Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[NFCI][SYCL] Refactor getBinaryImageFormat #12586

Merged
merged 2 commits into from
Feb 2, 2024
Merged

[NFCI][SYCL] Refactor getBinaryImageFormat #12586

merged 2 commits into from
Feb 2, 2024

Conversation

aelovikov-intel
Copy link
Contributor

A future PR will add support for magic numbers other than four bytes. Refactor the code to make those future changes easier to review.

@aelovikov-intel
[NFCI][SYCL] Refactor getBinaryImageFormat
aedcf7a 
A future PR will add support for magic numbers other than four bytes.
Refactor the code to make those future changes easier to review.
@aelovikov-intel aelovikov-intel requested a review from a team as a code owner February 1, 2024 19:36
@aelovikov-intel aelovikov-intel mentioned this pull request Feb 1, 2024
Merged
steffenlarsen
steffenlarsen approved these changes Feb 2, 2024
View reviewed changes
Copy link
Contributor

@steffenlarsen steffenlarsen left a comment

Choose a reason for hiding this comment

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

Overall good, with a few nits in #12587.

steffenlarsen
steffenlarsen approved these changes Feb 2, 2024
View reviewed changes
Copy link
Contributor

@steffenlarsen steffenlarsen left a comment

Choose a reason for hiding this comment

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

LGTM!

@aelovikov-intel aelovikov-intel merged commit 153ccbe into intel:sycl Feb 2, 2024
12 checks passed
@aelovikov-intel aelovikov-intel deleted the refactor-get-format branch February 2, 2024 20:12
@aelovikov-intel
Copy link
Contributor Author

Post commit failed on Arc GPU:

Failed Tests (1):
  SYCL :: Reduction/reduction_range_3d_rw.cpp

FAIL: SYCL :: Reduction/reduction_range_3d_rw.cpp (1551 of 1862)
******************** TEST 'SYCL :: Reduction/reduction_range_3d_rw.cpp' FAILED ********************
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 1
/__w/llvm/llvm/toolchain/bin//clang++   -fsycl -fsycl-targets=spir64 /__w/llvm/llvm/llvm/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp -o /__w/llvm/llvm/build-e2e/Reduction/Output/reduction_range_3d_rw.cpp.tmp.out
# executed command: /__w/llvm/llvm/toolchain/bin//clang++ -fsycl -fsycl-targets=spir64 /__w/llvm/llvm/llvm/sycl/test-e2e/Reduction/reduction_range_3d_rw.cpp -o /__w/llvm/llvm/build-e2e/Reduction/Output/reduction_range_3d_rw.cpp.tmp.out
# note: command had no output on stdout or stderr
# RUN: at line 2
env ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Reduction/Output/reduction_range_3d_rw.cpp.tmp.out
# executed command: env ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Reduction/Output/reduction_range_3d_rw.cpp.tmp.out
# .---command stdout------------
# | Device: Intel(R) Arc(TM) A750 Graphics, MaxWGSize: 1024, LocalMemSize: 65536, Driver: 1.3.27912
# | Start, T=i, BOp=St4plusIvE, Range={1, 1, 1}. PASSED
# | Start, T=i, BOp=St4plusIvE, Range={2, 2, 2}. PASSED
# | Start, T=i, BOp=St4plusIvE, Range={2, 3, 4}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={1, 1, 1025}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={1, 1025, 1}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={1025, 1, 1}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={2, 5, 2048}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={3, 3072, 2}. PASSED
# | Start, T=l, BOp=St4plusIvE, Range={3072, 8, 4}. PASSED
# | Start, T=i, BOp=St7bit_xorIvE, Range={2, 3072, 3}. PASSED
# | Start, T=i, BOp=St7bit_andIvE, Range={3072, 4, 3}. PASSED
# | Start, T=i, BOp=St6bit_orIvE, Range={2, 2, 3072}. PASSED
# | Start, T=m, BOp=St10multipliesIvE, Range={2, 3, 5}. PASSED
# | Start, T=m, BOp=St10multipliesIvE, Range={5, 2, 3}. PASSED
# | Start, T=i, BOp=N4sycl3_V17minimumIvEE, Range={1024, 8, 3}. PASSED
# | Start, T=i, BOp=N4sycl3_V17maximumIvEE, Range={3, 1024, 3}. PASSED
# | Start, T=f, BOp=St10multipliesIvE, Range={3, 3, 4}. PASSED
# | Start, T=9CustomVecIxE, BOp=13CustomVecPlusIxE, Range={2, 33, 1024}. PASSED
# | Start, T=9CustomVecIxE, BOp=13CustomVecPlusIxE, Range={2, 33, 1024}. PASSED
# | Start, T=i, BOp=19PlusWithoutIdentityIiE, Range={1, 1, 1}. PASSED
# | Start, T=i, BOp=19PlusWithoutIdentityIiE, Range={2, 2, 2}. PASSED
# | Start, T=i, BOp=19PlusWithoutIdentityIiE, Range={2, 3, 4}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={1, 1, 1025}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={1, 1025, 1}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={1025, 1, 1}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={2, 5, 2048}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={3, 3072, 2}. PASSED
# | Start, T=l, BOp=19PlusWithoutIdentityIlE, Range={3072, 8, 4}. FAILED
# | Start, T=i, BOp=25MultipliesWithoutIdentityIiE, Range={1, 1, 1}. PASSED
# | Start, T=i, BOp=25MultipliesWithoutIdentityIiE, Range={2, 2, 2}. PASSED
# | Start, T=i, BOp=25MultipliesWithoutIdentityIiE, Range={2, 3, 4}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={1, 1, 1025}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={1, 1025, 1}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={1025, 1, 1}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={2, 5, 2048}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={3, 3072, 2}. PASSED
# | Start, T=l, BOp=25MultipliesWithoutIdentityIlE, Range={3072, 8, 4}. PASSED
# `-----------------------------
# .---command stderr------------
# | Device: Intel(R) Arc(TM) A750 Graphics, MaxWGSize: 1024, LocalMemSize: 65536, Driver: 1.3.27912
# | Error, T=l, BOp=19PlusWithoutIdentityIlE, Range={3072, 8, 4}, Computed value=291941, Expected value=295013
# | 1 test-cases failed
# `-----------------------------
# error: command failed with exit status: 1

I believe I've seen it before and it's not specific to this PR.

aelovikov-intel added a commit that referenced this pull request Feb 5, 2024
@aelovikov-intel
[SYCL] Treat "ar" image format as PI_DEVICE_BINARY_TYPE_NATIVE (#12587)
5b3ba9f 
That's what AOT for Intel GPUs produces when targeting multiple devices
at once.

This PR is built on top of #12586.
@aelovikov-intel
Copy link
Contributor Author

SYCL Nigthly failures.

OpenCL CPU (on AMD runner):

Timed Out Tests (1):
  SYCL :: GroupAlgorithm/root_group.cpp

OpenCL CPU (Intel Arc GPU runner):

Unexpectedly Passed Tests (1):
  SYCL :: KernelFusion/Reduction/reduction.cpp

OpenCL CPU (Intel GEN12 runner) failed due to infrastructure issues.

@aelovikov-intel
Copy link
Contributor Author

Another run of SYCL Nightly (it was still latest commit over the weekend):
OpenCL CPU (AMD runner):

Timed Out Tests (2):
  SYCL :: Basic/accessor/accessor.cpp
  SYCL :: GroupAlgorithm/root_group.cpp

OpenCL CPU (Intel Arc GPU runner):

Timed Out Tests (1):
  SYCL :: Scheduler/SubBufferRemapping.cpp

********************
Unexpectedly Passed Tests (1):
  SYCL :: KernelFusion/Reduction/reduction.cpp

OpenCL CPU (Intel GEN12 runner) failed due to infrastructure issues.

@aelovikov-intel
Copy link
Contributor Author

aelovikov-intel commented Feb 5, 2024 •
edited
Loading

And the third SYCL Nightly run:

OpenCL CPU (AMD runner):

Timed Out Tests (1):
  SYCL :: GroupAlgorithm/root_group.cpp

OpenCL CPU (Intel Arc GPU runner):

Unexpectedly Passed Tests (1):
  SYCL :: KernelFusion/Reduction/reduction.cpp

OpenCL CPU (Intel GEN12 runner) failed due to infrastructure issues.

@aelovikov-intel aelovikov-intel mentioned this pull request Feb 5, 2024
Merged
aelovikov-intel added a commit to aelovikov-intel/llvm that referenced this pull request Feb 5, 2024
@aelovikov-intel
[SYCL][E2E] XPASS->UNSUPPORTED for KernelFusion/Reduction/reduction.cpp
a377bf6 
See notes in
intel#12540 (comment)
intel#12586 (comment)
@aelovikov-intel aelovikov-intel mentioned this pull request Feb 5, 2024
Merged
aelovikov-intel added a commit that referenced this pull request Feb 5, 2024
@aelovikov-intel
[SYCL][E2E] XPASS->UNSUPPORTED for KernelFusion/Reduction/reduction.c…
20aee78 
…pp (#12607)

See notes in
#12540 (comment)
#12586 (comment)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bso-intel bso-intel bso-intel approved these changes

@steffenlarsen steffenlarsen steffenlarsen approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@aelovikov-intel @bso-intel @steffenlarsen