tzakharko / m4-sme-explorationLinks
Exploring the scalable matrix extension of the Apple M4 processor
☆202Updated 10 months ago
Alternatives and similar repositories for m4-sme-exploration
Users that are interested in m4-sme-exploration are comparing it to the libraries listed below
Sorting:
- Apple GPU microarchitecture☆549Updated 11 months ago
- Apple AMX Instruction Set☆1,138Updated 8 months ago
- GPUOcelot: A dynamic compilation framework for PTX☆206Updated 7 months ago
- Nvidia Instruction Set Specification Generator☆293Updated last year
- Apple Firestorm/Icestorm CPU microarchitecture docs☆242Updated 2 years ago
- A description of Minotaur can be found in https://arxiv.org/abs/2306.00229.☆111Updated 3 weeks ago
- ☆297Updated 8 months ago
- Apple G13 GPU architecture docs and tools☆617Updated 4 months ago
- ☆136Updated 2 years ago
- Instruction latency & throughput profiler for AArch64☆39Updated last month
- IREE's PyTorch Frontend, based on Torch Dynamo.☆98Updated this week
- chipStar is a tool for compiling and running HIP/CUDA on SPIR-V via OpenCL or Level Zero APIs.☆298Updated 3 weeks ago
- ☆63Updated this week
- Super fast FP32 matrix multiplication on RDNA3☆73Updated 5 months ago
- Exocompilation for productive programming of hardware accelerators☆659Updated this week
- ☆293Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆353Updated this week
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆143Updated 2 months ago
- VSCode LLVM Compiler Explorer☆231Updated last year
- Tensor library & inference framework for machine learning☆110Updated 3 weeks ago
- Algebraic enhancements for GEMM & AI accelerators☆279Updated 6 months ago
- MLIR metal dialect☆31Updated last year
- Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.☆143Updated 2 weeks ago
- Running linear algebra as fast as possible on Apple silicon☆21Updated 2 years ago
- Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator☆213Updated last year
- High-Performance SGEMM on CUDA devices☆101Updated 8 months ago
- Online compiler for HIP and NVIDIA® CUDA® code to WebGPU☆194Updated 8 months ago
- A framework that support executing unmodified CUDA source code on non-NVIDIA devices.☆135Updated 8 months ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆114Updated 4 months ago
- Richard is gaining power☆193Updated 2 months ago