seb-v / fp32_sgemm_amdLinks
Super fast FP32 matrix multiplication on RDNA3
☆74Updated 6 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☆105Updated 8 months ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆117Updated 4 months ago
- GPUOcelot: A dynamic compilation framework for PTX☆209Updated 8 months ago
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆144Updated 2 months ago
- rocWMMA☆133Updated last week
- Nvidia Instruction Set Specification Generator☆293Updated last year
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆45Updated last month
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆97Updated last week
- An interactive web-based tool for exploring intermediate representations of PyTorch and Triton models☆51Updated last month
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆101Updated last month
- amdgpu example code in hip/asm☆42Updated last week
- Tenstorrent MLIR compiler☆186Updated this week
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆82Updated this week
- ☆151Updated this week
- Attention in SRAM on Tenstorrent Grayskull☆38Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆373Updated this week
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆70Updated 2 months ago
- Learning about CUDA by writing PTX code.☆138Updated last year
- Development repository for the Triton language and compiler☆133Updated this week
- Ahead of Time (AOT) Triton Math Library☆77Updated this week
- MLIR-based partitioning system☆136Updated this week
- ☆90Updated 11 months ago
- AI Tensor Engine for ROCm☆284Updated this week
- Test suite for probing the numerical behavior of NVIDIA tensor cores☆41Updated last year
- A simple profiler to count Nvidia PTX assembly instructions of OpenCL/SYCL/CUDA kernels for roofline model analysis.☆56Updated 6 months ago
- CUDA Matrix Multiplication Optimization☆225Updated last year
- Custom PTX Instruction Benchmark☆128Updated 7 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.☆98Updated this week
- A profiler to disclose and quantify hardware features on GPUs.☆174Updated 3 years ago
- An experimental CPU backend for Triton☆154Updated 4 months ago