Xtensa ISS op-test stage (hifi seed) (#20315)#20315
Closed
aliafzal wants to merge 1 commit into
Closed
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20315
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 270 PendingAs of commit ca4624e with merge base 574bfca ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@aliafzal has exported this pull request. If you are a Meta employee, you can view the originating Diff in D108805403. |
This PR needs a
|
meta-codesync
Bot
changed the title
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Jun 17, 2026
Summary: Add the first op-level test stage for the Cadence backend, run on the Xtensa Instruction Set Simulator (xt-run), mirroring the host cpu-build -> cpu-test flow with a new hifi-op-test job that runs after hifi-build. The existing operator gtests (ExecuTorch OperatorTest + EXPECT_TENSOR_EQ, calling the kernels directly) are cross-compiled for Xtensa via cadence.cmake and run on xt-run --exit_with_target_code, so the gtest exit code drives pass/fail. googletest is built for the target (not the host find_package), with libc++ and GTEST_HAS_PTHREAD=0; gated by EXECUTORCH_BUILD_CADENCE_OP_TESTS. This diff seeds the suite with one quantized op (test_op_quantized_relu_out) to prove the harness end to end; later diffs in the stack add vision, more hifi ops, and a models category. Differential Revision: D108805403
aliafzal
force-pushed
the
export-D108805403
branch
from
bf0a729 to
e03a5a2
Compare
aliafzal
added a commit
to aliafzal/executorch
that referenced
this pull request
Jun 17, 2026
Summary: Add the first op-level test stage for the Cadence backend, run on the Xtensa Instruction Set Simulator (xt-run), mirroring the host cpu-build -> cpu-test flow with a new hifi-op-test job that runs after hifi-build. The existing operator gtests (ExecuTorch OperatorTest + EXPECT_TENSOR_EQ, calling the kernels directly) are cross-compiled for Xtensa via cadence.cmake and run on xt-run --exit_with_target_code, so the gtest exit code drives pass/fail. googletest is built for the target (not the host find_package), with libc++ and GTEST_HAS_PTHREAD=0; gated by EXECUTORCH_BUILD_CADENCE_OP_TESTS. This diff seeds the suite with one quantized op (test_op_quantized_relu_out) to prove the harness end to end; later diffs in the stack add vision, more hifi ops, and a models category. Differential Revision: D108805403
aliafzal
force-pushed
the
export-D108805403
branch
from
e03a5a2 to
36df0b5
Compare
meta-codesync
Bot
changed the title
aliafzal
force-pushed
the
export-D108805403
branch
from
36df0b5 to
1d33c2d
Compare
Summary: Add the first op-level test stage for the Cadence backend, run on the Xtensa Instruction Set Simulator (xt-run), mirroring the host cpu-build -> cpu-test flow with a new hifi-op-test job that runs after hifi-build. The existing operator gtests (ExecuTorch OperatorTest + EXPECT_TENSOR_EQ, calling the kernels directly) are cross-compiled for Xtensa via cadence.cmake and run on xt-run --exit_with_target_code, so the gtest exit code drives pass/fail. googletest is built for the target (not the host find_package), with libc++ and GTEST_HAS_PTHREAD=0; gated by EXECUTORCH_BUILD_CADENCE_OP_TESTS. This diff seeds the suite with one quantized op (test_op_quantized_relu_out) to prove the harness end to end; later diffs in the stack add vision, more hifi ops, and a models category. Differential Revision: D108805403
meta-codesync
Bot
changed the title
aliafzal
force-pushed
the
export-D108805403
branch
from
1d33c2d to
ca4624e
Compare
Contributor
Author
|
Discarding this op-test export; superseded. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Summary:
Add the first op-level test stage for the Cadence backend, run on the Xtensa
Instruction Set Simulator (xt-run), mirroring the host cpu-build -> cpu-test
flow with a new hifi-op-test job that runs after hifi-build.
The existing operator gtests (ExecuTorch OperatorTest + EXPECT_TENSOR_EQ,
calling the kernels directly) are cross-compiled for Xtensa via cadence.cmake
and run on xt-run --exit_with_target_code, so the gtest exit code drives
pass/fail. googletest is built for the target (not the host find_package), with
libc++ and GTEST_HAS_PTHREAD=0; gated by EXECUTORCH_BUILD_CADENCE_OP_TESTS.
This diff seeds the suite with one quantized op (test_op_quantized_relu_out) to
prove the harness end to end; later diffs in the stack add vision, more hifi
ops, and a models category.
Differential Revision: D108805403