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

Jun Wang via llvm-commits llvm-commits at lists.llvm.org
Tue Jun 3 10:59:40 PDT 2025


================
@@ -45,6 +45,15 @@ v_dot2_f32_bf16 v5, src_scc, vcc_lo, src_scc neg_lo:[1,0,0] neg_hi:[1,0,0]
 v_dot2_f32_bf16 v255, 0xfe0b, vcc_hi, 0.5 neg_lo:[0,0,0] neg_hi:[0,0,0] clamp
 // GFX12: [0xff,0xc0,0x1a,0xcc,0xff,0xd6,0xc0,0x1b,0x0b,0xfe,0x00,0x00]
 
+v_dot2_f32_bf16_e64_dpp v1, v2, v3, v4 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf
----------------
jwanggit86 wrote:

done.

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


More information about the llvm-commits mailing list