/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (c) 2011, The Linux Foundation. All rights reserved.
 */


/* HEXAGON assembly optimized memset */
/* Replaces the standard library function memset */


        .macro HEXAGON_OPT_FUNC_BEGIN name
        .text
        .p2align 4
        .globl \name
        .type  \name, @function
\name:
        .endm

        .macro HEXAGON_OPT_FUNC_FINISH name
        .size  \name, . - \name
        .endm

/* FUNCTION: memset (v2 version) */
#if __HEXAGON_ARCH__ < 3
HEXAGON_OPT_FUNC_BEGIN memset
        {
                r6 = #8
                r7 = extractu(r0, #3 , #0)
                p0 = cmp.eq(r2, #0)
                p1 = cmp.gtu(r2, #7)
        }
        {
                r4 = vsplatb(r1)
                r8 = r0           /* leave r0 intact for return val  */
                r9 = sub(r6, r7)  /* bytes until double alignment  */
                if p0 jumpr r31   /* count == 0, so return  */
        }
        {
                r3 = #0
                r7 = #0
                p0 = tstbit(r9, #0)
                if p1 jump 2f /* skip byte loop */
        }

/* less than 8 bytes to set, so just set a byte at a time and return  */

                loop0(1f, r2) /* byte loop */
        .falign
1: /* byte loop */
        {
                memb(r8++#1) = r4
        }:endloop0
                jumpr r31
        .falign
2: /* skip byte loop */
        {
                r6 = #1
                p0 = tstbit(r9, #1)
                p1 = cmp.eq(r2, #1)
                if !p0 jump 3f /* skip initial byte store */
        }
        {
                memb(r8++#1) = r4
                r3:2 = sub(r3:2, r7:6)
                if p1 jumpr r31
        }
        .falign
3: /* skip initial byte store */
        {
                r6 = #2
                p0 = tstbit(r9, #2)
                p1 = cmp.eq(r2, #2)
                if !p0 jump 4f /* skip initial half store */
        }
        {
                memh(r8++#2) = r4
                r3:2 = sub(r3:2, r7:6)
                if p1 jumpr r31
        }
        .falign
4: /* skip initial half store */
        {
                r6 = #4
                p0 = cmp.gtu(r2, #7)
                p1 = cmp.eq(r2, #4)
                if !p0 jump 5f /* skip initial word store */
        }
        {
                memw(r8++#4) = r4
                r3:2 = sub(r3:2, r7:6)
                p0 = cmp.gtu(r2, #11)
                if p1 jumpr r31
        }
        .falign
5: /* skip initial word store */
        {
                r10 = lsr(r2, #3)
                p1 = cmp.eq(r3, #1)
                if !p0 jump 7f /* skip double loop */
        }
        {
                r5 = r4
                r6 = #8
                loop0(6f, r10) /* double loop */
        }

/* set bytes a double word at a time  */

        .falign
6: /* double loop */
        {
                memd(r8++#8) = r5:4
                r3:2 = sub(r3:2, r7:6)
                p1 = cmp.eq(r2, #8)
        }:endloop0
        .falign
7: /* skip double loop */
        {
                p0 = tstbit(r2, #2)
                if p1 jumpr r31
        }
        {
                r6 = #4
                p0 = tstbit(r2, #1)
                p1 = cmp.eq(r2, #4)
                if !p0 jump 8f /* skip final word store */
        }
        {
                memw(r8++#4) = r4
                r3:2 = sub(r3:2, r7:6)
                if p1 jumpr r31
        }
        .falign
8: /* skip final word store */
        {
                p1 = cmp.eq(r2, #2)
                if !p0 jump 9f /* skip final half store */
        }
        {
                memh(r8++#2) = r4
                if p1 jumpr r31
        }
        .falign
9: /* skip final half store */
        {
                memb(r8++#1) = r4
                jumpr r31
        }
HEXAGON_OPT_FUNC_FINISH memset
#endif


/*  FUNCTION: memset (v3 and higher version)  */
#if __HEXAGON_ARCH__ >= 3
HEXAGON_OPT_FUNC_BEGIN memset
        {
                r7=vsplatb(r1)
                r6 = r0
                if (r2==#0) jump:nt .L1
        }
        {
                r5:4=combine(r7,r7)
                p0 = cmp.gtu(r2,#8)
                if (p0.new) jump:nt .L3
        }
        {
                r3 = r0
                loop0(.L47,r2)
        }
        .falign
.L47:
        {
                memb(r3++#1) = r1
        }:endloop0 /* start=.L47 */
                jumpr r31
.L3:
        {
                p0 = tstbit(r0,#0)
                if (!p0.new) jump:nt .L8
                p1 = cmp.eq(r2, #1)
        }
        {
                r6 = add(r0, #1)
                r2 = add(r2,#-1)
                memb(r0) = r1
                if (p1) jump .L1
        }
.L8:
        {
                p0 = tstbit(r6,#1)
                if (!p0.new) jump:nt .L10
        }
        {
                r2 = add(r2,#-2)
                memh(r6++#2) = r7
                p0 = cmp.eq(r2, #2)
                if (p0.new) jump:nt .L1
        }
.L10:
        {
                p0 = tstbit(r6,#2)
                if (!p0.new) jump:nt .L12
        }
        {
                r2 = add(r2,#-4)
                memw(r6++#4) = r7
                p0 = cmp.eq(r2, #4)
                if (p0.new) jump:nt .L1
        }
.L12:
        {
                p0 = cmp.gtu(r2,#127)
                if (!p0.new) jump:nt .L14
        }
                r3 = and(r6,#31)
                if (r3==#0) jump:nt .L17
        {
                memd(r6++#8) = r5:4
                r2 = add(r2,#-8)
        }
                r3 = and(r6,#31)
                if (r3==#0) jump:nt .L17
        {
                memd(r6++#8) = r5:4
                r2 = add(r2,#-8)
        }
                r3 = and(r6,#31)
                if (r3==#0) jump:nt .L17
        {
                memd(r6++#8) = r5:4
                r2 = add(r2,#-8)
        }
.L17:
        {
                r3 = lsr(r2,#5)
                if (r1!=#0) jump:nt .L18
        }
        {
                r8 = r3
                r3 = r6
                loop0(.L46,r3)
        }
        .falign
.L46:
        {
                dczeroa(r6)
                r6 = add(r6,#32)
                r2 = add(r2,#-32)
        }:endloop0 /* start=.L46 */
.L14:
        {
                p0 = cmp.gtu(r2,#7)
                if (!p0.new) jump:nt .L28
                r8 = lsr(r2,#3)
        }
                loop0(.L44,r8)
        .falign
.L44:
        {
                memd(r6++#8) = r5:4
                r2 = add(r2,#-8)
        }:endloop0 /* start=.L44 */
.L28:
        {
                p0 = tstbit(r2,#2)
                if (!p0.new) jump:nt .L33
        }
        {
                r2 = add(r2,#-4)
                memw(r6++#4) = r7
        }
.L33:
        {
                p0 = tstbit(r2,#1)
                if (!p0.new) jump:nt .L35
        }
        {
                r2 = add(r2,#-2)
                memh(r6++#2) = r7
        }
.L35:
                p0 = cmp.eq(r2,#1)
                if (p0) memb(r6) = r1
.L1:
                jumpr r31
.L18:
                loop0(.L45,r3)
        .falign
.L45:
                dczeroa(r6)
        {
                memd(r6++#8) = r5:4
                r2 = add(r2,#-32)
        }
                memd(r6++#8) = r5:4
                memd(r6++#8) = r5:4
        {
                memd(r6++#8) = r5:4
        }:endloop0 /* start=.L45  */
                jump .L14
HEXAGON_OPT_FUNC_FINISH memset
#endif