seb-v / fp32_sgemm_amdLinks
Super fast FP32 matrix multiplication on RDNA3
☆68Updated 3 months ago
Alternatives and similar repositories for fp32_sgemm_amd
Users that are interested in fp32_sgemm_amd are comparing it to the libraries listed below
Sorting:
- High-Performance SGEMM on CUDA devices☆97Updated 5 months ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆107Updated last month
- GPUOcelot: A dynamic compilation framework for PTX☆202Updated 5 months ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 4 months ago
- ☆20Updated 2 months ago
- rocWMMA☆119Updated this week
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆67Updated this week
- monorepo for rocm libraries☆39Updated this week
- AI Tensor Engine for ROCm☆232Updated this week
- Development repository for the Triton language and compiler☆125Updated this week
- ☆48Updated last week
- MLIR-based partitioning system☆105Updated this week
- amdgpu example code in hip/asm☆35Updated last month
- An interactive web-based tool for exploring intermediate representations of PyTorch and Triton models☆46Updated 2 weeks ago
- A simple profiler to count Nvidia PTX assembly instructions of OpenCL/SYCL/CUDA kernels for roofline model analysis.☆55Updated 4 months ago
- ☆148Updated this week
- ☆83Updated 8 months ago
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆101Updated last week
- Nvidia Instruction Set Specification Generator☆280Updated last year
- An extension library of WMMA API (Tensor Core API)☆99Updated last year
- Tenstorrent MLIR compiler☆151Updated this week
- Ahead of Time (AOT) Triton Math Library☆70Updated last week
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆107Updated this week
- IREE's PyTorch Frontend, based on Torch Dynamo.☆93Updated this week
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.☆133Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆91Updated 3 weeks ago
- Tenstorrent's MLIR Based Compiler. We aim to enable developers to run AI on all configurations of Tenstorrent hardware, through an open-s…☆80Updated this week
- ☆50Updated last year
- ☆104Updated last year
- Learning about CUDA by writing PTX code.☆133Updated last year