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

// Differential kernel for the riscv64 RVV slice: the instructions GOROOT's
// vector kernels use (crypto/internal/fips140/subtle/xor_riscv64.s,
// internal/bytealg and internal/chacha8rand), spelled as they spell them.

#include "textflag.h"

TEXT ·config(SB), NOSPLIT, $0-0
	VSETVLI  X5, E8, M8, TA, MA, X6
	VSETVLI  X11, E8, M8, TA, MA, X5
	VSETVLI  X12, E8, M8, TA, MA, X5
	VSETVLI  X13, E8, M8, TU, MU, X15
	VSETIVLI $4, E32, M1, TA, MA, X0
	VSETIVLI $15, E32, M1, TA, MA, X12
	VSETVLI  $15, E32, M1, TA, MA, X12
	VSETVLI  X10, E16, M1, TU, MU, X12
	VSETVLI  X10, E32, M2, TA, MA, X12
	VSETVLI  X10, E64, M8, TU, MU, X12
	VSETIVLI $31, E32, M1, TA, MA, X12
	RET

TEXT ·loadsStores(SB), NOSPLIT, $0-0
	VLE8V  (X10), V8
	VLE8V  (X11), V16
	VLE8V  (X12), V16
	VIDV   V12
	VMV4RV V8, V24
	VSE8V  V24, (X10)
	VSE32V V0, (X11)
	VSE32V V8, (X11)
	VSE32V V15, (X11)
	RET

TEXT ·segmented(SB), NOSPLIT, $0-0
	VLSSEG4E32V (X14), X0, V0
	VLSSEG8E32V (X10), X0, V4
	RET

TEXT ·crypto(SB), NOSPLIT, $0-0
	VADDVV  V20, V4, V4
	VADDVV  V27, V11, V11
	VADDVX  X12, V12, V12
	VXORVV  V8, V16, V24
	VXORVV  V13, V13, V13
	VMSEQVX X12, V8, V0
	VMSNEVV V8, V16, V0
	VFIRSTM V0, X6
	VFIRSTM V0, X7
	VSLLVI  $8, V28, V30
	VSRLVI  $25, V29, V29
	RET