Enable dpnp build on AMD GPU #2302
Conversation
vlad-perevezentsev
requested review from
antonwolfy,
AlexanderKalistratov and
vtavana
as code owners
|
Array API standard conformance tests for dpnp=0.17.0dev6=py312he4f9c94_10 ran successfully. |
|
View rendered docs @ https://intelpython.github.io/dpnp/pull/2302/index.html |
| @@ -38,12 +38,12 @@ if(_dpnp_sycl_targets) | |||
| target_compile_options( | |||
| ${python_module_name} | |||
| PRIVATE | |||
| -fsycl-targets=${_dpnp_sycl_targets} | |||
| ${_dpnp_sycl_target_compile_options} | |||
There was a problem hiding this comment.
Should we do the same for each CMakeList.txt per every extension?
| if not arch: | ||
| raise ValueError("--arch is required when --target=hip") | ||
| cmake_args += [ | ||
| "-DDPNP_TARGET_HIP=ON", |
There was a problem hiding this comment.
For what do we need to define two variables? Can it be combined in a single one, like in dpctl: -DDPNP_TARGET_HIP={arch}?
There was a problem hiding this comment.
Additionally, --target=cuda is current dpnp approach, but:
- dpctl and dpnp should consider supporting targeting specific CUDA architectures
--target=hipmeans that there is no way to build simultaneously for HIP and CUDA (which is very, very much an edge case, but should be considered)
For these reasons, I think it is most sensible to move away from --target= universal approach to --target-cuda= and --target-hip= or something to that effect
| @@ -104,6 +105,16 @@ def run( | |||
| # Always builds using oneMKL interfaces for the cuda target | |||
| onemkl_interfaces = True | |||
|
|
|||
| if target == "hip": | |||
There was a problem hiding this comment.
What is about documentation updates?
We need to describe and provide an example how to enable build for HIP target.
This PR updates
СMakeListsfiles andbuild_locally.pyto enable building dpnp for AMD targets.To build dpnp on AMD:
--archis a required argument whentarget=hip.where `arch`` is the architecture of the AMD GPU.
To find the architecture, use