HAMR - Heterogeneous Accelerator Memory Resource (HAMR) v1.0
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
HAMR is a library defining an accelerator technology agnostic memory model that bridges between accelerator technologies (CUDA, HIP, ROCm, OpenMP, Sycl, OpenCL, Kokos, etc) and traditional CPUs in heterogeneous computing environments. HAMR is light weight and implemented in modern C++. HAMR can be used to manage memory with in a single code or as a data model for coupling codes in a technologically agnostic way. HAMR provides a Python module for coupling C++ and Python codes which implements zero-copy data transfers to and from Python using the Numpy array interface and Numba CUDA array interface protocols.
- Short Name / Acronym:
- HAMR v1.0
- Site Accession Number:
- 2022-046
- Software Type:
- Scientific
- License(s):
- BSD 3-clause "New" or "Revised" License
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOEPrimary Award/Contract Number:AC02-05CH11231
- DOE Contract Number:
- AC02-05CH11231
- Code ID:
- 110812
- OSTI ID:
- code-110812
- Country of Origin:
- United States
Similar Records
Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation
Evaluating performance and portability of high-level programming models: Julia, Python/Numba, and Kokkos on exascale nodes
Large language model evaluation for high–performance computing software development
Conference
·
Tue Aug 01 00:00:00 EDT 2023
·
OSTI ID:2000371
Evaluating performance and portability of high-level programming models: Julia, Python/Numba, and Kokkos on exascale nodes
Conference
·
Mon May 01 00:00:00 EDT 2023
·
OSTI ID:1994693
Large language model evaluation for high–performance computing software development
Journal Article
·
Wed Sep 04 00:00:00 EDT 2024
· Concurrency and Computation. Practice and Experience
·
OSTI ID:2474767