// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: BSD-3-Clause

// Differential kernel for the arm64 NEON slice: the logical and arithmetic
// three-register operations, permutations, comparisons, shifts, the crypto
// four-register group, element moves, table lookups and the structure
// loads and stores.  Every function is byte-compared against go tool asm.

#include "textflag.h"

// func simdLogic()
TEXT ·simdLogic(SB), NOSPLIT, $0-0
	VADD  V1.B16, V2.B16, V3.B16
	VADD  V1.B8, V2.B8, V3.B8
	VSUB  V1.S4, V2.S4, V3.S4
	VMUL  V1.H8, V2.H8, V3.H8
	VAND  V4.B16, V4.B16, V9.B16
	VORR  V5.B16, V4.B16, V3.B16
	VEOR  V0.B16, V1.B16, V0.B16
	VADDP V1.H8, V2.H8, V3.H8
	VCMEQ V24.S4, V13.S4, V12.S4
	VCMEQ $0, V2.H4, V3.H4
	RET

// func simdPerm()
TEXT ·simdPerm(SB), NOSPLIT, $0-0
	VZIP1   V16.H8, V3.H8, V19.H8
	VZIP1   V6.D2, V9.D2, V11.D2
	VZIP2   V22.D2, V25.D2, V21.D2
	VREV32  V2.H8, V1.H8
	VREV64  V2.S4, V3.S4
	VUADDLV V31.S4, V11
	VEXT    $4, V2.B8, V1.B8, V3.B8
	VEXT    $8, V2.B16, V1.B16, V3.B16
	RET

// func simdShift()
TEXT ·simdShift(SB), NOSPLIT, $0-0
	VSHL  $7, V22.D2, V25.D2
	VSHL  $24, V1.S4, V2.S4
	VUSHR $6, V22.H8, V23.H8
	VUSHR $56, V1.D2, V2.D2
	VSRI  $24, V1.S4, V2.S4
	VSRI  $56, V1.D2, V2.D2
	RET

// func simdCrypto4()
TEXT ·simdCrypto4(SB), NOSPLIT, $0-0
	VEOR3   V2.B16, V7.B16, V12.B16, V25.B16
	VBCAX   V1.B16, V2.B16, V26.B16, V31.B16
	VXAR    $63, V27.D2, V21.D2, V26.D2
	VRAX1   V26.D2, V29.D2, V30.D2
	VPMULL  V2.D1, V1.D1, V3.Q1
	VPMULL  V2.B8, V1.B8, V3.H8
	VPMULL2 V2.D2, V1.D2, V4.Q1
	VPMULL2 V2.B16, V1.B16, V4.H8
	RET

// func simdElement()
TEXT ·simdElement(SB), NOSPLIT, $0-0
	VDUP V31.B[15], V18
	VDUP V19.S[3], V18.S4
	VDUP V1.D[1], V2.D2
	VMOV V13.S[0], R20
	VMOV V11.B[11], V16.B[12]
	VMOV R20, V21.B[2]
	VMOV V2.B16, V4.B16
	RET

// func simdTable()
TEXT ·simdTable(SB), NOSPLIT, $0-0
	VTBL V22.B16, [V28.B16], V11.B16
	VTBL V18.B8, [V17.B16, V18.B16], V22.B8
	VTBL V31.B8, [V14.B16, V15.B16, V16.B16, V17.B16], V15.B8
	RET

// func simdLoadStore()
TEXT ·simdLoadStore(SB), NOSPLIT, $0-0
	VLD1   (R2), [V21.B16]
	VLD1   (R24), [V18.D1, V19.D1, V20.D1]
	VLD1   (R29), [V14.D1, V15.D1, V16.D1, V17.D1]
	VLD1.P 32(R1), [V2.B16, V3.B16]
	VLD1.P 64(R4), [V5.B16, V6.B16, V7.B16, V8.B16]
	VLD1R  (R1), [V9.B8]
	VLD1R  (R0), [V0.B16]
	VLD4R  (R0), [V0.B8, V1.B8, V2.B8, V3.B8]
	VST1   [V2.S4, V3.S4, V4.S4, V5.S4], (R14)
	VST1   [V14.H4, V15.H4, V16.H4], (R27)
	VST1.P [V2.B16], (R1)
	VST1.P [V2.B16, V3.B16], 32(R1)
	RET

// func simdLiteral()
TEXT ·simdLiteral(SB), NOSPLIT, $0-0
	VMOVS $0x80402010, V11
	VMOVD $0x8040201008040201, V20
	VMOVQ $0x7040201008040201, $0x8040201008040201, V10
	RET