ROCm / 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).
☆66Updated last year
Alternatives and similar repositories for atmi:
Users that are interested in atmi are comparing it to the libraries listed below
- nvptx-tools: a collection of tools for use with nvptx-none GCC toolchains.☆49Updated 6 months ago
- Compute applications.☆24Updated 5 years ago
- mallocMC: Memory Allocator for Many Core Architectures☆55Updated 3 weeks ago
- OpenCL compilation with clang compiler.☆26Updated this week
- SYCL-ML is a C++ library, implementing classical machine learning algorithms using SYCL.☆66Updated 5 years ago
- Directed Acyclic Graph Execution Engine (DAGEE) is a C++ library that enables programmers to express computation and data movement, as ta…☆45Updated 3 years ago
- Implementation of the SYCL specification.☆66Updated 8 months ago
- OpenSHMEM Application Programming Interface☆54Updated 4 months ago
- SYCL Conformance Tests☆68Updated this week
- MIOpenGEMM is now deprecated☆62Updated last year
- OpenCL tool to detect buffer overflows in GPU kernels☆21Updated 6 years ago
- Compiler agnostic metaprogramming library providing concepts, type operations and tuples for C++ and cuda☆84Updated this week
- Giddy - A lightweight GPU decompression library☆42Updated 5 years ago
- Codeplay project for contributions to the LLVM SYCL implementation☆30Updated 4 years ago
- GPU Optimization and Memory Abstraction Framework☆32Updated 5 years ago
- SYCL Open Source Specification☆130Updated last week
- Next generation FFT implementation for ROCm☆187Updated this week
- Simple example showing how to use DGMA in OpenCL☆14Updated 9 years ago
- Tools for parsing, assembling, and disassembling HSAIL.☆71Updated 4 years ago
- RAND library for HIP programming language☆117Updated this week
- ☆75Updated last year
- SYCL Reference Manual☆27Updated 10 months ago
- ☆56Updated last week
- Reusable software components for ROCm developers☆83Updated this week
- The Radeon Compute Profiler (RCP) is a performance analysis tool that gathers data from the API run-time and GPU for OpenCL™ and ROCm/HSA…☆86Updated 4 years ago
- Copy-hiding array abstraction to automatically migrate data between memory spaces☆106Updated this week
- Intel® GPU Compute Samples☆105Updated last week
- portDNN is a library implementing neural network algorithms written using SYCL☆111Updated 9 months ago
- A thin wrapper around miOpen and cuDNN☆41Updated last year
- A fast and highly scalable GPU dynamic memory allocator☆104Updated 10 years ago