ROCm Software Platform

Repositories

• AMDMIGraphX

  AMD's graph optimization engine.
  C++ 12 38 45 7 Updated Nov 29, 2020

• MIOpen

  AMD's Machine Intelligence Library
  NASL MIT 106 579 114 (5 issues need help) 40 Updated Nov 28, 2020

• iGEMMgen

  Code generator for implicit gemm algorithm for amdgpu.

  python amd gpu assembly convolution tensor-contraction implicit-gemm-algorithm
  Python MIT 3 7 3 5 Updated Nov 28, 2020

• rocSOLVER

  Next generation LAPACK implementation for ROCm platform
  C++ BSD-2-Clause 20 13 0 1 Updated Nov 28, 2020

• rocBLAS

  Next generation BLAS implementation for ROCm platform

  blas hip rocm
  C++ MIT 94 139 4 0 Updated Nov 27, 2020

• hipBLAS

  ROCm BLAS marshalling library
  C++ MIT 38 28 0 1 Updated Nov 27, 2020

• rocFFT

  Next generation FFT implementation for ROCm

  fft hip rocm
  C++ MIT 53 70 16 2 Updated Nov 28, 2020

• Tensile

  Stretching GPU performance for GEMMs and tensor contractions.

  python machine-learning amd gpu assembly opencl dnn
  Python MIT 64 75 10 8 Updated Nov 27, 2020

• hipSPARSE

  ROCm SPARSE marshalling library
  C++ MIT 17 16 1 3 Updated Nov 27, 2020

• hipCUB

  Reusable software components for rocm developers
  C++ 15 19 0 2 Updated Nov 26, 2020

• llvm-project-mlir
  C++ 1 0 0 1 Updated Nov 26, 2020

• rocRAND

  RAND library for HIP programming language

  gpu random cuda rng hip rocm
  C MIT 35 54 2 3 Updated Nov 25, 2020

• tensorflow-upstream

  Forked from tensorflow/tensorflow

  TensorFlow ROCm port
  C++ Apache-2.0 83,349 517 39 7 Updated Nov 25, 2020

• rocSPARSE

  Next generation SPARSE implementation for ROCm platform
  C++ MIT 21 28 1 0 Updated Nov 25, 2020

• ucx

  Forked from openucx/ucx

  Unified Communication Library X
  C 189 2 0 0 Updated Nov 25, 2020

• pytorch

  Forked from pytorch/pytorch

  Tensors and Dynamic neural networks in Python with strong GPU acceleration
  C++ 11,686 146 38 12 Updated Nov 24, 2020

• hipFFT

  hipFFT is a FFT marshalling library.
  C++ MIT 2 2 0 0 Updated Nov 24, 2020

• rccl

  ROCm Communication Collectives Library (RCCL)
  C++ 33 51 2 0 Updated Nov 21, 2020

• rocPRIM

  ROCm Parallel Primitives

  amd gpu parallel cuda primitive hip rocm
  C++ MIT 30 62 2 1 Updated Nov 20, 2020

• rocThrust

  ROCm Thrust - run Thrust dependent software on AMD GPUs
  C++ Apache-2.0 15 22 1 2 Updated Nov 20, 2020

• DeepBench

  Forked from baidu-research/DeepBench

  Benchmarking Deep Learning operations on different hardware
  C++ Apache-2.0 230 2 0 0 Updated Nov 19, 2020

• rocHPCG

  HPCG benchmark based on ROCm platform
  C++ BSD-3-Clause 4 4 0 0 Updated Nov 19, 2020

• onnxruntime

  Forked from microsoft/onnxruntime

  ONNX Runtime: cross-platform, high performance scoring engine for ML models
  C++ MIT 840 0 0 0 Updated Nov 18, 2020

• pytorch.github.io

  Forked from pytorch/pytorch.github.io

  The website for PyTorch
  Jupyter Notebook BSD-3-Clause 135 0 0 0 Updated Nov 17, 2020

• DeepSpeedExamples

  Forked from microsoft/DeepSpeedExamples

  Example models using DeepSpeed
  Python MIT 31 0 0 0 Updated Nov 16, 2020

• MIOpenTensile
  C++ 3 0 2 0 Updated Nov 15, 2020

• hip-rdma-perftest

  Verbs/RDMA benchmarks with ROCM support
  C 0 0 0 0 Updated Nov 13, 2020

• rocALUTION

  Next generation library for iterative sparse solvers for ROCm platform

  cplusplus fortran opencl solver openmp mpi cuda
  C++ MIT 16 28 0 0 Updated Nov 11, 2020

• hipfort

  Fortran interfaces for ROCm libraries
  Fortran 7 8 8 (1 issue needs help) 4 Updated Nov 5, 2020

• apex

  Forked from NVIDIA/apex

  A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
  Python BSD-3-Clause 650 3 1 0 Updated Nov 4, 2020