[SYCL] Enable LIT testing for Level Zero #1839
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
againull
commented
Jun 8, 2020
againull
commented
- Support discovery of Level Zero devices in get_device_count_by_type tool
- Support Level Zero backend in the lit scripts
- Add check-level0 make target
- Fix obvious mistake in the plugin in addMapping function
- Disable lit tests failing for Level Zero
Signed-off-by: Artur Gainullin <[email protected]>
* Create check target for the Level Zero * Add level0 backend support to lit.py Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
bjoernknafla
reviewed
Jun 9, 2020
bjoernknafla
reviewed
Jun 9, 2020
sycl/test/lit.cfg.py
Outdated
| @@ -105,10 +106,16 @@ def getDeviceCount(device_type): | |||
| if re.match(r".*cuda", result[1]): | |||
| is_cuda = True; | |||
|
|
|||
| # if we have found gpu and there is additional information, let's check | |||
| # whether this is CUDA device or not | |||
| if device_type == "gpu" and value > 0 and len(result[1]): | |||
There was a problem hiding this comment.
Would it make sense to also move the CUDA check above into this condition?
There was a problem hiding this comment.
You are right, fixed.
|
+1 |
Signed-off-by: Artur Gainullin <[email protected]>
|
The CUDA build is probably fixed by commit 4a8c432 ? |
sycl/test/lit.cfg.py
Outdated
| @@ -181,8 +188,8 @@ def getDeviceCount(device_type): | |||
| config.substitutions.append( ('%ACC_RUN_PLACEHOLDER', acc_run_substitute) ) | |||
| config.substitutions.append( ('%ACC_CHECK_PLACEHOLDER', acc_check_substitute) ) | |||
|
|
|||
| # PI API either supports OpenCL or CUDA. | |||
| if not cuda and found_at_least_one_device: | |||
| # PI API either supports OpenCL or CUDA or Level Zero. | |||
There was a problem hiding this comment.
Comment is misleading, PI can support multiple plugins simultaneously. It is LIT infrastructure that only runs with single backend.
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
Yes, true. |
rbegam
reviewed
Jun 10, 2020
rbegam
reviewed
Jun 10, 2020
Signed-off-by: Artur Gainullin <[email protected]>
Signed-off-by: Artur Gainullin <[email protected]>
smaslov-intel
approved these changes
Jun 11, 2020
bader
reviewed
Jun 11, 2020
|
|
||
| if err: | ||
| lit_config.warning("getDeviceCount {TYPE} {BACKEND} stderr:{ERR}".format( | ||
| TYPE=device_type, BACKEND=backend, ERR=err)) | ||
| return [value,is_cuda] | ||
| return [value,is_cuda,is_level0] |
There was a problem hiding this comment.
Please, fix return value type at line 93.
https://github.com/intel/llvm/runs/760440987
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.