Skip to content
This repository was archived by the owner on Mar 28, 2023. It is now read-only.

Conversation

@vladimirlaz
Copy link

The gpu_aot_target_opts LIT parameter and GPU_AOT_TARGET_OPTS CMake
variable are introduced to allow customization of the target device for
AOT compilation on GPU.

The gpu_aot_target_opts LIT parameter and GPU_AOT_TARGET_OPTS CMake
variable are introduced to allow customization of target device for
AOT compilation on GPU.
AGindinson
AGindinson previously approved these changes Nov 25, 2021
Copy link

@AGindinson AGindinson left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM personally. We should take note that -device * compilations take longer than -device <specified_platform> ones, but a) if there's no concern with llvm-test-suite CI time, it doesn't matter much at the moment; b) this is not something introduced by this patched.

bader
bader previously approved these changes Nov 30, 2021
v-klochkov
v-klochkov previously approved these changes Nov 30, 2021
v-klochkov
v-klochkov previously approved these changes Nov 30, 2021
@vladimirlaz vladimirlaz merged commit 68295c0 into intel:intel Dec 3, 2021
@vladimirlaz vladimirlaz deleted the add_opts branch February 2, 2022 10:44
aelovikov-intel pushed a commit to aelovikov-intel/llvm that referenced this pull request Mar 27, 2023
* [SYCL] Add gpu_aot_target_opts parameter

The gpu_aot_target_opts LIT parameter and the GPU_AOT_TARGET_OPTS CMake
variable is introduced to allow customization of the target device for
AOT compilation on GPU.

Co-authored-by: Alexey Bader <alexey.bader@intel.com>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants