seb-v / fp32_sgemm_amdLinks
Super fast FP32 matrix multiplication on RDNA3
☆70Updated 4 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☆98Updated 6 months ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆110Updated 2 months ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 4 months ago
- GPUOcelot: A dynamic compilation framework for PTX☆207Updated 6 months ago
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆132Updated 3 weeks ago
- Attention in SRAM on Tenstorrent Grayskull☆37Updated last year
- ☆53Updated this week
- amdgpu example code in hip/asm☆36Updated last week
- Nvidia Instruction Set Specification Generator☆286Updated last year
- AI Tensor Engine for ROCm☆243Updated this week
- rocWMMA☆121Updated this week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆101Updated last month
- An interactive web-based tool for exploring intermediate representations of PyTorch and Triton models☆46Updated this week
- A simple profiler to count Nvidia PTX assembly instructions of OpenCL/SYCL/CUDA kernels for roofline model analysis.☆55Updated 4 months ago
- ☆41Updated 3 months ago
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆69Updated 3 weeks ago
- MLIR-based partitioning system☆115Updated this week
- Development repository for the Triton language and compiler☆127Updated this week
- Ahead of Time (AOT) Triton Math Library☆75Updated this week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆93Updated last month
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆60Updated last week
- An extension library of WMMA API (Tensor Core API)☆99Updated last year
- Tenstorrent MLIR compiler☆169Updated this week
- ☆148Updated this week
- IREE's PyTorch Frontend, based on Torch Dynamo.☆94Updated last week
- AMD lab notes with code examples to demonstrate use of AMD GPUs☆100Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆47Updated 7 months ago
- ☆85Updated 9 months ago
- Custom PTX Instruction Benchmark☆126Updated 5 months ago