[llvm] [AMDGPU][MC] Allow dpp in v_dot2_f32_bf16 for GFX11 and 12 (PR #142451)

Stanislav Mekhanoshin via llvm-commits llvm-commits at lists.llvm.org
Mon Jun 2 12:35:59 PDT 2025


================
@@ -1878,6 +1878,8 @@ defm V_DOT4_F32_BF8_FP8 : VOP3P_Realtriple<GFX12Gen, 0x25>;
 defm V_DOT4_F32_FP8_FP8 : VOP3P_Realtriple<GFX12Gen, 0x26>;
 defm V_DOT4_F32_BF8_BF8 : VOP3P_Realtriple<GFX12Gen, 0x27>;
 
+defm V_DOT2_F32_BF16 : VOP3P_Realtriple<GFX12Gen, 0x1a>;
----------------
rampitec wrote:

There is VOP3P_Realtriple_gfx11_gfx12 already.

https://github.com/llvm/llvm-project/pull/142451


More information about the llvm-commits mailing list