================ @@ -936,19 +978,20 @@ define amdgpu_kernel void @add_i32_varying_vdata(ptr addrspace(1) %out, ptr addr ; GFX12W32-NEXT: s_cbranch_scc1 .LBB2_1 ; GFX12W32-NEXT: ; %bb.2: ; %ComputeEnd ; GFX12W32-NEXT: v_mbcnt_lo_u32_b32 v1, exec_lo, 0 -; GFX12W32-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1) +; GFX12W32-NEXT: s_delay_alu instid0(VALU_DEP_1) ; GFX12W32-NEXT: v_cmp_eq_u32_e32 vcc_lo, 0, v1 ; GFX12W32-NEXT: ; implicit-def: $vgpr1 -; GFX12W32-NEXT: s_and_saveexec_b32 s1, vcc_lo -; GFX12W32-NEXT: s_xor_b32 s1, exec_lo, s1 -; GFX12W32-NEXT: s_cbranch_execz .LBB2_4 +; GFX12W32-NEXT: s_xor_b32 s1, vcc_lo, exec_lo +; GFX12W32-NEXT: s_cmp_lg_u32 vcc_lo, 0 +; GFX12W32-NEXT: s_cmov_b32 exec_lo, vcc_lo +; GFX12W32-NEXT: s_cbranch_scc0 .LBB2_4 ---------------- ruiling wrote:
This can also be simplified into: s_and_saveexec_b32 s1, vcc_lo s_cselect_b32 exec_lo, vcc_lo, s1 s_cbranch_scc0 .LBB2_4 https://github.com/llvm/llvm-project/pull/108596 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
