+ void insertps(XMMRegister dst, XMMRegister src, byte imm8);
+ void pinsrd(XMMRegister dst, Register src, byte imm8);
+
+ void minps(XMMRegister dst, XMMRegister src);
+ void minps(XMMRegister dst, const Operand& src);
+ void maxps(XMMRegister dst, XMMRegister src);
+ void maxps(XMMRegister dst, const Operand& src);
+ void minpd(XMMRegister dst, XMMRegister src);
+ void minpd(XMMRegister dst, const Operand& src);
+ void maxpd(XMMRegister dst, XMMRegister src);
+ void maxpd(XMMRegister dst, const Operand& src);
+ void rcpps(XMMRegister dst, XMMRegister src);
+ void rcpps(XMMRegister dst, const Operand& src);
+ void rsqrtps(XMMRegister dst, XMMRegister src);
+ void rsqrtps(XMMRegister dst, const Operand& src);
+ void sqrtps(XMMRegister dst, XMMRegister src);
+ void sqrtps(XMMRegister dst, const Operand& src);
+ void sqrtpd(XMMRegister dst, XMMRegister src);
+ void sqrtpd(XMMRegister dst, const Operand& src);
+ void paddd(XMMRegister dst, XMMRegister src);
+ void paddd(XMMRegister dst, const Operand& src);
+ void psubd(XMMRegister dst, XMMRegister src);
+ void psubd(XMMRegister dst, const Operand& src);
+ void pmulld(XMMRegister dst, XMMRegister src);
+ void pmulld(XMMRegister dst, const Operand& src);
+ void pmuludq(XMMRegister dst, XMMRegister src);
+ void pmuludq(XMMRegister dst, const Operand& src);
+ void punpackldq(XMMRegister dst, XMMRegister src);
+ void punpackldq(XMMRegister dst, const Operand& src);
+ void psrldq(XMMRegister dst, uint8_t shift);
+ void pshufd(XMMRegister dst, XMMRegister src, uint8_t shuffle);
+ void cvtps2dq(XMMRegister dst, XMMRegister src);
+ void cvtps2dq(XMMRegister dst, const Operand& src);
+ void cvtdq2ps(XMMRegister dst, XMMRegister src);
+ void cvtdq2ps(XMMRegister dst, const Operand& src);