enp1s0 / ozIMMULinks
FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme
☆67Updated 2 months ago
Alternatives and similar repositories for ozIMMU
Users that are interested in ozIMMU are comparing it to the libraries listed below
Sorting:
- An extension library of WMMA API (Tensor Core API)☆97Updated 10 months ago
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆32Updated 2 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆88Updated this week
- CUDA Matrix Multiplication Optimization☆188Updated 10 months ago
- ☆50Updated last year
- 🎃 GPU load-balancing library for regular and irregular computations.☆62Updated 11 months ago
- ☆38Updated 5 years ago
- ☆40Updated 4 years ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆109Updated 8 months ago
- A language and compiler for irregular tensor programs.☆137Updated 6 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆79Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 10 months ago
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆86Updated last week
- AMD’s C++ library for accelerating tensor primitives☆41Updated this week
- Test suite for probing the numerical behavior of NVIDIA tensor cores☆38Updated 10 months ago
- This is a demo how to write a high performance convolution run on apple silicon☆54Updated 3 years ago
- Dissecting NVIDIA GPU Architecture☆95Updated 2 years ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- rocWMMA☆114Updated this week
- CAKE Library for constant-bandwidth matrix multiplication on CPUs☆15Updated last year
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆182Updated 4 months ago
- ☆96Updated last year
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆32Updated 4 years ago
- GPU Performance Advisor☆65Updated 2 years ago
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.☆131Updated last year
- A simple profiler to count Nvidia PTX assembly instructions of OpenCL/SYCL/CUDA kernels for roofline model analysis.☆52Updated 2 months ago
- Ahead of Time (AOT) Triton Math Library☆64Updated last week
- NVIDIA HPCG is based on the HPCG benchmark and optimized for performance on NVIDIA accelerated HPC systems.☆56Updated last month
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 2 months ago
- Next generation LAPACK implementation for ROCm platform☆101Updated this week