// The AVX/AVX-512 gap families: fused scalar multiply-add, carries through
// GF(2^8) affine transforms, population counts, non-temporal stores, mask
// moves and the KMOV widths.  Every result is folded back so no instruction
// is dead.

#include "textflag.h"

// func avxblend(a, b []float64) float64
TEXT ·avxblend(SB), NOSPLIT, $0-56
	MOVQ         a_base+0(FP), SI
	MOVQ         b_base+24(FP), DI
	VMOVUPD      (SI), Y0
	VMOVUPD      (DI), Y1
	VXORPS       Y2, Y2, Y2
	VSHUFPD      $5, Y0, Y1, Y3
	VMOVUPD      Y3, (SI)
	VPBLENDD     $3, Y0, Y1, Y4
	VPERM2F128   $1, Y4, Y0, Y0
	VEXTRACTF128 $1, Y0, X1
	VZEROALL
	VMOVSD       X1, ret+48(FP)
	RET

// func avxint(p *byte, n int) uint64
TEXT ·avxint(SB), NOSPLIT, $0-24
	MOVQ           p+0(FP), SI
	VMOVDQU        (SI), Y0
	VPCMPEQB       Y0, Y0, Y1
	VPSLLDQ        $2, X0, X0
	VPSRLDQ        $4, Y0, Y0
	VPALIGNR       $3, X0, X1, X1
	VPCLMULQDQ     $0, X0, X1, X2
	VGF2P8AFFINEQB $7, X2, X0, X3
	VPOPCNTB       X3, X4
	VPOPCNTD       Y0, Y5
	VPERMI2B       X0, X1, X2
	VPTEST         X0, X0
	VPMOVMSKB      X1, AX
	VZEROUPPER
	MOVQ           AX, ret+16(FP)
	RET

// func avxnt(p *float64)
TEXT ·avxnt(SB), NOSPLIT, $0-8
	MOVQ     p+0(FP), DI
	VMOVUPD  (DI), Y0
	VADDPD   Y0, Y0, Y0
	VMOVNTDQ Y0, (DI)
	VMOVNTDQ X0, 16(DI)
	VZEROALL
	RET

// func avxmas(a, b []float64) float64
TEXT ·avxmas(SB), NOSPLIT, $0-56
	MOVQ         a_base+0(FP), SI
	MOVQ         b_base+24(FP), DI
	VMOVSD       (SI), X0
	VMOVSD       (DI), X1
	VFMADD213SD  X1, X0, X0
	VFNMADD231SD X1, X0, X0
	VADDSD       X1, X0, X0
	VMOVSD       X0, ret+48(FP)
	RET

// func avxgpr(x, y uint64) uint64
TEXT ·avxgpr(SB), NOSPLIT, $0-24
	MOVQ  x+0(FP), AX
	MOVQ  y+8(FP), BX
	ANDNL BX, AX, CX
	MULXQ BX, DX, SI
	RORXL $3, AX, CX
	RORXQ $7, BX, SI
	MOVQ  CX, ret+16(FP)
	RET

// func avxmask(kin uint8, p *byte) uint8
TEXT ·avxmask(SB), NOSPLIT, $0-17
	MOVQ  p+8(FP), SI
	KMOVB kin+0(FP), K1
	KMOVB K1, K2
	KMOVW K2, K1
	KMOVD K1, K3
	KMOVQ K3, K4
	KMOVB K4, K1
	KMOVB K1, AX
	KMOVD K1, (SI)
	MOVB  AL, ret+8(FP)
	RET

// func avx512(p *uint64, n int) uint64
TEXT ·avx512(SB), NOSPLIT, $0-24
	MOVQ       p+0(FP), SI
	VMOVDQU64  (SI), Z0
	VPORQ      Z0, Z0, Z1
	VPOPCNTQ   Z1, Z2
	VPERMB     Z1, Z0, Z2
	VPXORD     Z2, Z1, Z0
	VMOVDQA64  Z0, (SI)
	VZEROUPPER
	XORQ       AX, AX
	MOVQ       AX, ret+16(FP)
	RET