[clang] [HIP][SPIR-V] Enable optimizations for amdgcnspirv target (PR #189383)

[Marcos Maronas via cfe-commits]

================
@@ -212,7 +212,7 @@
 // Check mixed AMDGCNSPIRV and concrete GPU arch.
 //
 
-// AMDGCNSPIRV: "-cc1" "-triple" "spirv64-amd-amdhsa" {{.*}}"-emit-llvm-bc" {{.*}}"-fembed-bitcode=marker" "-disable-llvm-passes" {{.*}} "-o" "[[AMDGCNSPV_BC:.*bc]]"
+// AMDGCNSPIRV: "-cc1" "-triple" "spirv64-amd-amdhsa" {{.*}}"-emit-llvm-bc" {{.*}}"-fembed-bitcode=marker"{{.*}}"-mllvm" "-vectorize-loops=false"{{.*}} "-o" "[[AMDGCNSPV_BC:.*bc]]"
----------------
maarquitos14 wrote:

What about `"-mllvm", "-vectorize-slp=false"`, `"-fno-unroll-loops"` and `"-mllvm", "-interleave-loops=false"`?

https://github.com/llvm/llvm-project/pull/189383