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

GitHub - Rust-GPU/Rust-CUDA：使用 Rust 撰寫和執行快速 GPU 程式碼的生態系統
➤ 打造 Rust 在 GPU 計算領域的地位
✤ https://github.com/Rust-GPU/Rust-CUDA
Rust-CUDA 是一個專案，旨在使 Rust 成為使用 CUDA 工具包進行高效能 GPU 計算的首選語言。它提供了一系列函式庫和工具，可將 Rust 編譯為快速的 PTX 程式碼，並與現有的 CUDA 函式庫整合。 該專案包含 `rustc_codegen_nvvm` (Rust 編譯器後端)、`cuda_std` (GPU 端功能)、`cudnn` (深度神經網路加速)、`cust` (CPU 端 CUDA 功能)、`gpu_rand` (GPU 隨機數產生) 和 `optix` (光線追蹤) 等多個 crates，旨在覆蓋整個 CUDA 生態系統。 儘管目前仍處於早期開發階段，但 Rust-CUDA 旨在克服以往 Rust 與 CUDA 整合的困難，並充分利用 Rust 的優勢，如效能
#開發工具 #GPU #Rust #CUDA

Rust CUDA Project

Link: https://github.com/Rust-GPU/Rust-CUDA
Discussion: https://news.ycombinator.com/item?id=43654881

Rust CUDA Project

https://github.com/Rust-GPU/Rust-CUDA

Nvidia adds native Python support to CUDA

Link: https://thenewstack.io/nvidia-finally-adds-native-python-support-to-cuda/
Discussion: https://news.ycombinator.com/item?id=43581584

Nvidia adds native Python support to CUDA

https://thenewstack.io/nvidia-finally-adds-native-python-support-to-cuda/

My brain is absolutely fried.
Today is the last day of coursework submissions for this semester. What a hectic month.
DNN with PyTorch, Brain model parallelisation with MPI, SYCL and OpenMP offloading of percolation models,hand optimizing serial codes for performance.
Two submissions due today. Submitted one and finalising my report for the second one.
Definitely having a pint after this

Ask HN: Why hasn't AMD made a viable CUDA alternative?

Discussion: https://news.ycombinator.com/item?id=43547309

It seems that #Vulkan could be the real alternative for using #AI on GPUs or CPUs of any brand, without necessarily having to rely on #CUDA or #AMD's #ROCm. I thought #SYCL was the alternative. This might finally free us from of monopoly #Nvidia.
#Khronos

Ported https://salykova.github.io/sgemm-gpu to Vulkan (nice article!)

it's 2x slower than Cuda. That one was tricky to port, (e.g. need to alias shared buffer to allow LDS/STS.128), half of it with AI, 2nd half going over lines 1-by-1

Ported the Kernel 5 from https://seb-v.github.io/optimization/update/2025/01/20/Fast-GPU-Matrix-multiplication.html to Vulkan

It's only 15% slower than Cuda (and it works on AMD)

In both cases, it's quite difficult to reason about SPIR-V ISA, apart the AMD GPU Analyzer that is helping!

Digging deeper

wasmVision 0.3.0 is out! We have some exiting new features for you such as MCP server support, and experimental GPU acceleration for vision models. Performance and stability improvements too. Go get it right now!

#wasm #computervision #opencv #golang #tinygo #rust #clang #mcp #cuda

https://github.com/wasmvision/wasmvision/releases/tag/v0.3.0

NVIDIA GeForce RTX 5060 e 5060 Ti: arrivo imminente
#Aprile2025 #Componenti #CUDA #Gaming #GDDR7 #GeForce #GPU #Hardware #Leak #Notizie #Novità #NVIDIA #NVIDIARTX #PC #RTX5060 #RTX5060Ti #Rumors #SchedeGrafiche #SchedeVideo #TechNews #Tecnologia

https://www.ceotech.it/nvidia-geforce-rtx-5060-e-5060-ti-arrivo-imminente/

Is there any difference between computing AI workloads in Vulkan, OpenCL and CUDA?

I know that some people say that NVIDIA doesn't support (quite well) OpenCL or Vulkan, performance is achieved by using CUDA. But what is the story for other vendors (Intel, AMD, QualComm, Apple) ?

Just got my RSS reader YOShInOn building with uv and running under WSL2 with the Cuda libraries, despite a slight version mismatch... All I gotta do is switch it from arangodb (terrible license) to postgres, and it might have a future... With sentence_transformers running under WSL2 I might even be able to deduplicate the million images in my Fraxinus image sorter

Sorting algorithms with CUDA

Link: https://ashwanirathee.com/blog/2025/sort2/
Discussion: https://news.ycombinator.com/item?id=43338405

Sorting Algorithm with CUDA

https://ashwanirathee.com/blog/2025/sort2/

WgPy: GPU-accelerated NumPy-like array library for web browsers

#CUDA #Python #WebGL #Package

https://hgpu.org/?p=29808

Which language/technology did you use when developing your first parallel program?

#OpenMP? #MPI? #CUDA? #pthreads? #Coarrays? #UPC? Something else?

pyATF: Constraint-Based Auto-Tuning in Python

#OpenCL #CUDA #Performance #AutoTuning #Compilers #Python #Package

https://hgpu.org/?p=29798

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators

#CUDA #CodeGeneration #LLM #DeepLearning #DL #Python #Package

https://hgpu.org/?p=29794