ROCm/HIP-CPU

Stars
107
Rank 323,587 (Top 7 %)
Language
C++
License
MIT License
Created about 4 years ago
Updated 8 months ago

ROCm/HIP-CPU

ROCm

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

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

HIP CPU Runtime

Repository | Issues | Documentation | Code Samples

The HIP CPU Runtime is a header-only library that allows CPUs to execute unmodified HIP code. It is generic and does not assume a particular CPU vendor or architecture. Please note the library is being actively developed, and is known to be incomplet; it might also be incorrekt and there could be a few bad bugs lurking.

Overview and Tutorials

HIP CPU Runtime tutorials per compiler and platform

GCC on Linux
GCC on MacOS
Microsoft C++ Compiler (MSVC) on Windows
Others (TODO)

Quick Links

HIP GPU Runtime FAQ

Questions and Feedback

FAQs
Please consult the FAQ before submitting a question.

Known Issues
If a pre-existing issue encompasses your feedback, please leave a reaction on the issue to up-vote or down-vote it, which will help us in prioritisation.

Provide Feedback
Submit questions, issues or feature requests.

Contribution

Contributions are most welcome and strongly encouraged. Please consult the contributing guide for details.

ROCm

AMD ROCm™ Software - GitHub Home

HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

MIOpen

AMD's Machine Intelligence Library

HIPIFY

HIPIFY: Convert CUDA to Portable C++ Code

hcc

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

rocBLAS

Next generation BLAS implementation for ROCm platform

composable_kernel

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

omnitrace

Omnitrace: Application Profiling, Tracing, and Analysis

rccl

ROCm Communication Collectives Library (RCCL)

ROCR-Runtime

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

Tensile

Stretching GPU performance for GEMMs and tensor contractions.

aomp

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.

AMDMIGraphX

AMD's graph optimization engine.

rocFFT

Next generation FFT implementation for ROCm

MIVisionX

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.

gpufort

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

rocPRIM

ROCm Parallel Primitives

rocm-examples

A collection of examples for the ROCm software stack

omniperf

Advanced Profiling and Analytics for AMD Hardware

rocprofiler

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

rocMLIR

rocSPARSE

Next generation SPARSE implementation for ROCm platform

rocm_smi_lib

rocRAND

RAND library for HIP programming language

rocThrust

ROCm Thrust - run Thrust dependent software on AMD GPUs

ROCm-Device-Libs

ROCm Device Libraries

rocSOLVER

Next generation LAPACK implementation for ROCm platform

rocWMMA

hipCUB

Reusable software components for ROCm developers

rocALUTION

Next generation library for iterative sparse solvers for ROCm platform

hipfort

Fortran interfaces for ROCm libraries

roctracer

ROCm Tracer Callback/Activity Library for Performance tracing AMD GPUs

hipSPARSE

ROCm SPARSE marshalling library

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).

ROCmValidationSuite

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.

rocm-cmake

CMake modules used within the ROCm libraries

hipFFT

hipFFT is a FFT marshalling library.

ROCgdb

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

amd_matrix_instruction_calculator

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

ROCm-CompilerSupport

The compiler support repository provides various Lightning Compiler related services.

rpp

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

ROCclr

rocm_bandwidth_test

Bandwidth test for ROCm

amdsmi

HIPCC

HIPCC: HIP compiler driver

aotriton

Ahead of Time (AOT) Triton Math Library

Experimental_ROC

Experimental and Intriguing Tools for ROCm

rocHPCG

HPCG benchmark based on ROCm platform

ROC_SHMEM

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

MISA

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

ROCm.github.io

TransferBench

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

rocm-blogs

Jupyter Notebook

clang-ocl

OpenCL compilation with clang compiler.

hipSOLVER

ROCm SOLVER marshalling library

ROCm-OpenCL-Driver

ROCm OpenCL Compiler Tool Driver

rdc

hipRAND

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

rccl-tests

RCCL Performance Benchmark Tests

ROCdbgapi

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.

pyrsmi

python package of rocm-smi-lib

hip-python

HIP Python Low-level Bindings

hip-tests

roc-stdpar

pytorch-micro-benchmarking

hipify_torch

rocmProfileData

rocm-docs-core

ROCm Documentation Python package for ReadTheDocs build standardization

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

rocBLAS-Examples

Examples illustrating usage of the rocBLAS library

OSU_Microbenchmarks

ROCm - UCX enabled OSU_Benchmarks

MITuna

rtg_tracer

Gromacs

ROCm's implementation of Gromacs

rocm-spack-pkgs

Repository to host spack recipes for ROCm

rbuild

Rocm build tool

rocm-core

rocm-llvm-python

Low-level Cython and Python bindings to the (ROCm) LLVM and AMD COMGR C API. Also ships the official LLVM Clang bindings.

hip-testsuite

MIFin

Tuna centric MIOpen client

flang

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.

numba-hip

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

tensorcast

hipSPARSELt

aomp-extras

hostcall services library, math library, and utilities

MIOpenExamples

MIOpen examples

rocprofiler-register

rocm-install-on-windows

hipOMB

OSU MPI benchmarks with ROCm support

migraphx-benchmark

rocm-recipes

Recipes for rocm

hipBLAS-common

Common files shared by hipBLAS and hipBLASLt