History

[OFFLOAD][L0] Add support to run ctor/dtor code (#187510 )

This PR adds support in the Level Zero plugin to execute
constructors/destructors on the device code. As spirv-link has some
limitations, it mimics the CUDA plugin behavior where the RTL constructs
the device side tables before invoking the kernel that will execute
them.

The kernel and other necessary symbols to create the device tables are
created by the SPIRVCtorDtorLowering pass to be added in #187509

2026-03-25 08:43:44 +01:00

[Offload] Escape \; in command string (#186120 )

2026-03-12 15:02:40 +01:00

cmake

[OpenMP] Emit aggregate kernel prototypes and remove libffi dependency (#186261 )

2026-03-20 13:08:23 -05:00

docs

[Offload] Add Offload API Sphinx documentation (#147323 )

2025-07-10 11:50:51 +01:00

include

[OpenMP][Offload] Add offload runtime support for dyn_groupprivate clause (#152831 )

2026-03-12 01:13:06 -07:00

liboffload

[Offload] Fix type mismatch by using uint64_t instead of size_t (#183375 )

2026-02-25 13:31:03 -08:00

libomptarget

[offload] - Remove standalone build in favor of 'runtimes' (#170693 )

2026-03-19 09:00:40 -05:00

plugins-nextgen

[OFFLOAD][L0] Add support to run ctor/dtor code (#187510 )

2026-03-25 08:43:44 +01:00

test

[offload] Use flang-rt for test feature requirements (#187733 )

2026-03-20 18:59:06 +01:00

tools

[Offload] Add argument to 'olInit' for global configuration options (#181872 )

2026-02-17 14:04:00 -06:00

unittests

[OFFLOAD] Enable Level Zero unittests (#185492 )

2026-03-11 14:09:59 +00:00

utils

…

CMakeLists.txt

[offload] - Remove standalone build in favor of 'runtimes' (#170693 )

2026-03-19 09:00:40 -05:00

Maintainers.md

[Offload] Add 'Maintainers.md' file for offload (#138177 )

2025-05-01 14:06:33 -05:00

README.md

…

README.txt

…

README.md

The LLVM/Offload Subproject

The Offload subproject aims at providing tooling, runtimes, and APIs that allow users to execute code on accelerators or other "co-processors" that may or may not match the architecture of their "host". In the long run, all kinds of targets are in scope of this effort, including but not limited to: CPUs, GPUs, FPGAs, AI/ML accelerators, distributed resources, etc.

For OpenMP offload users, the project is ready and fully usable. The final API design is still under development. More content will show up here and on our webpage soon. In the meantime, people are encouraged to participate in our meetings (see below) and check our development board as well as the discussions on Discourse.

Meetings

Every second Wednesday, 7:00 - 8:00am PT, starting Jan 24, 2024. Alternates with the OpenMP in LLVM meeting. invite.ics Meeting Minutes and Agenda