[libcxx-commits] [libcxx] [libcxx] Adjust inline assembly constraints for the AMDGPU target (PR #101747)

Matt Arsenault via libcxx-commits libcxx-commits at lists.llvm.org
Mon Aug 5 10:19:46 PDT 2024


================
@@ -291,17 +291,27 @@ struct is_same<T, T> { enum {value = 1}; };
 // when optimizations are enabled.
 template <class Tp>
 inline Tp const& DoNotOptimize(Tp const& value) {
-    asm volatile("" : : "r,m"(value) : "memory");
-    return value;
+  // The `m` constraint is invalid in the AMDGPU backend.
+#  if defined(__AMDGPU__) || defined(__NVPTX__)
----------------
arsenm wrote:

Messed up formatting 

https://github.com/llvm/llvm-project/pull/101747


More information about the libcxx-commits mailing list