aa1b377e71
Change license to BSD-2-Clause-Patent using an SPDX-License-Identifier statement. Cc: Liming Gao <liming.gao@intel.com> Cc: Leif Lindholm <leif@nuviainc.com> Cc: Ard Biesheuvel <ard.biesheuvel@arm.com> Signed-off-by: Michael D Kinney <michael.d.kinney@intel.com> Reviewed-by: Leif Lindholm <leif@nuviainc.com> Acked-by: Ard Biesheuvel <ard.biesheuvel@arm.com>
121 lines
3.4 KiB
ArmAsm
121 lines
3.4 KiB
ArmAsm
//
|
|
// Copyright (c) 2013, Linaro Limited
|
|
// All rights reserved.
|
|
// SPDX-License-Identifier: BSD-2-Clause-Patent
|
|
//
|
|
|
|
// Assumptions:
|
|
//
|
|
// ARMv8-a, AArch64
|
|
//
|
|
|
|
|
|
// Parameters and result.
|
|
#define src1 x0
|
|
#define src2 x1
|
|
#define limit x2
|
|
#define result x0
|
|
|
|
// Internal variables.
|
|
#define data1 x3
|
|
#define data1w w3
|
|
#define data2 x4
|
|
#define data2w w4
|
|
#define diff x6
|
|
#define endloop x7
|
|
#define tmp1 x8
|
|
#define tmp2 x9
|
|
#define pos x11
|
|
#define limit_wd x12
|
|
#define mask x13
|
|
|
|
.p2align 6
|
|
ASM_GLOBAL ASM_PFX(InternalMemCompareMem)
|
|
ASM_PFX(InternalMemCompareMem):
|
|
eor tmp1, src1, src2
|
|
tst tmp1, #7
|
|
b.ne .Lmisaligned8
|
|
ands tmp1, src1, #7
|
|
b.ne .Lmutual_align
|
|
add limit_wd, limit, #7
|
|
lsr limit_wd, limit_wd, #3
|
|
|
|
// Start of performance-critical section -- one 64B cache line.
|
|
.Lloop_aligned:
|
|
ldr data1, [src1], #8
|
|
ldr data2, [src2], #8
|
|
.Lstart_realigned:
|
|
subs limit_wd, limit_wd, #1
|
|
eor diff, data1, data2 // Non-zero if differences found.
|
|
csinv endloop, diff, xzr, ne // Last Dword or differences.
|
|
cbz endloop, .Lloop_aligned
|
|
// End of performance-critical section -- one 64B cache line.
|
|
|
|
// Not reached the limit, must have found a diff.
|
|
cbnz limit_wd, .Lnot_limit
|
|
|
|
// Limit % 8 == 0 => all bytes significant.
|
|
ands limit, limit, #7
|
|
b.eq .Lnot_limit
|
|
|
|
lsl limit, limit, #3 // Bits -> bytes.
|
|
mov mask, #~0
|
|
lsl mask, mask, limit
|
|
bic data1, data1, mask
|
|
bic data2, data2, mask
|
|
|
|
orr diff, diff, mask
|
|
|
|
.Lnot_limit:
|
|
rev diff, diff
|
|
rev data1, data1
|
|
rev data2, data2
|
|
|
|
// The MS-non-zero bit of DIFF marks either the first bit
|
|
// that is different, or the end of the significant data.
|
|
// Shifting left now will bring the critical information into the
|
|
// top bits.
|
|
clz pos, diff
|
|
lsl data1, data1, pos
|
|
lsl data2, data2, pos
|
|
|
|
// But we need to zero-extend (char is unsigned) the value and then
|
|
// perform a signed 32-bit subtraction.
|
|
lsr data1, data1, #56
|
|
sub result, data1, data2, lsr #56
|
|
ret
|
|
|
|
.Lmutual_align:
|
|
// Sources are mutually aligned, but are not currently at an
|
|
// alignment boundary. Round down the addresses and then mask off
|
|
// the bytes that precede the start point.
|
|
bic src1, src1, #7
|
|
bic src2, src2, #7
|
|
add limit, limit, tmp1 // Adjust the limit for the extra.
|
|
lsl tmp1, tmp1, #3 // Bytes beyond alignment -> bits.
|
|
ldr data1, [src1], #8
|
|
neg tmp1, tmp1 // Bits to alignment -64.
|
|
ldr data2, [src2], #8
|
|
mov tmp2, #~0
|
|
|
|
// Little-endian. Early bytes are at LSB.
|
|
lsr tmp2, tmp2, tmp1 // Shift (tmp1 & 63).
|
|
add limit_wd, limit, #7
|
|
orr data1, data1, tmp2
|
|
orr data2, data2, tmp2
|
|
lsr limit_wd, limit_wd, #3
|
|
b .Lstart_realigned
|
|
|
|
.p2align 6
|
|
.Lmisaligned8:
|
|
sub limit, limit, #1
|
|
1:
|
|
// Perhaps we can do better than this.
|
|
ldrb data1w, [src1], #1
|
|
ldrb data2w, [src2], #1
|
|
subs limit, limit, #1
|
|
ccmp data1w, data2w, #0, cs // NZCV = 0b0000.
|
|
b.eq 1b
|
|
sub result, data1, data2
|
|
ret
|