// PCALIGN padding on loong64: andi $0, $0, 0 (the architecture's NOP), plus
// the automatic loop-head alignment to a 16-byte boundary.
#include "textflag.h"

// func Pad16(x int64) int64
TEXT ·Pad16(SB), NOSPLIT, $0-16
	MOVV    x+0(FP), R4
	PCALIGN $16
	ADDV    $1, R4
	MOVV    R4, ret+8(FP)
	RET

// func Pad32(x int64) int64
TEXT ·Pad32(SB), NOSPLIT, $0-16
	MOVV    x+0(FP), R4
	PCALIGN $32
	ADDV    $1, R4
	MOVV    R4, ret+8(FP)
	RET

// func LoopAlign(x int64) int64
TEXT ·LoopAlign(SB), NOSPLIT, $0-16
	MOVV x+0(FP), R4
	MOVV $10, R5

loop:
	BEQ  R4, R5, done
	ADDV $1, R4
	JMP  loop

done:
	MOVV R4, ret+8(FP)
	RET