[llvm] [NVPTX] Add sparse MMA intrinsics (PR #150950)

LLVM Continuous Integration via llvm-commits llvm-commits at lists.llvm.org
Fri Aug 22 08:46:36 PDT 2025


llvm-ci wrote:

LLVM Buildbot has detected a new failure on builder `llvm-nvptx64-nvidia-ubuntu` running on `as-builder-7` while building `llvm` at step 6 "test-build-unified-tree-check-llvm".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/160/builds/23469

<details>
<summary>Here is the relevant piece of the build log for the reference</summary>

```
Step 6 (test-build-unified-tree-check-llvm) failure: test (failure)
******************** TEST 'LLVM :: CodeGen/NVPTX/wmma-ptx71-sm80.py' FAILED ********************
Exit Code: 255

Command Output (stderr):
--
"/usr/bin/python3" /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/llvm-project/llvm/test/CodeGen/NVPTX/wmma-ptx71-sm80.py --ptx=71 --gpu-arch=80 > /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll # RUN: at line 2
+ /usr/bin/python3 /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/llvm-project/llvm/test/CodeGen/NVPTX/wmma-ptx71-sm80.py --ptx=71 --gpu-arch=80
/home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/llvm-project/llvm/test/CodeGen/NVPTX/wmma.py:1270: SyntaxWarning: invalid escape sequence '\.'
  """
/home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll < /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll            --check-prefixes=INTRINSICS,M16N16,EXTGEOM,INT,SUBINT,MMA,ALTFLOAT,DOUBLE,PTX65MMA,PTX65LDMATRIX,PTX71MMA # RUN: at line 3
+ /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll --check-prefixes=INTRINSICS,M16N16,EXTGEOM,INT,SUBINT,MMA,ALTFLOAT,DOUBLE,PTX65MMA,PTX65LDMATRIX,PTX71MMA
/home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll < /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll            --check-prefixes=INTRINSICS # RUN: at line 5
+ /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll --check-prefixes=INTRINSICS
/home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/llc < /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71            | /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll # RUN: at line 7
+ /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/llc -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71
+ /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/FileCheck /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll
/home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/llc < /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/test/CodeGen/NVPTX/Output/wmma-ptx71-sm80.py.tmp-ptx71-sm_80.ll -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71            | /usr/local/cuda/bin/ptxas -arch=sm_60 -c - -arch=sm_80 # RUN: at line 9
+ /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/bin/llc -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx71
+ /usr/local/cuda/bin/ptxas -arch=sm_60 -c - -arch=sm_80
ptxas warning : incompatible redefinition for option 'gpu-name', the last value of this option was used
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38569; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38609; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38649; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38689; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38737; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38785; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38825; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38865; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38905; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38945; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 38993; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39041; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39077; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39111; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39145; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39179; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39217; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39257; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39297; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39337; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39381; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39423; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39465; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39465; error   : Argument 6 of instruction 'Sparse mma': value '2' out of range, expected to be in range [0..1]
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39507; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39507; error   : Argument 6 of instruction 'Sparse mma': value '3' out of range, expected to be in range [0..1]
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39553; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39601; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39649; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
ptxas /home/buildbot/worker/as-builder-7/llvm-nvptx64-nvidia-ubuntu/build/lit-tmp-g8hraboa/tmpxft_0032dae9_00000000-0_stdin, line 39697; info    : Advisory: Modifier '.sp::ordered_metadata' should be used on instruction 'mma' instead of modifier '.sp' as it is expected to have substantially reduced performance on some future architectures
...

```

</details>

https://github.com/llvm/llvm-project/pull/150950


More information about the llvm-commits mailing list