Tidy up. Remove trailing spaces and fix the worst of the 80 column violations.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157799 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 90 insertions, 74 deletions

diff --git a/lib/Target/X86/X86InstrFMA.td b/lib/Target/X86/X86InstrFMA.td
index 2736669..1b7f094 100644
--- a/lib/Target/X86/X86InstrFMA.td
+++ b/lib/Target/X86/X86InstrFMA.td
@@ -38,76 +38,79 @@ multiclass fma3p_rm<bits<8> opc, string OpcodeStr> {
 }
 
 // Intrinsic for 132 pattern
-multiclass fma3p_rm_int<bits<8> opc, string OpcodeStr, 
+multiclass fma3p_rm_int<bits<8> opc, string OpcodeStr,
                         PatFrag MemFrag128, PatFrag MemFrag256,
                         Intrinsic Int128, Intrinsic Int256> {
   def r_Int : FMA3<opc, MRMSrcReg, (outs VR128:$dst),
            (ins VR128:$src1, VR128:$src2, VR128:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
            [(set VR128:$dst, (Int128 VR128:$src1, VR128:$src3, VR128:$src2))]>;
-  //let mayLoad = 1 in
   def m_Int : FMA3<opc, MRMSrcMem, (outs VR128:$dst),
            (ins VR128:$src1, VR128:$src2, f128mem:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
-           [(set VR128:$dst, (Int128 VR128:$src1, (MemFrag128 addr:$src3), VR128:$src2))]>;
+           [(set VR128:$dst,
+             (Int128 VR128:$src1, (MemFrag128 addr:$src3), VR128:$src2))]>;
   def rY_Int : FMA3<opc, MRMSrcReg, (outs VR256:$dst),
            (ins VR256:$src1, VR256:$src2, VR256:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
            [(set VR256:$dst, (Int256 VR256:$src1, VR256:$src3, VR256:$src2))]>;
-  //let mayLoad = 1 in
   def mY_Int : FMA3<opc, MRMSrcMem, (outs VR256:$dst),
            (ins VR256:$src1, VR256:$src2, f256mem:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
-           [(set VR256:$dst, (Int256 VR256:$src1, (MemFrag256 addr:$src3), VR256:$src2))]>;
+           [(set VR256:$dst,
+             (Int256 VR256:$src1, (MemFrag256 addr:$src3), VR256:$src2))]>;
 }
 }
 
 multiclass fma3p_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
-                       string OpcodeStr, string PackTy, 
+                       string OpcodeStr, string PackTy,
                        PatFrag MemFrag128, PatFrag MemFrag256,
                        Intrinsic Int128, Intrinsic Int256> {
-  defm r132 : fma3p_rm_int <opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy)),
-                              MemFrag128, MemFrag256, Int128, Int256>;
-  defm r132 : fma3p_rm     <opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy))>;
-  defm r213 : fma3p_rm     <opc213, !strconcat(OpcodeStr, !strconcat("213", PackTy))>;
-  defm r231 : fma3p_rm     <opc231, !strconcat(OpcodeStr, !strconcat("231", PackTy))>;
+  defm r132 : fma3p_rm_int <opc132, !strconcat(OpcodeStr,
+                            !strconcat("132", PackTy)), MemFrag128, MemFrag256,
+                            Int128, Int256>;
+  defm r132 : fma3p_rm <opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy))>;
+  defm r213 : fma3p_rm <opc213, !strconcat(OpcodeStr, !strconcat("213", PackTy))>;
+  defm r231 : fma3p_rm <opc231, !strconcat(OpcodeStr, !strconcat("231", PackTy))>;
 }
 
 // Fused Multiply-Add
 let ExeDomain = SSEPackedSingle in {
-  defm VFMADDPS    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps", memopv4f32, memopv8f32,
-    int_x86_fma4_vfmadd_ps, int_x86_fma4_vfmadd_ps_256>;
-  defm VFMSUBPS    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps",  memopv4f32, memopv8f32,
-    int_x86_fma4_vfmsub_ps, int_x86_fma4_vfmsub_ps_256>;
-  defm VFMADDSUBPS : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps", memopv4f32, memopv8f32,
-    int_x86_fma4_vfmaddsub_ps, int_x86_fma4_vfmaddsub_ps_256>;
-  defm VFMSUBADDPS : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps", memopv4f32, memopv8f32,
-    int_x86_fma4_vfmsubadd_ps, int_x86_fma4_vfmaddsub_ps_256>;
+  defm VFMADDPS    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps", memopv4f32,
+    memopv8f32, int_x86_fma4_vfmadd_ps, int_x86_fma4_vfmadd_ps_256>;
+  defm VFMSUBPS    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps",  memopv4f32,
+    memopv8f32, int_x86_fma4_vfmsub_ps, int_x86_fma4_vfmsub_ps_256>;
+  defm VFMADDSUBPS : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps",
+    memopv4f32, memopv8f32, int_x86_fma4_vfmaddsub_ps,
+    int_x86_fma4_vfmaddsub_ps_256>;
+  defm VFMSUBADDPS : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps",
+    memopv4f32, memopv8f32, int_x86_fma4_vfmsubadd_ps,
+    int_x86_fma4_vfmaddsub_ps_256>;
 }
 
 let ExeDomain = SSEPackedDouble in {
-  defm VFMADDPD    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd", memopv2f64, memopv4f64,
-    int_x86_fma4_vfmadd_pd, int_x86_fma4_vfmadd_pd_256>, VEX_W;
-  defm VFMSUBPD    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd", memopv2f64, memopv4f64,
-    int_x86_fma4_vfmsub_pd, int_x86_fma4_vfmsub_pd_256>, VEX_W;
-  defm VFMADDSUBPD : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd", memopv2f64, memopv4f64, 
-    int_x86_fma4_vfmaddsub_pd, int_x86_fma4_vfmaddsub_pd_256>, VEX_W;
-  defm VFMSUBADDPD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd", memopv2f64, memopv4f64,
-    int_x86_fma4_vfmsubadd_pd, int_x86_fma4_vfmsubadd_pd_256>, VEX_W;
+  defm VFMADDPD    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfmadd_pd, int_x86_fma4_vfmadd_pd_256>, VEX_W;
+  defm VFMSUBPD    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfmsub_pd, int_x86_fma4_vfmsub_pd_256>, VEX_W;
+  defm VFMADDSUBPD : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfmaddsub_pd, int_x86_fma4_vfmaddsub_pd_256>, VEX_W;
+  defm VFMSUBADDPD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfmsubadd_pd, int_x86_fma4_vfmsubadd_pd_256>, VEX_W;
 }
 
 // Fused Negative Multiply-Add
 let ExeDomain = SSEPackedSingle in {
-  defm VFNMADDPS : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps",  memopv4f32, memopv8f32,
-    int_x86_fma4_vfnmadd_ps, int_x86_fma4_vfnmadd_ps_256>;
-  defm VFNMSUBPS : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps",  memopv4f32, memopv8f32,
-    int_x86_fma4_vfnmsub_ps, int_x86_fma4_vfnmsub_ps_256>;
+  defm VFNMADDPS : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps",  memopv4f32,
+    memopv8f32, int_x86_fma4_vfnmadd_ps, int_x86_fma4_vfnmadd_ps_256>;
+  defm VFNMSUBPS : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps",  memopv4f32,
+    memopv8f32, int_x86_fma4_vfnmsub_ps, int_x86_fma4_vfnmsub_ps_256>;
 }
 let ExeDomain = SSEPackedDouble in {
-  defm VFNMADDPD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd", memopv2f64, memopv4f64,
-    int_x86_fma4_vfnmadd_pd, int_x86_fma4_vfnmadd_pd_256>, VEX_W;
-  defm VFNMSUBPD : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd", memopv2f64, memopv4f64,
-    int_x86_fma4_vfnmsub_pd, int_x86_fma4_vfnmsub_pd_256>, VEX_W;
+  defm VFNMADDPD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfnmadd_pd, int_x86_fma4_vfnmadd_pd_256>, VEX_W;
+  defm VFNMSUBPD : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd", memopv2f64,
+    memopv4f64, int_x86_fma4_vfnmsub_pd, int_x86_fma4_vfnmsub_pd_256>, VEX_W;
 }
 
 let Predicates = [HasFMA3], AddedComplexity = 20 in {
@@ -118,11 +121,11 @@ let Predicates = [HasFMA3], AddedComplexity = 20 in {
 // FMA231: src1 = src2*src3 + src1
 def : Pat<(v4f64 (fadd (fmul VR256:$src2, (memopv4f64 addr:$src3)), VR256:$src1)),
         (VFMADDPDr231mY VR256:$src1, VR256:$src2, addr:$src3)>;
-                        
-// FMA231: src1 = src2*src3 + src1   
+
+// FMA231: src1 = src2*src3 + src1
 def : Pat<(v4f64 (fadd (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
         (VFMADDPDr231rY VR256:$src1, VR256:$src2, VR256:$src3)>;
-                        
+
 
 //------------
 // FP double precision ADD - 128
@@ -132,7 +135,7 @@ def : Pat<(v4f64 (fadd (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
 // FMA231: src1 = src2*src3 + src1
 def : Pat<(v2f64 (fadd (fmul VR128:$src2, (memopv2f64 addr:$src3)), VR128:$src1)),
             (VFMADDPDr231m VR128:$src1, VR128:$src2, addr:$src3)>;
-                        
+
 // FMA231: src1 = src2*src3 + src1
 def : Pat<(v2f64 (fadd (fmul VR128:$src2, VR128:$src3), VR128:$src1)),
             (VFMADDPDr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
@@ -143,11 +146,11 @@ def : Pat<(v2f64 (fadd (fmul VR128:$src2, VR128:$src3), VR128:$src1)),
 // FMA231: src1 = src2*src3 - src1
 def : Pat<(v4f64 (fsub (fmul VR256:$src2, (memopv4f64 addr:$src3)), VR256:$src1)),
            (VFMSUBPDr231mY VR256:$src1, VR256:$src2, addr:$src3)>;
-                        
+
 // FMA231: src1 = src2*src3 - src1
 def : Pat<(v4f64 (fsub (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
             (VFMSUBPDr231rY VR256:$src1, VR256:$src2, VR256:$src3)>;
-                        
+
 
 //------------
 // FP double precision SUB - 128
@@ -156,22 +159,22 @@ def : Pat<(v4f64 (fsub (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
 // FMA231: src1 = src2*src3 - src1
 def : Pat<(v2f64 (fsub (fmul VR128:$src2, (memopv2f64 addr:$src3)), VR128:$src1)),
             (VFMSUBPDr231m VR128:$src1, VR128:$src2, addr:$src3)>;
-                        
+
 // FMA231: src1 = src2*src3 - src1
 def : Pat<(v2f64 (fsub (fmul VR128:$src2, VR128:$src3), VR128:$src1)),
             (VFMSUBPDr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
-                        
+
 //------------
 // FP double precision FNMADD - 256
 //------------
 // FMA231: src1 = - src2*src3 + src1
 def : Pat<(v4f64 (fsub VR256:$src1, (fmul VR256:$src2, (memopv4f64 addr:$src3)))),
             (VFNMADDPDr231mY VR256:$src1, VR256:$src2, addr:$src3)>;
-                        
+
 // FMA231: src1 = - src2*src3 + src1
 def : Pat<(v4f64 (fsub VR256:$src1, (fmul VR256:$src2, VR256:$src3))),
             (VFNMADDPDr231rY VR256:$src1, VR256:$src2, VR256:$src3)>;
-                        
+
 //------------
 // FP double precision FNMADD - 128
 //------------
@@ -179,11 +182,11 @@ def : Pat<(v4f64 (fsub VR256:$src1, (fmul VR256:$src2, VR256:$src3))),
 // FMA231: src1 = - src2*src3 + src1
 def : Pat<(v2f64 (fsub VR128:$src1, (fmul VR128:$src2, (memopv2f64 addr:$src3)))),
             (VFNMADDPDr231m VR128:$src1, VR128:$src2, addr:$src3)>;
-                        
+
 // FMA231: src1 = - src2*src3 + src1
 def : Pat<(v2f64 (fsub VR128:$src1, (fmul VR128:$src2, VR128:$src3))),
             (VFNMADDPDr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
-                        
+
 //------------
 // FP single precision ADD - 256
 //------------
@@ -192,7 +195,7 @@ def : Pat<(v2f64 (fsub VR128:$src1, (fmul VR128:$src2, VR128:$src3))),
 def : Pat<(v8f32 (fadd (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
             (VFMADDPSr231rY VR256:$src1, VR256:$src2, VR256:$src3)>;
 
-// FMA213 : src1 = src2*src1 + src3            
+// FMA213 : src1 = src2*src1 + src3
 def : Pat<(v8f32 (fadd (fmul VR256:$src1, VR256:$src2), (memopv8f32 addr:$src3))),
             (VFMADDPSr213mY VR256:$src1, VR256:$src2, addr:$src3)>;
 
@@ -208,14 +211,14 @@ def : Pat<(v8f32 (fadd (fmul VR256:$src2, VR256:$src1), VR256:$src3)),
 // FP single precision ADD - 128
 //------------
 
-// FMA231 : src1 = src2*src3 + src1            
+// FMA231 : src1 = src2*src3 + src1
 def : Pat<(v4f32 (fadd (fmul VR128:$src2, (memopv4f32 addr:$src3)), VR128:$src1)),
             (VFMADDPSr231m VR128:$src1, VR128:$src2, addr:$src3)>;
 
-// FMA231 : src1 = src2*src3 + src1            
+// FMA231 : src1 = src2*src3 + src1
 def : Pat<(v4f32 (fadd (fmul VR128:$src2, VR128:$src3), VR128:$src1)),
         (VFMADDPSr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
-            
+
 //------------
 // FP single precision SUB - 256
 //------------
@@ -230,11 +233,11 @@ def : Pat<(v8f32 (fsub (fmul VR256:$src2, VR256:$src3), VR256:$src1)),
 //------------
 // FP single precision SUB - 128
 //------------
-// FMA231 : src1 = src2*src3 - src1            
+// FMA231 : src1 = src2*src3 - src1
 def : Pat<(v4f32 (fsub (fmul VR128:$src2, (memopv4f32 addr:$src3)), VR128:$src1)),
             (VFMSUBPSr231m VR128:$src1, VR128:$src2, addr:$src3)>;
 
-// FMA231 : src1 = src2*src3 - src1            
+// FMA231 : src1 = src2*src3 - src1
 def : Pat<(v4f32 (fsub (fmul VR128:$src2, VR128:$src3), VR128:$src1)),
             (VFMSUBPSr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
 
@@ -253,11 +256,11 @@ def : Pat<(v8f32 (fsub VR256:$src1, (fmul VR256:$src2, VR256:$src3))),
 // FP single precision FNMADD - 128
 //------------
 
-// FMA231 : src1 = src2*src3 - src1            
+// FMA231 : src1 = src2*src3 - src1
 def : Pat<(v4f32 (fsub VR128:$src1, (fmul VR128:$src2, (memopv4f32 addr:$src3)))),
             (VFNMADDPSr231m VR128:$src1, VR128:$src2, addr:$src3)>;
 
-// FMA231 : src1 = src2*src3 - src1            
+// FMA231 : src1 = src2*src3 - src1
 def : Pat<(v4f32 (fsub VR128:$src1, (fmul VR128:$src2, VR128:$src3))),
             (VFNMADDPSr231r VR128:$src1, VR128:$src2, VR128:$src3)>;
 
@@ -268,7 +271,8 @@ def : Pat<(v4f32 (fsub VR128:$src1, (fmul VR128:$src2, VR128:$src3))),
 //------------------------------
 
 let Constraints = "$src1 = $dst" in {
-multiclass fma3s_rm<bits<8> opc, string OpcodeStr, X86MemOperand x86memop, RegisterClass RC> {
+multiclass fma3s_rm<bits<8> opc, string OpcodeStr, X86MemOperand x86memop,
+                    RegisterClass RC> {
   def r : FMA3<opc, MRMSrcReg, (outs RC:$dst),
            (ins RC:$src1, RC:$src2, RC:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
@@ -279,8 +283,8 @@ multiclass fma3s_rm<bits<8> opc, string OpcodeStr, X86MemOperand x86memop, Regis
            []>;
 }
 
-multiclass fma3s_rm_int<bits<8> opc, string OpcodeStr,X86MemOperand x86memop, RegisterClass RC,
-           Intrinsic IntId> {
+multiclass fma3s_rm_int<bits<8> opc, string OpcodeStr, X86MemOperand x86memop,
+                        RegisterClass RC, Intrinsic IntId> {
   def r_Int : FMA3<opc, MRMSrcReg, (outs RC:$dst),
            (ins RC:$src1, RC:$src2, RC:$src3),
            !strconcat(OpcodeStr, "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
@@ -293,33 +297,45 @@ multiclass fma3s_rm_int<bits<8> opc, string OpcodeStr,X86MemOperand x86memop, Re
 }
 
 multiclass fma3s_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
-                       string OpcodeStr, string PackTy, X86MemOperand MemOp, 
+                       string OpcodeStr, string PackTy, X86MemOperand MemOp,
                        RegisterClass RC, Intrinsic IntId> {
-  defm r132    : fma3s_rm         <opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy)), MemOp, RC>;
-  defm r213    : fma3s_rm         <opc213, !strconcat(OpcodeStr, !strconcat("213", PackTy)), MemOp, RC>;
-  defm r231    : fma3s_rm         <opc231, !strconcat(OpcodeStr, !strconcat("231", PackTy)), MemOp, RC>;
-  defm r132_Int: fma3s_rm_int     <opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy)), MemOp, VR128, IntId>;
+  defm r132     : fma3s_rm     <opc132, !strconcat(OpcodeStr,
+                                !strconcat("132", PackTy)), MemOp, RC>;
+  defm r213     : fma3s_rm     <opc213, !strconcat(OpcodeStr,
+                                !strconcat("213", PackTy)), MemOp, RC>;
+  defm r231     : fma3s_rm     <opc231, !strconcat(OpcodeStr,
+                                !strconcat("231", PackTy)), MemOp, RC>;
+  defm r132_Int : fma3s_rm_int <opc132, !strconcat(OpcodeStr,
+                               !strconcat("132", PackTy)), MemOp, VR128, IntId>;
 }
 
-defm VFMADDSS : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd", "ss", f32mem, FR32, int_x86_fma4_vfmadd_ss>, VEX_LIG;
-defm VFMADDSD : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd", "sd", f64mem, FR64, int_x86_fma4_vfmadd_sd>, VEX_W, VEX_LIG;
-defm VFMSUBSS : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub", "ss", f32mem, FR32, int_x86_fma4_vfmsub_ss>, VEX_LIG;
-defm VFMSUBSD : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub", "sd", f64mem, FR64, int_x86_fma4_vfmsub_sd>, VEX_W, VEX_LIG;
-
-defm VFNMADDSS : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd", "ss", f32mem, FR32, int_x86_fma4_vfnmadd_ss>, VEX_LIG;
-defm VFNMADDSD : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd", "sd", f64mem, FR64, int_x86_fma4_vfnmadd_sd>, VEX_W, VEX_LIG;
-defm VFNMSUBSS : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub", "ss", f32mem, FR32, int_x86_fma4_vfnmsub_ss>, VEX_LIG;
-defm VFNMSUBSD : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub", "sd", f64mem, FR64, int_x86_fma4_vfnmsub_sd>, VEX_W, VEX_LIG;
+defm VFMADDSS : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd", "ss", f32mem, FR32,
+                            int_x86_fma4_vfmadd_ss>, VEX_LIG;
+defm VFMADDSD : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd", "sd", f64mem, FR64,
+                            int_x86_fma4_vfmadd_sd>, VEX_W, VEX_LIG;
+defm VFMSUBSS : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub", "ss", f32mem, FR32,
+                            int_x86_fma4_vfmsub_ss>, VEX_LIG;
+defm VFMSUBSD : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub", "sd", f64mem, FR64,
+                            int_x86_fma4_vfmsub_sd>, VEX_W, VEX_LIG;
+
+defm VFNMADDSS : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd", "ss", f32mem, FR32,
+                             int_x86_fma4_vfnmadd_ss>, VEX_LIG;
+defm VFNMADDSD : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd", "sd", f64mem, FR64,
+                             int_x86_fma4_vfnmadd_sd>, VEX_W, VEX_LIG;
+defm VFNMSUBSS : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub", "ss", f32mem, FR32,
+                             int_x86_fma4_vfnmsub_ss>, VEX_LIG;
+defm VFNMSUBSD : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub", "sd", f64mem, FR64,
+                             int_x86_fma4_vfnmsub_sd>, VEX_W, VEX_LIG;
 
 
 let Predicates = [HasFMA3], AddedComplexity = 20 in {
 
 //------------
-// FP  scalar ADD 
+// FP  scalar ADD
 //------------
 
 
-// FMADD231 : src1 = src2*src3 + src1            
+// FMADD231 : src1 = src2*src3 + src1
 def : Pat<(f32 (fadd (fmul FR32:$src2, FR32:$src3), FR32:$src1)),
             (VFMADDSSr231r FR32:$src1, FR32:$src2, FR32:$src3)>;