[Mlir-commits] [mlir] [mlir][linalg] Restrict linalg.pack to not have artificial padding. (PR #150522)

[LLVM Continuous Integration]

llvm-ci wrote:

LLVM Buildbot has detected a new failure on builder `mlir-nvidia` running on `mlir-nvidia` while building `mlir` at step 7 "test-build-check-mlir-build-only-check-mlir".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/138/builds/16619

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

```
Step 7 (test-build-check-mlir-build-only-check-mlir) failure: test (failure)
******************** TEST 'MLIR :: Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir' FAILED ********************
Exit Code: 2

Command Output (stdout):
--
# RUN: at line 10
/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-opt /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir -transform-interpreter -test-transform-dialect-erase-schedule -one-shot-bufferize="bufferize-function-boundaries" -buffer-deallocation-pipeline="private-function-dynamic-ownership" -cse -canonicalize -test-lower-to-llvm | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-runner -e main -entry-point-result=void -shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_runner_utils.so,/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_c_runner_utils.so | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/FileCheck /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir
# executed command: /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-opt /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir -transform-interpreter -test-transform-dialect-erase-schedule -one-shot-bufferize=bufferize-function-boundaries -buffer-deallocation-pipeline=private-function-dynamic-ownership -cse -canonicalize -test-lower-to-llvm
# .---command stderr------------
# | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir:89:13: error: expected 'tensor<1x16x8x1xi32>' for the packed domain value, got 'tensor<2x16x8x1xi32>'
# |   %A_pack = linalg.pack %A padding_value(%zero : i32) inner_dims_pos = [0, 1] inner_tiles = [8, 1] into %A_pack_empty : tensor<7x16xi32> -> tensor<2x16x8x1xi32>
# |             ^
# | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir:89:13: note: see current operation: %4 = "linalg.pack"(%arg0, %1, %0) <{inner_dims_pos = array<i64: 0, 1>, operandSegmentSizes = array<i32: 1, 1, 1, 0>, static_inner_tiles = array<i64: 8, 1>}> : (tensor<7x16xi32>, tensor<2x16x8x1xi32>, i32) -> tensor<2x16x8x1xi32>
# `-----------------------------
# error: command failed with exit status: 1
# executed command: /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-runner -e main -entry-point-result=void -shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_runner_utils.so,/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_c_runner_utils.so
# .---command stderr------------
# | Error: entry point not found
# `-----------------------------
# error: command failed with exit status: 1
# executed command: /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/FileCheck /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir
# .---command stderr------------
# | FileCheck error: '<stdin>' is empty.
# | FileCheck command line:  /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/FileCheck /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/Dialect/Linalg/CPU/pack-unpack-mmt4d.mlir
# `-----------------------------
# error: command failed with exit status: 2

--

********************


```

</details>

https://github.com/llvm/llvm-project/pull/150522