VCMPNEW V1, V2, V3              // 10611087
	VCMPNEWCC V1, V2, V3            // 10611487
	VPERM V1, V2, V3, V4            // 108110eb
	VPERMR V1, V2, V3, V4           // 108110fb
	VPERMXOR V1, V2, V3, V4         // 108110ed
	VBPERMQ V1, V2, V3              // 1061154c
	VBPERMD V1, V2, V3              // 106115cc
	VSEL V1, V2, V3, V4             // 108110ea
	VSPLTB $1, V1, V2               // 10410a0c

	SHA256MSG2 X2, X11       // 440f38cdda
	SHA256MSG2 X11, X11      // 450f38cddb
	// Test VPERMQ with both uint8 and int8 immediate args
	VPERMQ $-40, Y8, Y8 // c443fd00c0d8
	VPERMQ $216, Y8, Y8 // c443fd00c0d8
	// Test that VPERMPD that shares ytab list with VPERMQ continues to work too.
	VPERMPD $-40, Y7, Y7 // c4e3fd01ffd8
	VPERMPD $216, Y7, Y7 // c4e3fd01ffd8
	// Check that LEAL is permitted to use overflowing offset.

	LXVD2X (CPOOL+R0), PH
	LXVD2X (CPOOL+R16), PL

	// VPERM byte selections
	LXVD2X (CPOOL+R18), SEL2
	LXVD2X (CPOOL+R19), SEL1

	LXVD2X (R16)(x_ptr), T1
	LXVD2X (R0)(x_ptr), T0

	// Put in true little endian order
	XXPERMDI T0, T0, $2, T0
	XXPERMDI T1, T1, $2, T1

	// First round
	VPERM   T1, T0, SEL1, RED2    // d1 d0 d1 d0
	VPERM   ZER, RED2, SEL2, RED1 // 0  d1 d0  0

	// Third round
	VPERM T1, T0, SEL1, RED2    // d1 d0 d1 d0
	VPERM ZER, RED2, SEL2, RED1 // 0  d1 d0  0
	VSQ   RED1, RED2, RED2      // Guaranteed not to underflow

	VSLDB $8, T1, T0, T0
	VSLDB $8, T2, T1, T1

	VACCQ  T0, RED1, CAR1
	VAQ    T0, RED1, T0
	VACCCQ T1, RED2, CAR1, CAR2
	VACQ   T1, RED2, CAR1, T1
	VAQ    T2, CAR2, T2

	// Last round
	VPERM T1, T0, SEL1, RED2    // d1 d0 d1 d0