Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.

Administered by:

Server stats:

15K
active users

mstdn.social: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.4

#gpgpu

0 posts0 participants0 posts today
Public
Habr

Ведущий разработчик ChatGPT и его новый проект — Безопасный Сверхинтеллект

Многие знают об Илье Суцкевере только то, что он выдающийся учёный и программист, родился в СССР, соосновал OpenAI и входит в число тех, кто в 2023 году изгнал из компании менеджера Сэма Альтмана. А когда того вернули, Суцкевер уволился по собственному желанию в новый стартап Safe Superintelligence («Безопасный Сверхинтеллект»). Илья Суцкевер действительно организовал OpenAI вместе с Маском, Брокманом, Альтманом и другими единомышленниками, причём был главным техническим гением в компании. Ведущий учёный OpenAI сыграл ключевую роль в разработке ChatGPT и других продуктов. Сейчас Илье всего 38 лет — совсем немного для звезды мировой величины.

habr.com/ru/companies/ruvds/ar

#Илья_Суцкевер #Ilya_Sutskever #OpenAI #10x_engineer #AlexNet #Safe_Superintelligence #ImageNet #неокогнитрон #GPU #GPGPU #CUDA #компьютерное_зрение #LeNet #Nvidia_GTX 580 #DNNResearch #Google_Brain #Алекс_Крижевски #Джеффри_Хинтон #Seq2seq #TensorFlow #AlphaGo #Томаш_Миколов #Word2vec #fewshot_learning #машина_Больцмана #сверхинтеллект #GPT #ChatGPT #ruvds_статьи

ХабрВедущий разработчик ChatGPT и его новый проект — Безопасный СверхинтеллектМногие знают об Илье Суцкевере только то, что он выдающийся учёный и программист, родился в СССР, соосновал OpenAI и входит в число тех, кто в 2023 году изгнал из компании менеджера Сэма Альтмана. А...
Public *
Dr. Moritz Lehmann

Hot Aisle's 8x AMD #MI300X server is the fastest computer I've ever tested in #FluidX3D #CFD, achieving a peak #LBM performance of 205 GLUPs/s, and a combined VRAM bandwidth of 23 TB/s. 🖖🤯
The #RTX 5090 looks like a toy in comparison.

MI300X beats even Nvidia's GH200 94GB. This marks a very fascinating inflection point in #GPGPU: #CUDA is not the performance leader anymore. 🖖😛
You need a cross-vendor language like #OpenCL to leverage its power.

FluidX3D on #GitHub: github.com/ProjectPhysX/FluidX

FluidX3D benchmarks: the 8x AMD MI300X system leaves every other benchmarked computer behind in the dust.
how 8x MI300X show up in OpenCL
Public
Giuseppe Bilotta

First day of the #GPGPU course at #UniCT. Class is small, but students seem curious, gave me the opportunity to discuss in more details some things that usually go unmentioned. Hopefully it'll hold.

Only negative side, I had to take a longer route home because the park between my house and the university was closed 8-(

Public
Giuseppe Bilotta

I'm getting the material ready for my upcoming #GPGPU course that starts on March. Even though I most probably won't get to it,I also checked my trivial #SYCL programs. Apparently the 2025.0 version of the #Intel #OneAPI #DPCPP runtime doesn't like any #OpenCL platform except Intel's own (I have two other platforms that support #SPIRV, so why aren't they showing up? From the documentation I can find online this should be sufficient, but apparently it's not …)

Public
Anthony Cowley

This look at how many HLSL instructions different variations of an endian swap compile to with AMD tooling is... well, frankly, it's upsetting. All variations are similar, but compile down to anywhere from 1 to 13 IR ops. Contorting code to trigger desired compilation paths is familar to many GHC Haskellers, but it's an incredible deterrent to prioritizing performance. martinfullerblog.wordpress.com

Martin Fuller's Graphics Ramblings · Massaging the Shader Compiler to emit Optimum InstructionsModern GPU’s feature sophisticated instruction sets for executing shaders. However this blog details how difficult and unintuiative it can be to have the shader compiler leverage the optimum …
#gpgpu
Replied in thread
Public
Kevin Karhan :verified:

@enigmatico @lispi314 @kimapr @bunnybeam case in point:

  • #Bloatedness was the original post topic and yes, due to #TechBros "#BuildFastBreakThings" mentality, #Bloatware is increasing given that a shitty bloated 50+MB "#WebApp" with like nw.js is easy to slap together (and yes I did so myself!) than to put in way more thought and effort (as you can see on the slow progression of OS/1337...

  • Yes, #Accessibility is something that needs to be taken more seriously and it's good to see that there's at least some attemots at making #accessibility mandatory (at least in #Germany, where I know from some insider that a big telco is investing a lot in that!) for a growng number of industries and websites...

  • And whilst one can slap an #RTX5090 on any laptop that has a fully-functional #ExpressCard slot (with #PCIe interface, using some janky adaptors!) that'll certainly not make sense beyond some #CUDA or other #GPGPU-style workloads as it's bottlenecked to a single PCIe lane of 2.0 (500MB/s) or just 1.0a(250MB/s) speeds.

Needless to say there is a need to THINN DOWN things cuz the current speed of #Enshittifcation and bloatedness combined with #AntiRepairDesign and overpriced yet worse #tech in general makes it unsustainable for an ever increasing population!

  • Not everyone wants (or even can!) indebt themselves just to have a phone or laptop!

Should we aim for more "#FrugslComputing"?

  • Abdolutely!

Is it realistic to expect things to be in a perfectly accessible TUI that ebery screenreader can handle?

  • No!

That being said the apathy of consumers is real, and very frustrating:

People get nudged into accepting all the bs and it really pisses me off because they want me to look like ab outsider / asshole for not submitting to #consumerism and #unsustainable shite...

ぷにすきーENIGMATICO :flag_bisexual: :flag_nonbinary: (@enigmatico)I get this is a joke, but here is the thing (aside of the joke). People doesnt use crappy laptops anymore. People moves on to phones/tablets, or if they want something more serious, something like a gamer PC. Most people will buy a console if they want to play games though. In that context, nobody cares anymore about bloat. If you are a developer its easier for you to use some bloaty framework that gets the job done in a couple days, because at the end of the day, if you're going to be exploited and crunched to death, you might as well make it as short as possible. And as a consumer, nobody really cares. You buy whatever allows you to do what you wwant and thats it. Or whatever your pocket allows you. And to be completely honest with you all, this has always been like this. You have to do with what you have. Could the world be better if everyone used pure C and assembly? Maybe... if companies had the intention to spend years developing ttheir products and fixing critical bugs before launch. By the time of the launch they would be obsolete. Kinda what happen to Duke Nukem Forever. RN: (📎1)
Continued thread
Public
Oblomov

Even better, in the afternoon I managed to find a workaround for my #GPGPU software building but hanging when trying to run it, which seems to be related to an issue with some versions of the #AMD software stack and many integrated GPUs, not just the #SteamDeck specifically. So exporting the HSA_ENABLE_SDMA=0 environment vriable was sufficient to get my software running again. I'm dropping the information here in case others find it useful.

#ROCm #GPU #APU #HIP

2/2

Continued thread
Public *
Giuseppe Bilotta

It's out, if anyone is curious

doi.org/10.1002/cpe.8313

This is a “how to” guide. #GPUSPH, as the name suggests, was designed from the ground up to run on #GPU (w/ #CUDA, for historical reasons). We wrote a CPU version a long time ago for a publication that required a comparison, but it was never maintained. In 2021, I finally took the plunge, and taking inspiration from #SYCL, adapted the device code in functor form, so that it could be “trivially” compiled for CPU as well.

#HPC#GPGPU
Public
Anthony Cowley

Here’s hoping that the transition of #Rust #GPU to community ownership goes well! The intention to focus on #GPGPU is more than welcome, as I feel the development of some GPU programming ecosystems has been held back by a too-narrow focus on traditional GPU graphics techniques. The dream is to be able to write CUDA-like Rust that can target hardware from multiple vendors!

rust-gpu.github.io/blog/transi

rust-gpu.github.ioRust GPU Transitions to Community Ownership |
Public
Karsten Schmidt

Uploaded a new demo/example showing how to perform GPU-side data reductions using thi.ng/shader-ast & thi.ng/webgl multi-pass pipeline. Arbitrary reduction functions supported. If there's interest, this could be expanded & packaged up as library... 90% of this example is boiler plate, 9.9% benchmarking & debug outputs...

Demo:
demo.thi.ng/umbrella/gpgpu-red

Source code:
github.com/thi-ng/umbrella/blo

Readme w/ benchmark results:
github.com/thi-ng/umbrella/tre

Related discussion:
github.com/thi-ng/umbrella/iss

Screenshot of linked readme with benchmark results: Using 512x512 input texture @ MBA M1 2020, 16GB Chrome 126.0.6478.127: benchmarking: GPU warmup... 1.50ms (100 runs) total: 111.30ms, runs: 1000 (@ 1 calls/iter) freq: 8984.73 ops/sec mean: 0.11ms, median: 0.00ms, range: [0.00..40.00] q1: 0.00ms, q3: 0.00ms sd: 1537.52% benchmarking: CPU warmup... 104.20ms (100 runs) total: 1462.30ms, runs: 1000 (@ 1 calls/iter) freq: 683.85 ops/sec mean: 1.46ms, median: 1.60ms, range: [0.90..1.90] q1: 1.10ms, q3: 1.70ms sd: 20.89% Firefox 128.0 benchmarking: GPU warmup... 1.00ms (100 runs) total: 181.00ms, runs: 1000 (@ 1 calls/iter) freq: 5524.86 ops/sec mean: 0.18ms, median: 0.00ms, range: [0.00..176.00] q1: 0.00ms, q3: 0.00ms sd: 3073.54% benchmarking: CPU warmup... 116.00ms (100 runs) total: 1076.00ms, runs: 1000 (@ 1 calls/iter) freq: 929.37 ops/sec mean: 1.08ms, median: 1.00ms, range: [0.00..2.00] q1: 1.00ms, q3: 1.00ms sd: 38.57%
#ThingUmbrella#WebGL#ShaderAST
Public *
The Great Refactoring

Bringing C++ to Godot with GDExtensions

After playing with Godot within its own rules, I decided to check out what is the experience of bringing in external C++ code into a Godot project through their GDExtensions system. Using it, I bring over two different implementations of toyBrot into a regular Godot project. One with C++ threads and another with OpenCL, pushing Godot being its […]

https://vilelasagna.ddns.net/coding/bringing-c-to-godot-with-gdextensions/

By: @vilelasagna@mastodon.gamedev.place
#c_ #coding #define #else #endif #GDExtensions #Godot #godotengine #GPGPU #ifndef #include #multithreading #OpenCL

GIF
A screenshot of a code editor showing a CMakeLists.txt file in the godot-cpp directory
Public
Giuseppe Bilotta

It's official now: I hate #NUMA and variable frequency.

This is re: fediscience.org/@giuseppebilot

It might just be that I'm more proficient analyzing and working around #GPU quirks (happens, when you do mostly #GPGPU for more than a decade) than #CPU, but there's so many weird things happening on this machine that I don't know where to start from.

FediScience.orgGiuseppe Bilotta (@giuseppebilotta@fediscience.org)One of the reviewers for the manuscript on introducing CPU support in #GPUSPH asked for scalability tests on more than 8 cores (when I originally wrote the whole thing the only decent CPU I had at hand was an AMD Ryzen 7 3700X 8-Core Processor). It's a reasonable request, so I've been running tests on the new server we got at #INGV, that sports a dual AMD EPYC 7713 64-Core Processor. The most interesting so far has been that GPUSPH does seem to scale decently, but the baseline is lower. #HPC
ExploreLive feeds
About