kuterd / nv_isa_solver
Nvidia Instruction Set Specification Generator
☆254Updated 8 months ago
Alternatives and similar repositories for nv_isa_solver:
Users that are interested in nv_isa_solver are comparing it to the libraries listed below
- Learning about CUDA by writing PTX code.☆123Updated last year
- ctypes wrappers for HIP, CUDA, and OpenCL☆128Updated 8 months ago
- ☆432Updated 3 months ago
- Visualization of cache-optimized matrix multiplication☆104Updated 5 years ago
- GPUOcelot: A dynamic compilation framework for PTX☆178Updated last month
- RDNA3 emulator☆52Updated last week
- High-Performance SGEMM on CUDA devices☆85Updated last month
- Tenstorrent MLIR compiler☆100Updated this week
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆63Updated this week
- Fastest kernels written from scratch☆188Updated this week
- Apple GPU microarchitecture☆502Updated 5 months ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆227Updated this week
- An experimental CPU backend for Triton☆99Updated last week
- Tutorials on tinygrad☆352Updated 2 weeks ago
- pytorch from scratch in pure C/CUDA and python☆40Updated 5 months ago
- An unofficial cuda assembler, for all generations of SASS, hopefully :)☆461Updated last year
- A minimal Tensor Processing Unit (TPU) inspired by Google's TPUv1.☆133Updated 7 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.☆71Updated this week
- A framework that support executing unmodified CUDA source code on non-NVIDIA devices.☆115Updated 2 months ago
- Exploring the scalable matrix extension of the Apple M4 processor☆165Updated 4 months ago
- Fast CUDA matrix multiplication from scratch☆659Updated last year
- Development repository for the Triton language and compiler☆109Updated this week
- Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.☆130Updated this week
- LLM training in simple, raw C/HIP for AMD GPUs☆43Updated 5 months ago
- Sniff CUDA ioctls☆190Updated last year
- MLIR-based partitioning system☆71Updated this week
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆39Updated 10 months ago
- CudaPAD is a PTX/SASS viewer for NVIDIA Cuda kernels and provides an on-the-fly view of the assembly.☆115Updated 2 years ago
- ☆72Updated this week