Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

HAMR - Heterogeneous Accelerator Memory Resource (HAMR) v1.0

Software ·
DOI:https://doi.org/10.5281/zenodo.6471012· OSTI ID:code-110812 · Code ID:110812
 [1]
  1. 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:
USDOE

Primary 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
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

Related Subjects