[Mlir-commits] [mlir] [MLIR][XeGPU] Support leading unit dims in vector.multi_reduction in sg to wi pass (PR #188767)

[llvmlistbot at llvm.org]

github-actions[bot] wrote:

<!--PREMERGE ADVISOR COMMENT: Linux-->
# :penguin: Linux x64 Test Results

* 7728 tests passed
* 603 tests skipped
* 1 test failed

## Failed Tests
(click on a test name to see its output)

### MLIR
<details>
<summary>MLIR.Dialect/XeGPU/sg-to-wi-experimental-unit.mlir</summary>

```
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 2
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/mlir-opt  --xevm-attach-target='module=xevm_* chip=pvc' --allow-unregistered-dialect  --test-xegpu-sg-to-wi-distribute-experimental --split-input-file /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir | /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/mlir-opt '--xevm-attach-target=module=xevm_* chip=pvc' --allow-unregistered-dialect --test-xegpu-sg-to-wi-distribute-experimental --split-input-file /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir
# note: command had no output on stdout or stderr
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir
# .---command stderr------------
# | /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir:496:11: error: CHECK: expected string not found in input
# | // CHECK: %[[SHUF0_1:.*]], %{{.*}} = gpu.shuffle xor %[[RED0]], %[[C1]], %[[C16_0]] : f32
# |           ^
# | <stdin>:306:37: note: scanning from here
# |  %c1_i32_11 = arith.constant 1 : i32
# |                                     ^
# | <stdin>:306:37: note: with "RED0" equal to "3"
# |  %c1_i32_11 = arith.constant 1 : i32
# |                                     ^
# | <stdin>:306:37: note: with "C1" equal to "c1_i32_11"
# |  %c1_i32_11 = arith.constant 1 : i32
# |                                     ^
# | <stdin>:306:37: note: with "C16_0" equal to "c16_i32"
# |  %c1_i32_11 = arith.constant 1 : i32
# |                                     ^
# | <stdin>:308:18: note: possible intended match here
# |  %shuffleResult_13, %valid_14 = gpu.shuffle xor %13, %c1_i32_11, %c16_i32_12 : f32
# |                  ^
# | 
# | Input file: <stdin>
# | Check file: /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/test/Dialect/XeGPU/sg-to-wi-experimental-unit.mlir
# | 
# | -dump-input=help explains the following input dump.
# | 
# | Input was:
# | <<<<<<
# |              .
# |              .
# |              .
# |            301:  %9 = vector.insert %8, %cst_1 [0, 0] : f32 into vector<1x2xf32> 
# |            302:  %10 = vector.extract_strided_slice %cst {offsets = [0, 0, 1], sizes = [1, 1, 1], strides = [1, 1, 1]} : vector<1x1x2xf32> to vector<1x1x1xf32> 
# |            303:  %11 = vector.shape_cast %10 : vector<1x1x1xf32> to vector<1xf32> 
# |            304:  %12 = vector.extract %cst_0[0, 1] : f32 from vector<1x2xf32> 
# |            305:  %13 = vector.reduction <add>, %11 : vector<1xf32> into f32 
# |            306:  %c1_i32_11 = arith.constant 1 : i32 
# | check:496'0                                         X error: no match found
# | check:496'1                                           with "RED0" equal to "3"
# | check:496'2                                           with "C1" equal to "c1_i32_11"
# | check:496'3                                           with "C16_0" equal to "c16_i32"
# |            307:  %c16_i32_12 = arith.constant 16 : i32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            308:  %shuffleResult_13, %valid_14 = gpu.shuffle xor %13, %c1_i32_11, %c16_i32_12 : f32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | check:496'4                      ?                                                                  possible intended match
# |            309:  %14 = arith.addf %13, %shuffleResult_13 : f32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            310:  %c2_i32_15 = arith.constant 2 : i32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            311:  %c16_i32_16 = arith.constant 16 : i32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            312:  %shuffleResult_17, %valid_18 = gpu.shuffle xor %14, %c2_i32_15, %c16_i32_16 : f32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |            313:  %15 = arith.addf %14, %shuffleResult_17 : f32 
# | check:496'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# |              .
# |              .
# |              .
# | >>>>>>
# `-----------------------------
# error: command failed with exit status: 1

--

```
</details>

If these failures are unrelated to your changes (for example tests are broken or flaky at HEAD), please open an issue at https://github.com/llvm/llvm-project/issues and add the `infrastructure` label.

https://github.com/llvm/llvm-project/pull/188767