From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Thu, 12 Jan 2017 18:26:30 +0000 (+0000)
Subject: AMDGPU: Fold fneg into fmul_legacy
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=49dd8fcb21ca39c846f92f1858b0ec0a875082a2;p=llvm

AMDGPU: Fold fneg into fmul_legacy

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291784 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index 99700147880..a6c5e06d883 100644
--- a/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -2815,6 +2815,7 @@ static bool fnegFoldsIntoOp(unsigned Opc) {
   case ISD::FMAD:
   case AMDGPUISD::RCP:
   case AMDGPUISD::RCP_LEGACY:
+  case AMDGPUISD::FMUL_LEGACY:
     return true;
   default:
     return false;
@@ -2860,8 +2861,10 @@ SDValue AMDGPUTargetLowering::performFNegCombine(SDNode *N,
       DAG.ReplaceAllUsesWith(N0, DAG.getNode(ISD::FNEG, SL, VT, Res));
     return Res;
   }
-  case ISD::FMUL: {
+  case ISD::FMUL:
+  case AMDGPUISD::FMUL_LEGACY: {
     // (fneg (fmul x, y)) -> (fmul x, (fneg y))
+    // (fneg (fmul_legacy x, y)) -> (fmul_legacy x, (fneg y))
     SDValue LHS = N0.getOperand(0);
     SDValue RHS = N0.getOperand(1);
 
@@ -2872,7 +2875,7 @@ SDValue AMDGPUTargetLowering::performFNegCombine(SDNode *N,
     else
       RHS = DAG.getNode(ISD::FNEG, SL, VT, RHS);
 
-    SDValue Res = DAG.getNode(ISD::FMUL, SL, VT, LHS, RHS);
+    SDValue Res = DAG.getNode(Opc, SL, VT, LHS, RHS);
     if (!N0.hasOneUse())
       DAG.ReplaceAllUsesWith(N0, DAG.getNode(ISD::FNEG, SL, VT, Res));
     return Res;
diff --git a/test/CodeGen/AMDGPU/fneg-combines.ll b/test/CodeGen/AMDGPU/fneg-combines.ll
index b692332b436..c09b7e1fcde 100644
--- a/test/CodeGen/AMDGPU/fneg-combines.ll
+++ b/test/CodeGen/AMDGPU/fneg-combines.ll
@@ -1052,11 +1052,189 @@ define void @v_fneg_rcp_legacy_f32(float addrspace(1)* %out, float addrspace(1)*
   ret void
 }
 
+; --------------------------------------------------------------------------------
+; fmul_legacy tests
+; --------------------------------------------------------------------------------
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_legacy_f32_e64 [[RESULT:v[0-9]+]], [[A]], -[[B]]
+; GCN-NEXT: buffer_store_dword [[RESULT]]
+define void @v_fneg_mul_legacy_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store float %fneg, float addrspace(1)* %out.gep
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_store_use_mul_legacy_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_mul_legacy_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_xor_b32_e32 [[NEG_MUL_LEGACY:v[0-9]+]], 0x80000000, [[ADD]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL_LEGACY]]
+; GCN: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_legacy_store_use_mul_legacy_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  store volatile float %mul, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_multi_use_mul_legacy_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_mul_legacy_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_xor_b32_e32 [[NEG_MUL_LEGACY:v[0-9]+]], 0x80000000, [[ADD]]
+; GCN: v_mul_legacy_f32_e32 [[MUL:v[0-9]+]], 4.0, [[ADD]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL_LEGACY]]
+; GCN: buffer_store_dword [[MUL]]
+define void @v_fneg_mul_legacy_multi_use_mul_legacy_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  %use1 = call float @llvm.amdgcn.fmul.legacy(float %mul, float 4.0)
+  store volatile float %fneg, float addrspace(1)* %out
+  store volatile float %use1, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_fneg_x_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_legacy_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_legacy_fneg_x_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %fneg.a = fsub float -0.000000e+00, %a
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %fneg.a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_x_fneg_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_legacy_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_legacy_x_fneg_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %fneg.b = fsub float -0.000000e+00, %b
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %a, float %fneg.b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_fneg_fneg_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_legacy_f32_e64 [[ADD:v[0-9]+]], [[A]], -[[B]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_legacy_fneg_fneg_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %fneg.a = fsub float -0.000000e+00, %a
+  %fneg.b = fsub float -0.000000e+00, %b
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %fneg.a, float %fneg.b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_store_use_fneg_x_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_xor_b32_e32 [[NEG_A:v[0-9]+]], 0x80000000, [[A]]
+; GCN-DAG: v_mul_legacy_f32_e32 [[NEG_MUL_LEGACY:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL_LEGACY]]
+; GCN: buffer_store_dword [[NEG_A]]
+define void @v_fneg_mul_legacy_store_use_fneg_x_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %fneg.a = fsub float -0.000000e+00, %a
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %fneg.a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  store volatile float %fneg.a, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_legacy_multi_use_fneg_x_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_mul_legacy_f32_e32 [[NEG_MUL_LEGACY:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_mul_legacy_f32_e64 [[MUL:v[0-9]+]], -[[A]], s{{[0-9]+}}
+; GCN-NEXT: buffer_store_dword [[NEG_MUL_LEGACY]]
+; GCN: buffer_store_dword [[MUL]]
+define void @v_fneg_mul_legacy_multi_use_fneg_x_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr, float addrspace(1)* %b.ptr, float %c) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %b.gep = getelementptr inbounds float, float addrspace(1)* %b.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %b = load volatile float, float addrspace(1)* %b.gep
+  %fneg.a = fsub float -0.000000e+00, %a
+  %mul = call float @llvm.amdgcn.fmul.legacy(float %fneg.a, float %b)
+  %fneg = fsub float -0.000000e+00, %mul
+  %use1 = call float @llvm.amdgcn.fmul.legacy(float %fneg.a, float %c)
+  store volatile float %fneg, float addrspace(1)* %out
+  store volatile float %use1, float addrspace(1)* %out
+  ret void
+}
+
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 declare float @llvm.fma.f32(float, float, float) #1
 declare float @llvm.fmuladd.f32(float, float, float) #1
 declare float @llvm.amdgcn.rcp.f32(float) #1
 declare float @llvm.amdgcn.rcp.legacy(float) #1
+declare float @llvm.amdgcn.fmul.legacy(float, float) #1
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }