Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -26135,24 +26135,39 @@
 static SDValue PerformFNEGCombine(SDNode *N, SelectionDAG &DAG,
                                   const X86Subtarget *Subtarget) {
   EVT VT = N->getValueType(0);
+  EVT SVT = VT.getScalarType();
   SDValue Arg = N->getOperand(0);
+  SDLoc DL(N);
+
+  // Let legalize expand this if it isn't a legal type yet.
+  if (!DAG.getTargetLoweringInfo().isTypeLegal(VT))
+    return SDValue();
+
+  // If we're negating a FMUL node on a target with FMA, then we can avoid the
+  // use of a constant by performing (0 - A*B) instead.
+  if (Arg.getOpcode() == ISD::FMUL && (SVT == MVT::f32 || SVT == MVT::f64) &&
+      (Subtarget->hasFMA() || Subtarget->hasFMA4() || Subtarget->hasAVX512())) {
+    SDValue Zero = DAG.getConstantFP(0.0, DL, VT);
+    return DAG.getNode(X86ISD::FNMADD, DL, VT, Arg.getOperand(0),
+                       Arg.getOperand(1), Zero);
+  }
 
   // If we're negating a FMA node, then we can adjust the
   // instruction to include the extra negation.
   if (Arg.hasOneUse()) {
     switch (Arg.getOpcode()) {
-      case X86ISD::FMADD:
-        return DAG.getNode(X86ISD::FNMSUB, SDLoc(N), VT, Arg.getOperand(0),
-                           Arg.getOperand(1), Arg.getOperand(2));
-      case X86ISD::FMSUB:
-        return DAG.getNode(X86ISD::FNMADD, SDLoc(N), VT, Arg.getOperand(0),
-                           Arg.getOperand(1), Arg.getOperand(2));
-      case X86ISD::FNMADD:
-        return DAG.getNode(X86ISD::FMSUB, SDLoc(N), VT, Arg.getOperand(0),
-                           Arg.getOperand(1), Arg.getOperand(2));
-      case X86ISD::FNMSUB:
-        return DAG.getNode(X86ISD::FMADD, SDLoc(N), VT, Arg.getOperand(0),
-                           Arg.getOperand(1), Arg.getOperand(2));
+    case X86ISD::FMADD:
+      return DAG.getNode(X86ISD::FNMSUB, DL, VT, Arg.getOperand(0),
+                         Arg.getOperand(1), Arg.getOperand(2));
+    case X86ISD::FMSUB:
+      return DAG.getNode(X86ISD::FNMADD, DL, VT, Arg.getOperand(0),
+                         Arg.getOperand(1), Arg.getOperand(2));
+    case X86ISD::FNMADD:
+      return DAG.getNode(X86ISD::FMSUB, DL, VT, Arg.getOperand(0),
+                         Arg.getOperand(1), Arg.getOperand(2));
+    case X86ISD::FNMSUB:
+      return DAG.getNode(X86ISD::FMADD, DL, VT, Arg.getOperand(0),
+                         Arg.getOperand(1), Arg.getOperand(2));
     }
   }
   return SDValue();
Index: test/CodeGen/X86/fma_patterns.ll
===================================================================
--- test/CodeGen/X86/fma_patterns.ll
+++ test/CodeGen/X86/fma_patterns.ll
@@ -1109,4 +1109,76 @@
   ret <4 x float> %a
 }
 
+; Pattern: (fneg (fmul x, y)) -> (fnmadd x, y, 0)
+
+define double @test_f64_fneg_fmul(double %x, double %y) #0 {
+; FMA-LABEL: test_f64_fneg_fmul:
+; FMA:       # BB#0:
+; FMA-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; FMA-NEXT:    vfnmadd213sd %xmm2, %xmm1, %xmm0
+; FMA-NEXT:    retq
+;
+; FMA4-LABEL: test_f64_fneg_fmul:
+; FMA4:       # BB#0:
+; FMA4-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; FMA4-NEXT:    vfnmaddsd %xmm2, %xmm1, %xmm0, %xmm0
+; FMA4-NEXT:    retq
+;
+; AVX512-LABEL: test_f64_fneg_fmul:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; AVX512-NEXT:    vfnmadd213sd %xmm2, %xmm0, %xmm1
+; AVX512-NEXT:    vmovaps %zmm1, %zmm0
+; AVX512-NEXT:    retq
+  %m = fmul double %x, %y
+  %n = fsub double -0.0, %m
+  ret double %n
+}
+
+define <4 x float> @test_v4f32_fneg_fmul(<4 x float> %x, <4 x float> %y) #0 {
+; FMA-LABEL: test_v4f32_fneg_fmul:
+; FMA:       # BB#0:
+; FMA-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; FMA-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; FMA-NEXT:    retq
+;
+; FMA4-LABEL: test_v4f32_fneg_fmul:
+; FMA4:       # BB#0:
+; FMA4-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; FMA4-NEXT:    vfnmaddps %xmm2, %xmm1, %xmm0, %xmm0
+; FMA4-NEXT:    retq
+;
+; AVX512-LABEL: test_v4f32_fneg_fmul:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vxorps %xmm2, %xmm2, %xmm2
+; AVX512-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; AVX512-NEXT:    retq
+  %m = fmul <4 x float> %x, %y
+  %n = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %m
+  ret <4 x float> %n
+}
+
+define <4 x double> @test_v4f64_fneg_fmul(<4 x double> %x, <4 x double> %y) #0 {
+; FMA-LABEL: test_v4f64_fneg_fmul:
+; FMA:       # BB#0:
+; FMA-NEXT:    vxorpd %ymm2, %ymm2, %ymm2
+; FMA-NEXT:    vfnmadd213pd %ymm2, %ymm1, %ymm0
+; FMA-NEXT:    retq
+;
+; FMA4-LABEL: test_v4f64_fneg_fmul:
+; FMA4:       # BB#0:
+; FMA4-NEXT:    vxorpd %ymm2, %ymm2, %ymm2
+; FMA4-NEXT:    vfnmaddpd %ymm2, %ymm1, %ymm0, %ymm0
+; FMA4-NEXT:    retq
+;
+; AVX512-LABEL: test_v4f64_fneg_fmul:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vxorps %ymm2, %ymm2, %ymm2
+; AVX512-NEXT:    vfnmadd213pd %ymm2, %ymm1, %ymm0
+; AVX512-NEXT:    retq
+  %m = fmul <4 x double> %x, %y
+  %n = fsub <4 x double> <double -0.0, double -0.0, double -0.0, double -0.0>, %m
+  ret <4 x double> %n
+}
+
 attributes #0 = { "unsafe-fp-math"="true" }
Index: test/CodeGen/X86/fma_patterns_wide.ll
===================================================================
--- test/CodeGen/X86/fma_patterns_wide.ll
+++ test/CodeGen/X86/fma_patterns_wide.ll
@@ -737,4 +737,56 @@
   ret <16 x float> %a
 }
 
+; Pattern: (fneg (fmul x, y)) -> (fnmadd x, y, 0)
+
+define <16 x float> @test_v16f32_fneg_fmul(<16 x float> %x, <16 x float> %y) #0 {
+; FMA-LABEL: test_v16f32_fneg_fmul:
+; FMA:       # BB#0:
+; FMA-NEXT:    vxorps %ymm4, %ymm4, %ymm4
+; FMA-NEXT:    vfnmadd213ps %ymm4, %ymm2, %ymm0
+; FMA-NEXT:    vfnmadd213ps %ymm4, %ymm3, %ymm1
+; FMA-NEXT:    retq
+;
+; FMA4-LABEL: test_v16f32_fneg_fmul:
+; FMA4:       # BB#0:
+; FMA4-NEXT:    vxorps %ymm4, %ymm4, %ymm4
+; FMA4-NEXT:    vfnmaddps %ymm4, %ymm2, %ymm0, %ymm0
+; FMA4-NEXT:    vfnmaddps %ymm4, %ymm3, %ymm1, %ymm1
+; FMA4-NEXT:    retq
+;
+; AVX512-LABEL: test_v16f32_fneg_fmul:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vpxord %zmm2, %zmm2, %zmm2
+; AVX512-NEXT:    vfnmadd213ps %zmm2, %zmm1, %zmm0
+; AVX512-NEXT:    retq
+  %m = fmul <16 x float> %x, %y
+  %n = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %m
+  ret <16 x float> %n
+}
+
+define <8 x double> @test_v8f64_fneg_fmul(<8 x double> %x, <8 x double> %y) #0 {
+; FMA-LABEL: test_v8f64_fneg_fmul:
+; FMA:       # BB#0:
+; FMA-NEXT:    vxorpd %ymm4, %ymm4, %ymm4
+; FMA-NEXT:    vfnmadd213pd %ymm4, %ymm2, %ymm0
+; FMA-NEXT:    vfnmadd213pd %ymm4, %ymm3, %ymm1
+; FMA-NEXT:    retq
+;
+; FMA4-LABEL: test_v8f64_fneg_fmul:
+; FMA4:       # BB#0:
+; FMA4-NEXT:    vxorpd %ymm4, %ymm4, %ymm4
+; FMA4-NEXT:    vfnmaddpd %ymm4, %ymm2, %ymm0, %ymm0
+; FMA4-NEXT:    vfnmaddpd %ymm4, %ymm3, %ymm1, %ymm1
+; FMA4-NEXT:    retq
+;
+; AVX512-LABEL: test_v8f64_fneg_fmul:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vpxord %zmm2, %zmm2, %zmm2
+; AVX512-NEXT:    vfnmadd213pd %zmm2, %zmm1, %zmm0
+; AVX512-NEXT:    retq
+  %m = fmul <8 x double> %x, %y
+  %n = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %m
+  ret <8 x double> %n
+}
+
 attributes #0 = { "unsafe-fp-math"="true" }