu.social

AMD GPU Issues in Ubuntu 22.04.2 LTS: "amdgpu bonaire not supported" & "snd hda intel hsw/bdw hd audio hdmi/dp requires binding with gfx driver"

askubuntu.com/q/1475108/612

#boot #amdgraphics #amdgpu #ubuntudrivers #opencl

Last updated 1 year ago

Phoronix · @phoronix
2801 followers · 2552 posts · Server noc.social
Pekka Jääskeläinen · @pekka
23 followers · 28 posts · Server fosstodon.org

PoCL 4.0 released! Various new features to support more CUDA, HIP and SYCL app inputs via chipStar and DPC++. Also MacOS/CPU support is back and has now a maintainer, and a lot more: github.com/pocl/pocl/releases/

#opencl #HeterogeneousComputing #opensource

Last updated 1 year ago

Dr. Moritz Lehmann · @ProjectPhysX
218 followers · 69 posts · Server mast.hpc.social

New toy has arrived! AMD Instinct with delicious 64GB VRAM 🖖😋 perfect for workloads 🖖🧐🔥

#hpc #mi210 #gpu #opencl

Last updated 1 year ago

Dr. Moritz Lehmann · @ProjectPhysX
217 followers · 66 posts · Server mast.hpc.social

In 2 weeks I'll be hosting a webinar on programming at @cheese_coe Center of Excellence! ✨🧀✨
Register here, it's free: bit.ly/3C3cxey
Looking forward to sharing my knowledge with you! 🖖😎

#opencl #gpu #hpc

Last updated 1 year ago

Felix LeClair(received offers) · @fclc
406 followers · 1276 posts · Server mast.hpc.social

I'll be speaking during the OneAPI dev summit tomorrow, specifically the panel discussion on accelerated computing.

Partially as a meme/Sanity check the challenge of this afternoon:

Can I got from no installs to a GPU accelerated simulation of OpenFOAM using an Arc a770 on Linux?

Plan is 2212, 3.19, 2023.1 and 23 (in case I need to fall back to )

#openfoam #petsc #oneapi #mesa #opencl

Last updated 1 year ago

jeancf · @jeancf
251 followers · 472 posts · Server noc.social

I am considering writing a test suite for "rusticl" ( implementation) and I am wondering how I should name my crate... 🤔 😜
@phoronix

#opencl #rustlang

Last updated 1 year ago

Pekka Jääskeläinen · @pekka
21 followers · 27 posts · Server fosstodon.org

Many of you have waited for this eagerly: PoCL 4.0-rc1 is now ready for testing! github.com/pocl/pocl/releases/ The usual LLVM upgrade, an experimental Level Zero driver, CPU subgroups, prog. scope variables, Unified
Shared Memory, etc. etc! Please test with your favourite platform and OpenCL application!
@thekhronosgroup

#opencl

Last updated 1 year ago