Łukasz Plewa
dd824164c8
Adds olMemPrefetch and the OL_MEM_MIGRATION_FLAG_* enum, wired through a new dataPrefetchImpl on the plugin interface with Level Zero and CUDA implementations. Backends without prefetch support inherit the default no-op. Prefetch is a hint that migrates a USM allocation between the host and a device so subsequent accesses on the target side are faster. Assisted-by: Claude
Liboffload
This directory contains the implementation of the work-in-progress new API for Offload. It builds on top of the existing plugin implementations but provides a single level of abstraction suitable for implementation of many offloading language runtimes, rather than just OpenMP.
Testing liboffload
The main test suite for liboffload can be run with the check-offload-unit
target, which runs the offload.unittests executable. The test suite will
automatically run on every available device, but can be restricted to a single
platform (CUDA, AMDGPU) with a command line argument:
$ ./offload.unittests --platform=CUDA
Tracing of Offload API calls can be enabled by setting the OFFLOAD_TRACE
environment variable. This works with any program that uses liboffload.
$ OFFLOAD_TRACE=1 ./offload.unittests
---> olInit(nullptr)-> OL_SUCCESS
# etc
The host plugin is not currently supported.
Modifying liboffload
The main header (OffloadAPI.h) and some implementation details are
autogenerated with tablegen. See the API definition README
for implementation details.