Index: lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -2787,6 +2787,23 @@
       DAG.ReplaceAllUsesWith(N0, DAG.getNode(ISD::FNEG, SL, VT, Res));
     return Res;
   }
+  case ISD::FMUL: {
+    // (fneg (fmul x, y)) -> (fmul x, (fneg y))
+    SDValue LHS = N0.getOperand(0);
+    SDValue RHS = N0.getOperand(1);
+
+    if (LHS.getOpcode() == ISD::FNEG)
+      LHS = LHS.getOperand(0);
+    else if (RHS.getOpcode() == ISD::FNEG)
+      RHS = RHS.getOperand(0);
+    else
+      RHS = DAG.getNode(ISD::FNEG, SL, VT, RHS);
+
+    SDValue Res = DAG.getNode(ISD::FMUL, SL, VT, LHS, RHS);
+    if (!N0.hasOneUse())
+      DAG.ReplaceAllUsesWith(N0, DAG.getNode(ISD::FNEG, SL, VT, Res));
+    return Res;
+  }
   default:
     return SDValue();
   }
Index: test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
===================================================================
--- test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
+++ test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
@@ -19,8 +19,8 @@
 ; VI: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, |v{{[0-9]+}}|
 ; VI: v_cndmask_b32_e32
 ; VI: v_add_f32_e64 v{{[0-9]+}}, |v{{[0-9]+}}|, |v{{[0-9]+}}|
-; VI: v_mul_f32_e32
-; VI: v_mad_f32 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}, 1.0
+; VI: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
+; VI: v_mad_f32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 1.0
 define void @multiple_fadd_use_test_f32(float addrspace(1)* %out, float %x, float %y, float %z) #0 {
   %a11 = fadd fast float %y, -1.0
   %a12 = call float @llvm.fabs.f32(float %a11)
@@ -114,8 +114,8 @@
 ; VI: v_cmp_gt_f16_e64 vcc, |v{{[0-9]+}}|, |v{{[0-9]+}}|
 ; VI: v_cndmask_b32_e32
 ; VI: v_add_f16_e64 v{{[0-9]+}}, |v{{[0-9]+}}|, |v{{[0-9]+}}|
-; VI: v_mul_f16_e32
-; VI: v_mad_f16 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}, 1.0
+; VI: v_mul_f16_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
+; VI: v_mad_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 1.0
 define void @multiple_fadd_use_test_f16(half addrspace(1)* %out, i16 zeroext %x.arg, i16 zeroext %y.arg, i16 zeroext %z.arg) #0 {
   %x = bitcast i16 %x.arg to half
   %y = bitcast i16 %y.arg to half
Index: test/CodeGen/AMDGPU/fneg-combines.ll
===================================================================
--- test/CodeGen/AMDGPU/fneg-combines.ll
+++ test/CodeGen/AMDGPU/fneg-combines.ll
@@ -173,6 +173,183 @@
   ret void
 }
 
+; --------------------------------------------------------------------------------
+; fmul tests
+; --------------------------------------------------------------------------------
+
+; GCN-LABEL: {{^}}v_fneg_mul_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_f32_e64 [[RESULT:v[0-9]+]], [[A]], -[[B]]
+; GCN-NEXT: buffer_store_dword [[RESULT]]
+define void @v_fneg_mul_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 = fmul float %a, %b
+  %fneg = fsub float -0.000000e+00, %mul
+  store float %fneg, float addrspace(1)* %out.gep
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_store_use_mul_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_mul_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_xor_b32_e32 [[NEG_MUL:v[0-9]+]], 0x80000000, [[ADD]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL]]
+; GCN: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_store_use_mul_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 = fmul float %a, %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_multi_use_mul_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN-DAG: v_mul_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_xor_b32_e32 [[NEG_MUL:v[0-9]+]], 0x80000000, [[ADD]]
+; GCN: v_mul_f32_e32 [[MUL:v[0-9]+]], 4.0, [[ADD]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL]]
+; GCN: buffer_store_dword [[MUL]]
+define void @v_fneg_mul_multi_use_mul_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 = fmul float %a, %b
+  %fneg = fsub float -0.000000e+00, %mul
+  %use1 = fmul float %mul, 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_fneg_x_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_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 = fmul float %fneg.a, %b
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_x_fneg_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_f32_e32 [[ADD:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_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 = fmul float %a, %fneg.b
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_fneg_fneg_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: {{buffer|flat}}_load_dword [[B:v[0-9]+]]
+; GCN: v_mul_f32_e64 [[ADD:v[0-9]+]], [[A]], -[[B]]
+; GCN-NEXT: buffer_store_dword [[ADD]]
+define void @v_fneg_mul_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 = fmul float %fneg.a, %fneg.b
+  %fneg = fsub float -0.000000e+00, %mul
+  store volatile float %fneg, float addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_mul_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_f32_e32 [[NEG_MUL:v[0-9]+]], [[B]], [[A]]
+; GCN-NEXT: buffer_store_dword [[NEG_MUL]]
+; GCN: buffer_store_dword [[NEG_A]]
+define void @v_fneg_mul_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 = fmul float %fneg.a, %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_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_f32_e32 [[NEG_MUL:v[0-9]+]], [[B]], [[A]]
+; GCN-DAG: v_mul_f32_e64 [[MUL:v[0-9]+]], -[[A]], s{{[0-9]+}}
+; GCN-NEXT: buffer_store_dword [[NEG_MUL]]
+; GCN: buffer_store_dword [[MUL]]
+define void @v_fneg_mul_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 = fmul float %fneg.a, %b
+  %fneg = fsub float -0.000000e+00, %mul
+  %use1 = fmul float %fneg.a, %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
 
 attributes #0 = { nounwind }
Index: test/CodeGen/AMDGPU/mad-combine.ll
===================================================================
--- test/CodeGen/AMDGPU/mad-combine.ll
+++ test/CodeGen/AMDGPU/mad-combine.ll
@@ -273,12 +273,12 @@
 ; 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_mad_f32 [[RESULT:v[0-9]+]], [[A]], -[[B]], -[[C]]
 
 ; 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_sub_f32_e64 [[RESULT:v[0-9]+]], -[[TMP]], [[C]]
+; SI-DENORM-SLOWFMAF: v_mul_f32_e64 [[TMP:v[0-9]+]], [[A]], -[[B]]
+; SI-DENORM-SLOWFMAF: v_subrev_f32_e32 [[RESULT:v[0-9]+]], [[C]], [[TMP]]
 
 ; SI: buffer_store_dword [[RESULT]]
 define void @combine_to_mad_fsub_2_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #1 {
@@ -306,15 +306,15 @@
 ; 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-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_mad_f32 [[RESULT0:v[0-9]+]], [[A]], -[[B]], -[[C]]
+; SI-STD-DAG: v_mad_f32 [[RESULT1:v[0-9]+]], [[A]], -[[B]], -[[D]]
 
 ; 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]]
 
-; SI-DENORM-SLOWFMAF: v_mul_f32_e32 [[TMP:v[0-9]+]], [[B]], [[A]]
-; SI-DENORM-SLOWFMAF-DAG: v_sub_f32_e64 [[RESULT0:v[0-9]+]], -[[TMP]], [[C]]
-; SI-DENORM-SLOWFMAF-DAG: v_sub_f32_e64 [[RESULT1:v[0-9]+]], -[[TMP]], [[D]]
+; SI-DENORM-SLOWFMAF: v_mul_f32_e64 [[TMP:v[0-9]+]], [[A]], -[[B]]
+; SI-DENORM-SLOWFMAF-DAG: v_subrev_f32_e32 [[RESULT0:v[0-9]+]], [[C]], [[TMP]]
+; SI-DENORM-SLOWFMAF-DAG: v_subrev_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{{$}}