ROCK-Kernel-Driver
ROCm
ROCK-Kernel-Driver | ROCm | |
---|---|---|
7 | 198 | |
279 | 3,637 | |
2.2% | - | |
9.5 | 0.0 | |
18 days ago | 5 months ago | |
C | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ROCK-Kernel-Driver
- what are the latest amd gpu drivers
-
How AMD is Fighting NVIDIA with RDNA3 - Chiplet Engineering Explained
No, just dangling documentation on the ROCm/HIP etc repos/sites, and the knowledge that all device DMA used to only support PCIe-a-like within the drivers/firmware, but as per that whitepaper above mentions a lot of effort was put into infinity fabric of CDNA2 so it would be very strange to use it for p2p. That the driver memory topology only recently enabled p2pDMA from what I have been following. This of course would require firmware (if not already there) and userspace to handle such a situation. Hence why I was asking for clearer source on MI250x specifically, and if it was recent.
-
Which distro feels most completed?
Even if people refer to AMDGPU driver as AMD made, it is not AMD but guys from open source, this: https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver which also leads to this: https://www.kernel.org/doc/html/latest/ and https://en.wikipedia.org/wiki/AMDgpu_(Linux_kernel_module)#:~:text=Community%5Bedit%5D,libdrm%2C%20Xorg%2C%20Wayland#:~:text=Community%5Bedit%5D,libdrm%2C%20Xorg%2C%20Wayland). If i got that right. AMDGPU PRO driver is what is installed on Windows a proprietary driver which it seems is built upon AMDGPU open source but this one is signed by AMD... Witch got me thinking as AMD refusing to bring Radeon Software Center to Linux, seems like best thin for open source is to community and companies like Canonical, Rad Hat etc start builtin hardware for open software... a perfect mix of things?
- There is now a dedicated wikipedia ROCm page :)
- What is the situation for AMD GPU drivers on linux?
-
Official ROCm website now lists support for RDNA 2
Plus, if we're going to talk about stuff developers are sick of, how about releasing packages that are broken? https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/pull/117 Kind of pointless to put up a release package if it's going to be obviously broken to this extent. In the end getting this to work still involved manually going in and patching things, both with the driver and then with the runtime libraries for tensorflow, making it not much better than dealing with NVIDIA. Even worse since this at least would've been caught in automated testing.
-
Corectrl doesn't have finer control?
https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/blob/roc-1.9.x/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c#L469
ROCm
-
AMD May Get Across the CUDA Moat
Yep, did exactly that. IMO he threw a fit, even though AMD was working with him squashing bugs. https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...
- ROCm 5.7.0 Release
-
ROCm Is AMD's #1 Priority, Executive Says
Ok, I wonder what's wrong. maybe it's this? https://stackoverflow.com/questions/4959621/error-1001-in-cl...
Nope. Anything about this on the arch wiki? Nope
This bug report[2] from 2021? Maybe I need to update my groups.
[2]: https://github.com/RadeonOpenCompute/ROCm/issues/1411
$ ls -la /dev/kfd
-
Simplifying GPU Application Development with HMM
HMM is, I believe, a Linux feature.
AMD added HMM support in ROCm 5.0 according to this: https://github.com/RadeonOpenCompute/ROCm/blob/develop/CHANG...
-
AMD Ryzen APU turned into a 16GB VRAM GPU and it can run Stable Diffusion
Woot AMD now supports APU? I sold my notebook as i hit a wall when trying rocm [1] Is there a list oft Wirkung apu's ?
[1] https://github.com/RadeonOpenCompute/ROCm/issues/1587
-
Nvidia's CUDA Monopoly
Last I heard he's abandoned working with AMD products.
https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...
-
Nvidia H100 GPUs: Supply and Demand
They're talking about the meltdown he had on stream [1] (in front of the mentioned pirate flag), that ended with him saying he'd stop using AMD hardware [2]. He recanted this two weeks after talking with AMD [3].
Maybe he'll succeed, but this definitely doesn't scream stability to me. I'd be wary of investing money into his ventures (but then I'm not a VC, so what do I know).
[1] https://www.youtube.com/watch?v=Mr0rWJhv9jU
[2] https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...
[3] https://twitter.com/realGeorgeHotz/status/166980346408248934...
-
Open or closed source Nvidia driver?
As for rocm support on consumer devices, AMD wont even clarify what devices are supported. https://github.com/RadeonOpenCompute/ROCm/pull/1738
-
Why Nvidia Keeps Winning: The Rise of an AI Giant
He flamed out, then is back after Lisa Su called him (lmao)
https://geohot.github.io/blog/jekyll/update/2023/05/24/the-t...
https://www.youtube.com/watch?v=Mr0rWJhv9jU
https://github.com/RadeonOpenCompute/ROCm/issues/2198#issuec...
https://geohot.github.io/blog/jekyll/update/2023/06/07/a-div...
On a personal level that youtube doesn't make him come off looking that good... like people are trying to get patches to him and generally soothe him/damage control and he's just being a bit of a manchild. And it sounds like that's the general course of events around a lot of his "efforts".
On the other hand he's not wrong either, having this private build inside AMD and not even validating official, supported configurations for the officially supported non-private builds they show to the world isn't a good look, and that's just the very start of the problems around ROCm. AMD's OpenCL runtime was never stable or good either and every experience I've heard with it was "we spent so much time fighting AMD-specific runtime bugs and specs jank that what we ended up with was essentially vendor-proprietary anyway".
On the other other hand, it sounds like AMD know this is a mess and has some big stability/maturity improvements in the pipeline. It seems clear from some of the smoke coming out of the building that they're cooking on more general ROCm support for RDNA cards, and generally working to patch the maturity and stability issues he's talking about. I hate the "wait for drivers/new software release bro it's gonna fix everything" that surrounds AMD products but in this case I'm at least hopeful they seem to understand the problem, even if it's completely absurdly late.
Some of what he was viewing as "the process happening in secret" was likely people doing rush patches on the latest build to accommodate him, and he comes off as berating them over it. Again, like, that stream just comes off as "mercurial manchild" not coding genius. And everyone knew the driver situation is bad, that's why there's notionally alpha for him to realize here in the first place. He's bumping into moneymakers, and getting mad about it.
-
Disable "SetTensor/CopyTensor" console logging.
I tried to train another model using InceptionResNetV2 and the same issues happens. Also, this happens even using the model.predict() method if using the GPU. Probably this is an issue related to the AMD Radeon RX 6700 XT or some mine misconfiguration. System Inormation: ArchLinux 6.1.32-1-lts - AMD Radeon RX 6700 XT - gfx1031 Opened issues: - https://github.com/RadeonOpenCompute/ROCm/issues/2250 - https://github.com/ROCmSoftwarePlatform/tensorflow-upstream/issues/2125
What are some alternatives?
radeon-profile - Application to read current clocks of ATi Radeon cards (xf86-video-ati, xf86-video-amdgpu)
tensorflow-directml - Fork of TensorFlow accelerated by DirectML
vgpu_unlock - Unlock vGPU functionality for consumer grade GPUs.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
rocm-arch - A collection of Arch Linux PKGBUILDS for the ROCm platform
oneAPI.jl - Julia support for the oneAPI programming toolkit.
SHARK - SHARK - High Performance Machine Learning Distribution
llama.cpp - LLM inference in C/C++
plaidml - PlaidML is a framework for making deep learning work everywhere.
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
tensorflow-upstream - TensorFlow ROCm port
ROCm-OpenCL-Runtime - ROCm OpenOpenCL Runtime