AMDGPU/SI: Select mad patterns to v_mac_f32
The two-address instruction pass will convert these back to v_mad_f32
if necessary.
Differential Revision: http://reviews.llvm.org/D11060
llvm-svn: 242038
diff --git a/llvm/test/CodeGen/AMDGPU/mad-combine.ll b/llvm/test/CodeGen/AMDGPU/mad-combine.ll
index bc07162..c98f851 100644
--- a/llvm/test/CodeGen/AMDGPU/mad-combine.ll
+++ b/llvm/test/CodeGen/AMDGPU/mad-combine.ll
@@ -19,7 +19,7 @@
; SI-DAG: buffer_load_dword [[B:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4{{$}}
; SI-DAG: buffer_load_dword [[C:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8{{$}}
-; SI-STD: v_mad_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[C]]
+; SI-STD: v_mac_f32_e32 [[C]], [[B]], [[A]]
; SI-DENORM: v_fma_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[C]]
@@ -29,7 +29,8 @@
; SI-DENORM-SLOWFMAF: v_mul_f32_e32 [[TMP:v[0-9]+]], [[B]], [[A]]
; SI-DENORM-SLOWFMAF: v_add_f32_e32 [[RESULT:v[0-9]+]], [[C]], [[TMP]]
-; SI: buffer_store_dword [[RESULT]]
+; SI-DENORM: buffer_store_dword [[RESULT]]
+; SI-STD: buffer_store_dword [[C]]
define void @combine_to_mad_f32_0(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #1 {
%tid = tail call i32 @llvm.r600.read.tidig.x() #0
%gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
@@ -54,8 +55,8 @@
; SI-DAG: buffer_load_dword [[C:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8{{$}}
; SI-DAG: buffer_load_dword [[D:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:12{{$}}
-; SI-STD-DAG: v_mad_f32 [[RESULT0:v[0-9]+]], [[A]], [[B]], [[C]]
-; SI-STD-DAG: v_mad_f32 [[RESULT1:v[0-9]+]], [[A]], [[B]], [[D]]
+; SI-STD-DAG: v_mac_f32_e32 [[C]], [[B]], [[A]]
+; SI-STD-DAG: v_mac_f32_e32 [[D]], [[B]], [[A]]
; SI-DENORM-DAG: v_fma_f32 [[RESULT0:v[0-9]+]], [[A]], [[B]], [[C]]
; SI-DENORM-DAG: v_fma_f32 [[RESULT1:v[0-9]+]], [[A]], [[B]], [[D]]
@@ -64,8 +65,10 @@
; SI-DENORM-SLOWFMAF-DAG: v_add_f32_e32 [[RESULT0:v[0-9]+]], [[C]], [[TMP]]
; SI-DENORM-SLOWFMAF-DAG: v_add_f32_e32 [[RESULT1:v[0-9]+]], [[D]], [[TMP]]
-; SI-DAG: buffer_store_dword [[RESULT0]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI-DAG: buffer_store_dword [[RESULT1]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4{{$}}
+; SI-DENORM-DAG: buffer_store_dword [[RESULT0]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
+; SI-DENORM-DAG: buffer_store_dword [[RESULT1]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4{{$}}
+; SI-STD-DAG: buffer_store_dword [[C]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
+; SI-STD-DAG: buffer_store_dword [[D]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4{{$}}
; SI: s_endpgm
define void @combine_to_mad_f32_0_2use(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #1 {
%tid = tail call i32 @llvm.r600.read.tidig.x() #0
@@ -96,13 +99,14 @@
; SI-DAG: buffer_load_dword [[B:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4{{$}}
; SI-DAG: buffer_load_dword [[C:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8{{$}}
-; SI-STD: v_mad_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[C]]
+; SI-STD: v_mac_f32_e32 [[C]], [[B]], [[A]]
; SI-DENORM: v_fma_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[C]]
; SI-DENORM-SLOWFMAF: v_mul_f32_e32 [[TMP:v[0-9]+]], [[B]], [[A]]
; SI-DENORM-SLOWFMAF: v_add_f32_e32 [[RESULT:v[0-9]+]], [[TMP]], [[C]]
-; SI: buffer_store_dword [[RESULT]]
+; SI-DENORM: buffer_store_dword [[RESULT]]
+; SI-STD: buffer_store_dword [[C]]
define void @combine_to_mad_f32_1(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #1 {
%tid = tail call i32 @llvm.r600.read.tidig.x() #0
%gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
@@ -482,7 +486,7 @@
; SI-DAG: buffer_load_dword [[E:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:16{{$}}
; SI-STD: v_mad_f32 [[TMP:v[0-9]+]], [[D]], [[E]], -[[C]]
-; SI-STD: v_mad_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[TMP]]
+; SI-STD: v_mac_f32_e32 [[TMP]], [[B]], [[A]]
; SI-DENORM: v_fma_f32 [[TMP:v[0-9]+]], [[D]], [[E]], -[[C]]
; SI-DENORM: v_fma_f32 [[RESULT:v[0-9]+]], [[A]], [[B]], [[TMP]]
@@ -492,7 +496,8 @@
; SI-DENORM-SLOWFMAF: v_add_f32_e32 [[TMP2:v[0-9]+]], [[TMP0]], [[TMP1]]
; SI-DENORM-SLOWFMAF: v_subrev_f32_e32 [[RESULT:v[0-9]+]], [[C]], [[TMP2]]
-; SI: buffer_store_dword [[RESULT]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
+; SI-DENORM: buffer_store_dword [[RESULT]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
+; SI-STD: buffer_store_dword [[TMP]], v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
; SI: s_endpgm
define void @aggressive_combine_to_mad_fsub_2_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #1 {
%tid = tail call i32 @llvm.r600.read.tidig.x() #0