mz24cn / gemm_optimization
The repository targets the OpenCL gemm function performance optimization. It compares several libraries clBLAS, clBLAST, MIOpenGemm, Intel MKL(CPU) and cuBLAS(CUDA) on different matrix sizes/vendor's hardwares/OS. Out-of-the-box easy as MSVC, MinGW, Linux(CentOS) x86_64 binary provided. 在不同矩阵大小/硬件/操作系统下比较几个BLAS库的sgemm函数性能，提供binary，开盒即用。
☆16Updated 5 years ago
Alternatives and similar repositories for gemm_optimization:
Users that are interested in gemm_optimization are comparing it to the libraries listed below
- An extension library of WMMA API (Tensor Core API)☆87Updated 6 months ago
- A Winograd Minimal Filter Implementation in CUDA☆23Updated 3 years ago
- This is a tuned sparse matrix dense vector multiplication(SpMV) library☆21Updated 8 years ago
- Optimize GEMM with tensorcore step by step☆19Updated last year
- flexible-gemm conv of deepcore☆17Updated 5 years ago
- ICML2017 MEC: Memory-efficient Convolution for Deep Neural Network C++实现(非官方)☆17Updated 5 years ago
- ☆25Updated 9 months ago
- ☆38Updated 3 years ago
- ☆38Updated 4 years ago
- A GPU benchmark suite for assessing on-chip GPU memory bandwidth☆104Updated 7 years ago
- ☆59Updated last month
- ☆40Updated 4 years ago
- Subpart source code of of deepcore v0.7☆27Updated 4 years ago
- This is a demo how to write a high performance convolution run on apple silicon☆52Updated 2 years ago
- Common libraries for PPL projects☆29Updated 3 months ago
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆32Updated 4 years ago
- Yet another Polyhedra Compiler for DeepLearning☆19Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆99Updated 4 months ago
- Dissecting NVIDIA GPU Architecture☆82Updated 2 years ago
- ☆17Updated 4 years ago
- study of cutlass☆19Updated 2 months ago
- FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme☆51Updated 4 months ago
- Machine Intelligence Shader Autogen. AMDGPU ML shader code generator. (previously iGEMMgen)☆34Updated 3 months ago
- amdgpu example code in hip/asm☆24Updated last week
- how to design cpu gemm on x86 with avx256, that can beat openblas.☆67Updated 5 years ago
- An unofficial cuda assembler, for all generations of SASS, hopefully ：）☆79Updated last year
- ☆17Updated 9 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆87Updated 10 months ago
- Winograd-based convolution implementation in OpenCL☆28Updated 7 years ago