1 files changed, 8 insertions, 14 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/bf16-math.ll b/llvm/test/CodeGen/AMDGPU/bf16-math.ll
index 682b3b4..30a7864 100644
--- a/llvm/test/CodeGen/AMDGPU/bf16-math.ll
+++ b/llvm/test/CodeGen/AMDGPU/bf16-math.ll
@@ -391,9 +391,7 @@ define amdgpu_ps float @test_clamp_v2bf16_folding(<2 x bfloat> %src0, <2 x bfloa
 define amdgpu_ps void @v_test_mul_add_v2bf16_vvv(ptr addrspace(1) %out, <2 x bfloat> %a, <2 x bfloat> %b, <2 x bfloat> %c) {
 ; GCN-LABEL: v_test_mul_add_v2bf16_vvv:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_pk_mul_bf16 v2, v2, v3
-; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GCN-NEXT:    v_pk_add_bf16 v2, v2, v4
+; GCN-NEXT:    v_pk_fma_bf16 v2, v2, v3, v4
 ; GCN-NEXT:    global_store_b32 v[0:1], v2, off
 ; GCN-NEXT:    s_endpgm
   %mul = fmul contract <2 x bfloat> %a, %b
@@ -405,9 +403,7 @@ define amdgpu_ps void @v_test_mul_add_v2bf16_vvv(ptr addrspace(1) %out, <2 x bfl
 define amdgpu_ps void @v_test_mul_add_v2bf16_vss(ptr addrspace(1) %out, <2 x bfloat> %a, <2 x bfloat> inreg %b, <2 x bfloat> inreg %c) {
 ; GCN-LABEL: v_test_mul_add_v2bf16_vss:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_pk_mul_bf16 v2, v2, s0
-; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GCN-NEXT:    v_pk_add_bf16 v2, v2, s1
+; GCN-NEXT:    v_pk_fma_bf16 v2, v2, s0, s1
 ; GCN-NEXT:    global_store_b32 v[0:1], v2, off
 ; GCN-NEXT:    s_endpgm
   %mul = fmul contract <2 x bfloat> %a, %b
@@ -419,9 +415,9 @@ define amdgpu_ps void @v_test_mul_add_v2bf16_vss(ptr addrspace(1) %out, <2 x bfl
 define amdgpu_ps void @v_test_mul_add_v2bf16_sss(ptr addrspace(1) %out, <2 x bfloat> inreg %a, <2 x bfloat> inreg %b, <2 x bfloat> inreg %c) {
 ; GCN-LABEL: v_test_mul_add_v2bf16_sss:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_pk_mul_bf16 v2, s0, s1
+; GCN-NEXT:    v_mov_b32_e32 v2, s2
 ; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GCN-NEXT:    v_pk_add_bf16 v2, v2, s2
+; GCN-NEXT:    v_pk_fma_bf16 v2, s0, s1, v2
 ; GCN-NEXT:    global_store_b32 v[0:1], v2, off
 ; GCN-NEXT:    s_endpgm
   %mul = fmul contract <2 x bfloat> %a, %b
@@ -433,9 +429,7 @@ define amdgpu_ps void @v_test_mul_add_v2bf16_sss(ptr addrspace(1) %out, <2 x bfl
 define amdgpu_ps void @v_test_mul_add_v2bf16_vsc(ptr addrspace(1) %out, <2 x bfloat> %a, <2 x bfloat> inreg %b) {
 ; GCN-LABEL: v_test_mul_add_v2bf16_vsc:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_pk_mul_bf16 v2, v2, s0
-; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GCN-NEXT:    v_pk_add_bf16 v2, v2, 0.5 op_sel_hi:[1,0]
+; GCN-NEXT:    v_pk_fma_bf16 v2, v2, s0, 0.5 op_sel_hi:[1,1,0]
 ; GCN-NEXT:    global_store_b32 v[0:1], v2, off
 ; GCN-NEXT:    s_endpgm
   %mul = fmul contract <2 x bfloat> %a, %b
@@ -447,9 +441,9 @@ define amdgpu_ps void @v_test_mul_add_v2bf16_vsc(ptr addrspace(1) %out, <2 x bfl
 define amdgpu_ps void @v_test_mul_add_v2bf16_vll(ptr addrspace(1) %out, <2 x bfloat> %a) {
 ; GCN-LABEL: v_test_mul_add_v2bf16_vll:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_pk_mul_bf16 v2, 0x42c83f80, v2
-; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GCN-NEXT:    v_pk_add_bf16 v2, 0x43484000, v2
+; GCN-NEXT:    s_mov_b32 s0, 0x43484000
+; GCN-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
+; GCN-NEXT:    v_pk_fma_bf16 v2, 0x42c83f80, v2, s0
 ; GCN-NEXT:    global_store_b32 v[0:1], v2, off
 ; GCN-NEXT:    s_endpgm
   %mul = fmul contract <2 x bfloat> %a, <bfloat 1.0, bfloat 100.0>