Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
toad.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mastodon server operated by David Troy, a tech pioneer and investigative journalist addressing threats to democracy. Thoughtful participation and discussion welcome.

Administered by:

Server stats:

273
active users

toad.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.8

#cuda

3 posts2 participants0 posts today
Public
Chris Vitalos

Like many #Linux users, I use that #OS to extend old #PC #hardware lifecycle. My #Dell #Optiplex 9020 includes a Pascal based #GPU.

My issue is I cannot install a more modern GPU because of physical constraints with the chassis itself.

>Maxwell, Pascal, and Volta architectures are now feature-complete with no further enhancements planned. ... Users should plan migration .., as future toolkits will be unable to target [these] GPUs. 1/

docs.nvidia.com/cuda/cuda-tool

docs.nvidia.com1. CUDA 12.9 Release Notes — Release Notes 12.9 documentationThe Release Notes for the CUDA Toolkit.
#Nvidia#CUDA
Public
Hacker News 50

Faster sorting with SIMD CUDA intrinsics (2024)

Link: winwang.blog/posts/bitonic-sor
Discussion: news.ycombinator.com/item?id=4

winwang.blog · Faster sorting with SIMD CUDA intrinsicsFull code on Github: https://github.com/wiwa/blog-code/ Hi Link to heading Recently, I finished a batch at the Recurse Center… is what I would have said if this post were written when I intended to write it (i.e. 3 months ago). My project there focused on a questionable application of CUDA (mostly irrelevant to this post), but it got me thinking more about other GPU-friendly algorithms. Instead of my Recurse project (which I hope to write about in a later post), I want to simply begin writing about technical stuff I’ve played around with.
#cuda
Public
Hacker News 50

PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch

Link: arxiv.org/abs/2503.19779
Discussion: news.ycombinator.com/item?id=4

arXiv.orgPyGraph: Robust Compiler Support for CUDA Graphs in PyTorchCUDA Graphs -- a recent hardware feature introduced for NVIDIA GPUs -- aim to reduce CPU launch overhead by capturing and launching a series of GPU tasks (kernels) as a DAG. However, deploying CUDA Graphs faces several challenges today due to the static structure of a graph. It also incurs performance overhead due to data copy. In fact, we show a counter-intuitive result -- deploying CUDA Graphs hurts performance in many cases. We introduce PyGraph, a novel approach to automatically harness the power of CUDA Graphs within PyTorch2. Driven by three key observations, PyGraph embodies three novel optimizations: it enables wider deployment of CUDA Graphs, reduces GPU kernel parameter copy overheads, and selectively deploys CUDA Graphs based on a cost-benefit analysis. PyGraph seamlessly integrates with PyTorch2's compilation toolchain, enabling efficient use of CUDA Graphs without manual modifications to the code. We evaluate PyGraph across various machine learning benchmarks, demonstrating substantial performance improvements over PyTorch2.
#cuda
Public
Eva Winterschön

💻 FreeBSD CUDA drm-61-kmod 💻

"Just going to test the current pkg driver, this will only take a second...", the old refrain goes. Surely, it will not punt away an hour or so of messing about in loader.conf on this EPYC system...

- Here are some notes to back-track a botched/crashing driver kernel panic situation.
- Standard stuff, nothing new over the years here with loader prompt.
- A few directives are specific to this system, though may provide a useful general reference.
- The server has an integrated GPU in addition to nvidia pcie, so a module blacklist for the "amdgpu" driver is necessary (EPYC 4564P).

Step 1: during boot-up, "exit to loader prompt"
Step 2: set/unset the values as needed at the loader prompt

unset nvidia_load
unset nvidia_modeset_load
unset hw.nvidiadrm.modeset
set module_blacklist=amdgpu,nvidia,nvidia_modeset
set machdep.hyperthreading_intr_allowed=0
set verbose_loading=YES
set boot_verbose=YES
set acpi_dsdt_load=YES
set audit_event_load=YES
kern.consmsgbuf_size=1048576
set loader_menu_title=waffenschwester
boot

Step 3: login to standard tty shell
Step 4: edit /boot/loader.conf (and maybe .local)
Step 5: edit /etc/rc.conf (and maybe .local)
Step 6: debug the vast output from kern.consmsgbuf logs

Screenshot of an IPMI terminal, showing the FreeBSD kernel loader prompt, with variables printed, and the discussed variables being set. After this stage, the boot process resumes.
#freebsd#nvidia#cuda
ExploreLive feeds
About