Discover ROCm/rocALUTION Open Source project

HIP: C++ Heterogeneous-Compute Interface for Portability

4,470

HIP

AMD's Machine Intelligence Library

3,398

MIOpen

Assembly

1,046

HIPIFY

HIPIFY: Convert CUDA to Portable C++ Code

HCC is an Open Source, Optimizing C++ Compiler for Heterogeneous Compute currently for the ROCm GPU Computing Platform

440

hcc

Next generation BLAS implementation for ROCm platform

425

rocBLAS

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

308

composable_kernel

Omnitrace: Application Profiling, Tracing, and Analysis

285

omnitrace

ROCm Communication Collectives Library (RCCL)

283

rccl

Stretching GPU performance for GEMMs and tensor contractions.

231

Tensile

ROCm Platform Runtime: ROCr a HPC market enhanced HSA based runtime

211

ROCR-Runtime

AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples.

205

aomp

Fortran

203

AMDMIGraphX

AMD's graph optimization engine.

Next generation FFT implementation for ROCm

181

rocFFT

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX also delivers a highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions.

174

MIVisionX

GPUFORT: S2S translation tool for CUDA Fortran and Fortran+X in the spirit of hipify

168

gpufort

Fortran

159

rocPRIM

ROCm Parallel Primitives

Advanced Profiling and Analytics for AMD Hardware

154

omniperf

ROC profiler library. Profiling with perf-counters and derived metrics.

128

rocprofiler

122

rocm-examples

A collection of examples for the ROCm software stack

rocMLIR

rocSPARSE

Next generation SPARSE implementation for ROCm platform

rocm_smi_lib

rocRAND

RAND library for HIP programming language

An implementation of HIP that works on CPUs, across OSes.

111

HIP-CPU

ROCm Thrust - run Thrust dependent software on AMD GPUs

107

rocThrust

Next generation LAPACK implementation for ROCm platform

100

ROCm-Device-Libs

ROCm Device Libraries

rocSOLVER

Reusable software components for ROCm developers

hipCUB

rocWMMA

ROCm Tracer Callback/Activity Library for Performance tracing AMD GPUs

roctracer

ROCm SPARSE marshalling library

hipSPARSE

Fortran interfaces for ROCm libraries

hipfort

Fortran

atmi

Asynchronous Task and Memory Interface, or ATMI, is a runtime framework and programming model for heterogeneous CPU-GPU systems. It provides a consistent, declarative API to create task graphs on CPUs and GPUs (integrated and discrete).

The ROCm Validation Suite is a system administrator’s and cluster manager's tool for detecting and troubleshooting common problems affecting AMD GPU(s) running in a high-performance computing environment, enabled using the ROCm software stack on a compatible platform.

ROCmValidationSuite

CMake modules used within the ROCm libraries

rocm-cmake

CMake

hipFFT

hipFFT is a FFT marshalling library.

A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators

amd_matrix_instruction_calculator

The compiler support repository provides various Lightning Compiler related services.

ROCm-CompilerSupport

AMD ROCm Performance Primitives (RPP) library is a comprehensive high-performance computer vision library for AMD processors with HIP/OpenCL/CPU back-ends.

rpp

This is ROCgdb, the ROCm source-level debugger for Linux, based on GDB, the GNU source-level debugger.

ROCclr

ROCgdb

rocm_bandwidth_test

Bandwidth test for ROCm

HIPCC: HIP compiler driver

HIPCC

Experimental and Intriguing Tools for ROCm

Experimental_ROC

HPCG benchmark based on ROCm platform

rocHPCG

ROC_SHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.

ROC_SHMEM

Machine Intelligence Shader Autogen. AMDGPU ML shader code generator. (previously iGEMMgen)

MISA

amdsmi

ROCm.github.io

TransferBench

TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)

OpenCL compilation with clang compiler.

clang-ocl

CMake

hipSOLVER

ROCm SOLVER marshalling library

Ahead of Time (AOT) Triton Math Library

aotriton

ROCm OpenCL Compiler Tool Driver

ROCm-OpenCL-Driver

RCCL Performance Benchmark Tests

rocm-blogs

Jupyter Notebook

rccl-tests

Cuda

hipRAND

Random number library that generate pseudo-random and quasi-random numbers.

rdc

RDC

The AMD Debugger API is a library that provides all the support necessary for a debugger and other tools to perform low level control of the execution and inspection of execution state of AMD's commercially available GPU architectures.

ROCdbgapi

python package of rocm-smi-lib

pyrsmi

HIP Python Low-level Bindings

hip-python

hip-tests

roc-stdpar

pytorch-micro-benchmarking

hipify_torch

rocmProfileData

ROCm Documentation Python package for ReadTheDocs build standardization

rocm-docs-core

CSS

rocAL

The AMD rocAL is designed to efficiently decode and process images and videos from a variety of storage formats and modify them through a processing graph programmable by the user.

half

rocprofiler-sdk

Examples illustrating usage of the rocBLAS library

rocBLAS-Examples

ROCm - UCX enabled OSU_Benchmarks

OSU_Microbenchmarks

MITuna

rtg_tracer

Repository to host spack recipes for ROCm

rocm-spack-pkgs

rbuild

Rocm build tool

ROCm's implementation of Gromacs

Gromacs

rocm-core

CMake

hip-testsuite

Tuna centric MIOpen client

MIFin

Low-level Cython and Python bindings to the (ROCm) LLVM C API.

rocm-llvm-python

Mirror of flang repo: The source repo is https://github.com/flang-compiler/flang . Once a day the master branch is updated from the upstream source repo and then locked. AOMP or ROCm developers may commit or create PRs on branch aomp-dev.

flang

hipSPARSELt

hostcall services library, math library, and utilities

aomp-extras

MIOpenExamples

MIOpen examples

OSU MPI benchmarks with ROCm support

hipOMB

numba-hip

HIP backend patch for Numba, the NumPy aware dynamic Python compiler using LLVM.