================
@@ -362,24 +358,34 @@ define amdgpu_ps void
@struct_buffer_atomic_add_v2f16_noret(<2 x half> %val, <4
ret void
}
-define amdgpu_ps float @struct_buffer_atomic_add_v2bf16_ret(<2 x i16> %val, <4
x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
+define amdgpu_ps float @struct_buffer_atomic_add_v2bf16_ret(<2 x bfloat> %val,
<4 x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
; GFX12-LABEL: struct_buffer_atomic_add_v2bf16_ret:
; GFX12: ; %bb.0:
; GFX12-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen offen
th:TH_ATOMIC_RETURN
+; GFX12-NEXT: v_mov_b32_e32 v1, 0
+; GFX12-NEXT: v_mov_b32_e32 v2, 0
; GFX12-NEXT: s_waitcnt vmcnt(0)
+; GFX12-NEXT: flat_store_b32 v[1:2], v0
+; GFX12-NEXT: v_mov_b32_e32 v0, 1.0
+; GFX12-NEXT: s_waitcnt lgkmcnt(0)
; GFX12-NEXT: ; return to shader part epilog
;
; GFX12-GISEL-LABEL: struct_buffer_atomic_add_v2bf16_ret:
; GFX12-GISEL: ; %bb.0:
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen
offen th:TH_ATOMIC_RETURN
+; GFX12-GISEL-NEXT: v_mov_b32_e32 v1, 0
+; GFX12-GISEL-NEXT: v_mov_b32_e32 v2, 0
; GFX12-GISEL-NEXT: s_waitcnt vmcnt(0)
+; GFX12-GISEL-NEXT: flat_store_b32 v[1:2], v0
+; GFX12-GISEL-NEXT: v_mov_b32_e32 v0, 1.0
+; GFX12-GISEL-NEXT: s_waitcnt lgkmcnt(0)
; GFX12-GISEL-NEXT: ; return to shader part epilog
- %orig = call <2 x i16> @llvm.amdgcn.struct.buffer.atomic.fadd.v2bf16(<2 x
i16> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
- %r = bitcast <2 x i16> %orig to float
----------------
mariusz-sikora-at-amd wrote:
Found issue in GlobalISel and bitcast with bfloat type. I prepare fix and push
in different change.
https://github.com/llvm/llvm-project/pull/75917
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
