Matrix failures on BMG Linux

### Describe the bug

https://github.com/intel/llvm/actions/runs/19151375733/job/54743282591?pr=20542


```
   SYCL :: Matrix/joint_matrix_bfloat16_accumulator.cpp
    SYCL :: Matrix/joint_matrix_half_accumulator.cpp
```

```

  
  ********************
  FAIL: SYCL :: Matrix/joint_matrix_bfloat16_accumulator.cpp (1688 of 1911)
  ******************** TEST 'SYCL :: Matrix/joint_matrix_bfloat16_accumulator.cpp' FAILED ********************
  Exit Code: -6
  
  Command Output (stdout):
  --
  # RUN: at line 21
  env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # executed command: env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 21
  env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # executed command: env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 22
  env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 22
  env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 23
  env IGC_JointMatrixLoadStoreOpt=1 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=1 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_bfloat16_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # .---command stderr------------
  # | terminate called after throwing an instance of 'sycl::_V1::exception'
  # |   what():  level_zero backend failed with error: 20 (UR_RESULT_ERROR_DEVICE_LOST)
  # `-----------------------------
  # error: command failed with exit status: -6
  
  --
  
  ********************
  FAIL: SYCL :: Matrix/joint_matrix_half_accumulator.cpp (1761 of 1911)
  ******************** TEST 'SYCL :: Matrix/joint_matrix_half_accumulator.cpp' FAILED ********************
  Exit Code: -6
  
  Command Output (stdout):
  --
  # RUN: at line 22
  env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # executed command: env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 22
  env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # executed command: env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 23
  env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 23
  env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=2 env env UR_LOADER_USE_LEVEL_ZERO_V2=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | B packed:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # RUN: at line 24
  env IGC_JointMatrixLoadStoreOpt=1 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu  /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # executed command: env IGC_JointMatrixLoadStoreOpt=1 env env UR_LOADER_USE_LEVEL_ZERO_V2=0 ONEAPI_DEVICE_SELECTOR=level_zero:gpu /__w/llvm/llvm/build-e2e/Matrix/Output/joint_matrix_half_accumulator.cpp.tmp.out
  # .---command stdout------------
  # | B row major:
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 8 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 16 x 16 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 16 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 1 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 16 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # | Testing: 32 x 64 x 32 [TM x TN x TK]
  # `-----------------------------
  # .---command stderr------------
  # | terminate called after throwing an instance of 'sycl::_V1::exception'
  # |   what():  level_zero backend failed with error: 20 (UR_RESULT_ERROR_DEVICE_LOST)
  # `-----------------------------
  # error: command failed with exit status: -6
  
  --
```

### To reproduce

1. Include a code snippet that is as short as possible
2. Specify the command which should be used to compile the program
3. Specify the command which should be used to launch the program
4. Indicate what is wrong and what was expected


### Environment

- OS: [e.g Windows/Linux]
- Target device and vendor: [e.g. Intel GPU]
- DPC++ version: [e.g. commit hash or output of `clang++ --version`]
- Dependencies version: [e.g. the output of `sycl-ls --verbose`]


### Additional context

_No response_

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Matrix failures on BMG Linux #20594

Describe the bug

To reproduce

Environment

Additional context

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Matrix failures on BMG Linux #20594

Description

Describe the bug

To reproduce

Environment

Additional context

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions