================ @@ -106,106 +100,6 @@ define <2 x half> @flat_atomic_fadd_v2f16_rtn(ptr %ptr, <2 x half> %data) { ret <2 x half> %ret } -define amdgpu_kernel void @flat_atomic_fadd_v2bf16_noret(ptr %ptr, <2 x i16> %data) { -; GFX940-LABEL: flat_atomic_fadd_v2bf16_noret: -; GFX940: ; %bb.0: -; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24 -; GFX940-NEXT: s_load_dword s4, s[2:3], 0x2c -; GFX940-NEXT: s_waitcnt lgkmcnt(0) -; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1] -; GFX940-NEXT: v_mov_b32_e32 v2, s4 -; GFX940-NEXT: flat_atomic_pk_add_bf16 v[0:1], v2 -; GFX940-NEXT: s_endpgm - %ret = call <2 x i16> @llvm.amdgcn.flat.atomic.fadd.v2bf16.p0(ptr %ptr, <2 x i16> %data) ---------------- yxsamliu wrote:
do we have equivalent codegen tests for the counterpart atomicrmw insts to cover the removed tests? same as below https://github.com/llvm/llvm-project/pull/97050 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits