[DXC][DirectX][Intel] Incorrect `QuadAll` results for 2D compute quads
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 72/100
- Issue type
- Bug
- Clarity
- Clearly specified
- Activity status
- Active
- Domain
- testing-qa
Research direction
Start by locating the native cs_6_7 QuadAll test in the offload test suite and read its shader and expected output. Check how its 16 predicate patterns map to the two 2×2 quads for [numthreads(4, 2, 1)], then compare the result on the reported Intel Arc Pro B50 setup. Done means determining whether the observed masks contradict the HLSL quad mapping and recording a reproducible test result.
Written by the indexing model from the issue text.
Description
DXC’s native cs_6_7 QuadAll test returns incorrect results on Intel Arc Pro B50 with Direct3D 12 and driver 32.0.101.9150 .
The shader uses [numthreads(4, 2, 1)] and tests all 16 predicate patterns. The HLSL specification requires two 2×2 quads per group.
Expected: Mask 15, lanes 0–3
Actual: Masks 12–15, lanes 2–3
The actual output matches grouping four consecutive SV_GroupIndex values into each quad instead of using 2×2 SV_GroupThreadID blocks. This strongly suggests incorrect quad mapping in the Intel driver.
- Dominant language
- C++
- Stars
- 20
- Forks
- 41
- Avg merge
- 5d 2h
- Merged PRs (30d)
- 29
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from llvm/offload-test-suite
-
Change Lavapipe installation on DXC CIPossibly taken @joaosaffran claimed this 1 day ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
llvm/offload-test-suite#1703 · 1 assignee ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
llvm/offload-test-suite#1562 ·
Maintainers usually reply within 1 day
-
[LongVec] Add a abs test casePossibly taken @farzonl claimed this 17 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
llvm/offload-test-suite#1441 · 2 comments · 1 assignee ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 65/100
llvm/offload-test-suite#1712 ·
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
llvm/offload-test-suite#1702 ·
Maintainers usually reply within 1 day
All issues in llvm/offload-test-suite
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
xiaoyifang/goldendict-ng#3148 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 91/100
triton-inference-server/server#9069 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
Maintainers usually reply within 4 days
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
[Bug]: Launching Space Calibrator causes Bluetooth mouse lag due to a 100% duty-cycle BLE scanPossibly taken @Yuuki204 claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100