[rocjitsu] Add CI workflow with HIP device kernel tests - #6448
Closed
newling wants to merge 1 commit into
Closed
Conversation
github-actions
Bot
added
the
github actions
newling
changed the title
newling
marked this pull request as ready for review
May 27, 2026 02:29
Contributor
Author
|
@amd-arosa I want to land this as a stop-gap until you have rocjitsu tests running in CI. Currently there are no rocjitsu tests run in CI (unless I'm mistaken) which isn't good. |
kuhar
reviewed
May 27, 2026
Comment on lines
+50
to
+57
| # Add the AMD ROCm apt repo and its signing key. | ||
| sudo mkdir -p --mode=0755 /etc/apt/keyrings | ||
| wget -q -O - https://repo.radeon.com/rocm/rocm.gpg.key \ | ||
| | gpg --dearmor \ | ||
| | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null | ||
| echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] \ | ||
| https://repo.radeon.com/rocm/apt/latest noble main" \ | ||
| | sudo tee /etc/apt/sources.list.d/rocm.list |
Member
There was a problem hiding this comment.
Why not grab therock tarball / pip install?
Contributor
Author
There was a problem hiding this comment.
That's what I (well, Claude) was trying initially, but couldn't get it work one CI job where it failed: https://github.com/ROCm/rocm-systems/actions/runs/26478854701/job/77971169397
So when Claude got it working with an apt install I pivoted to this approach. I can try with therock again, is would be nicer.
Contributor
Author
Comment on lines
+76
to
+77
| CC: clang | ||
| CXX: clang++ |
Member
There was a problem hiding this comment.
nit: set these via -DCMAKE_CXX_COMPILER / C_COMPILER? it's a bit awkward to use to separate configuration mechanisms
kuhar
reviewed
May 27, 2026
| name: Linux (clang, Release) | ||
| runs-on: ubuntu-24.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 |
Member
There was a problem hiding this comment.
I think the best practice is to pin to a specific SHA
3 tasks
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed from the AMD apt repo for hipcc and device libraries. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related: ROCm#6479 (alternative using pip rocm-sdk-core)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul, rocBLAS GEMM). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK and math libraries installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm SDK installed via pip from TheRock. Decouple HIP test cmake gate from HSA_RUNTIME64 — the HIP tests only need hipcc for compilation and LD_PRELOAD at runtime. Prefer ROCM_PATH from env over deriving from compiler location in rj_add_device_kernel, for pip SDK compatibility. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative approach using ROCm apt packages - ROCm#6441: earlier pip attempt (closed)
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 27, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 28, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 29, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
May 29, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
Contributor
Author
|
See #6499 |
newling
added a commit
to newling/rocm-systems
that referenced
this pull request
Jun 5, 2026
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting. After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed via TheRock nightly tarball. RocminfoTest excluded (requires /dev/kfd, unavailable on CI). Related PRs: - ROCm#6448: alternative using ROCm apt packages - ROCm#6479: alternative using ROCm pip packages
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
2 participants
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
Before this PR, the TheRock CI builds rocjitsu (as part of THEROCK_ENABLE_EMULATION) but does not run its tests — rocjitsu is not in repos-config.json. The only rocjitsu-specific CI is pre-commit formatting.
After this PR, every PR touching emulation/rocjitsu/ gets a dedicated job that builds rocjitsu and runs its full ctest suite (~450 tests), including HIP integration tests (memcpy, vector_add, matmul). No GPU hardware needed — tests run on the built-in CPU emulator. ROCm installed from the AMD apt repo for hipcc and device libraries.
RocminfoTest excluded (requires /dev/kfd, unavailable on CI).
Test plan