[Mlir-commits] [mlir] [mlir] Change default NVVM compilation to `fatbin` from `bin` (PR #70052)

[Guray Ozen]

grypp wrote:

Submitting this as it should fix the integration test problem below:
```
******************** TEST 'MLIR :: Integration/GPU/CUDA/all-reduce-and.mlir' FAILED ********************
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 1
/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-opt /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/GPU/CUDA/all-reduce-and.mlir  | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-opt -test-lower-to-nvvm  | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-cpu-runner    --shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_cuda_runtime.so    --shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_runner_utils.so    --entry-point-result=void  | /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/FileCheck /vol/worker/mlir-nvidia/mlir-nvidia/llvm.src/mlir/test/Integration/GPU/CUDA/all-reduce-and.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/GPU/CUDA/all-reduce-and.mlir
# executed command: /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-opt -test-lower-to-nvvm
# executed command: /vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/bin/mlir-cpu-runner --shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_cuda_runtime.so --shared-libs=/vol/worker/mlir-nvidia/mlir-nvidia/llvm.obj/lib/libmlir_runner_utils.so --entry-point-result=void
# .---command stderr------------
# | 'cuModuleLoadData(&module, data)' failed with 'CUDA_ERROR_INVALID_SOURCE'
# | 'cuModuleGetFunction(&function, module, name)' failed with 'CUDA_ERROR_INVALID_HANDLE'
# | 'cuFuncSetAttribute( function, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES, smem)' failed with 'CUDA_ERROR_INVALID_HANDLE'
# | 'cuLaunchKernel(function, gridX, gridY, gridZ, blockX, blockY, blockZ, smem, stream, params, extra)' failed with 'CUDA_ERROR_INVALID_HANDLE'
# | 'cuModuleUnload(module)' failed with 'CUDA_ERROR_INVALID_HANDLE'
```

https://github.com/llvm/llvm-project/pull/70052