================ @@ -754,13 +754,21 @@ define amdgpu_kernel void @constant_load_v16i16_align2(ptr addrspace(4) %ptr0) # ; GFX12-NEXT: global_load_u16 v6, v8, s[0:1] offset:8 ; GFX12-NEXT: global_load_u16 v5, v8, s[0:1] offset:4 ; GFX12-NEXT: global_load_u16 v4, v8, s[0:1] +; GFX12-NEXT: s_wait_loadcnt 0x7 ---------------- jayfoad wrote:
This wait is required to ensure that the global_load_u16 on line 749 writes to v3 before the global_load_d16_hi_b16 on line 758. https://github.com/llvm/llvm-project/pull/105549 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
