[MLIR] [AMDGPU] Use correct flags when building SerializeToHsaco

The SerializeToHsaco pass does not depend on ROCm being available on
the build system - it only requires ROCm to be present at runtime.
However, the CMake file that built it tested for
MLIR_ENABLE_ROCM_RUNNER , which implies that ROCm is currently
available and is used to control building ROCm integration tests.

Referencing MLIR_ENABLE_ROCM_RUNNER instead of
MLIR_ENABLE_ROCM_CONVERSIONS in the SerializeToHsaco build therefore
causes problems for clients who wish to build projects that depend on
this pass on a system without an AMD GPU present.

Reviewed By: whchung

Differential Revision: https://reviews.llvm.org/D120663

Author: krzysz00

mlir/lib/Dialect/GPU/CMakeLists.txt

@@ -119,7 +119,7 @@ if(MLIR_ENABLE_CUDA_RUNNER)
 
 endif()
 
-if(MLIR_ENABLE_ROCM_RUNNER)
+if(MLIR_ENABLE_ROCM_CONVERSIONS)
   if (NOT ("AMDGPU" IN_LIST LLVM_TARGETS_TO_BUILD))
     message(SEND_ERROR
       "Building mlir with ROCm support requires the AMDGPU backend")