Skip to content

[ESIMD][LIT] Add trivial test cases for EsimdFenceMask enum #4757

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Oct 14, 2021

Conversation

v-klochkov
Copy link
Contributor

Signed-off-by: Vyacheslav N Klochkov [email protected]

@v-klochkov v-klochkov requested a review from kbobrovs October 13, 2021 05:28
@v-klochkov v-klochkov requested a review from kychendev as a code owner October 13, 2021 05:28
@@ -152,6 +152,39 @@ SYCL_ESIMD_FUNCTION SYCL_EXTERNAL simd<float, 16> foo() {
// CHECK: %[[SI6:[0-9a-zA-Z_.]+]] = load i32, i32 addrspace(4)* %[[SI6_ADDR]]
// CHECK: call void @llvm.genx.scatter.scaled.v8i1.v8i32.v8i32(<8 x i1> %{{[0-9a-zA-Z_.]+}}, i32 0, i16 0, i32 %[[SI6]], i32 %{{[0-9a-zA-Z_.]+}}, <8 x i32> %{{[0-9a-zA-Z_.]+}}, <8 x i32> %{{[0-9a-zA-Z_.]+}})
}
esimd_fence(ESIMD_GLOBAL_COHERENT_FENCE);
Copy link
Contributor

Choose a reason for hiding this comment

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

I would suggest to follow this procedure:

// 2. Test cases above should be refactored not to use user-level APIs like
//   gather and use __esimd* calls instead.

since we are testing low-level intrinsic translation here, tests should better invoke __esimd_fence.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Thank you. Fixed in 0c2f3fe

@v-klochkov
Copy link
Contributor Author

v-klochkov commented Oct 13, 2021

The test esimd/matrix_transpose_usm.cpp failed on Windows/CI. It is unrelated to this PR.
http://icl-jenkins.sc.intel.com:8080/blue/organizations/jenkins/SYCL_CI%2Fintel%2FWin%2FTest_Suite/detail/Test_Suite/8085/pipeline/

I made minor changes in the test matrix_transpose_usm.cpp to slightly reduce the chance of timeout: intel/llvm-test-suite#513

@v-klochkov v-klochkov requested a review from kbobrovs October 13, 2021 19:43
@bader bader merged commit 25d92a7 into intel:sycl Oct 14, 2021
@v-klochkov v-klochkov deleted the esimd_misprint_fix branch October 14, 2021 17:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants