-defm VFNMADDPS : fma_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps">;
-defm VFNMADDPD : fma_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd">, VEX_W;
-defm VFNMSUBPS : fma_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps">;
-defm VFNMSUBPD : fma_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd">, VEX_W;
+let ExeDomain = SSEPackedSingle in {
+ defm VFNMADDPS : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps">;
+ defm VFNMSUBPS : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps">;
+}
+let ExeDomain = SSEPackedDouble in {
+ defm VFNMADDPD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd">, VEX_W;
+ defm VFNMSUBPD : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd">, VEX_W;
+}
+
+multiclass fma3s_rm<bits<8> opc, string OpcodeStr, X86MemOperand x86memop> {
+ def r : FMA3<opc, MRMSrcReg, (outs VR128:$dst),
+ (ins VR128:$src1, VR128:$src2),
+ !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+ []>;
+ def m : FMA3<opc, MRMSrcMem, (outs VR128:$dst),
+ (ins VR128:$src1, x86memop:$src2),
+ !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+ []>;
+}
+
+multiclass fma3s_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
+ string OpcodeStr> {
+ defm SSr132 : fma3s_rm<opc132, !strconcat(OpcodeStr, "132ss"), f32mem>;
+ defm SSr213 : fma3s_rm<opc213, !strconcat(OpcodeStr, "213ss"), f32mem>;
+ defm SSr231 : fma3s_rm<opc231, !strconcat(OpcodeStr, "231ss"), f32mem>;
+ defm SDr132 : fma3s_rm<opc132, !strconcat(OpcodeStr, "132sd"), f64mem>, VEX_W;
+ defm SDr213 : fma3s_rm<opc213, !strconcat(OpcodeStr, "213sd"), f64mem>, VEX_W;
+ defm SDr231 : fma3s_rm<opc231, !strconcat(OpcodeStr, "231sd"), f64mem>, VEX_W;
+}
+
+defm VFMADD : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd">;
+defm VFMSUB : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub">;
+
+defm VFNMADD : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd">;
+defm VFNMSUB : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub">;