mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-08-29 13:57:58 -04:00
a967b1f51c
Drop the XOR implementation generated by the vectorizer: this has always been a bit of a hack, and now that arm64 has an intrinsics version that works on ARM too, let's use that instead. So copy the part of the arm64 code that can be shared (so not the EOR3 version). The arm64 code will be updated in a subsequent patch to share this implementation. Performance (QEMU mach-virt VM running on Synquacer [Cortex-A53 @ 1 GHz] Before: [ 3.519687] xor: measuring software checksum speed [ 3.521725] neon : 1660 MB/sec [ 3.524733] 32regs : 1105 MB/sec [ 3.527751] 8regs : 1098 MB/sec [ 3.529911] arm4regs : 1540 MB/sec After: [ 3.517654] xor: measuring software checksum speed [ 3.519454] neon : 1896 MB/sec [ 3.522499] 32regs : 1090 MB/sec [ 3.525560] 8regs : 1083 MB/sec [ 3.527700] arm4regs : 1556 MB/sec Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Acked-by: Christoph Hellwig <hch@lst.de> Link: https://patch.msgid.link/20260422171655.3437334-12-ardb+git@google.com Signed-off-by: Eric Biggers <ebiggers@kernel.org>
102 lines
2.3 KiB
C
102 lines
2.3 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
#include "xor_impl.h"
|
|
|
|
static void
|
|
xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0];
|
|
p1[1] ^= p2[1];
|
|
p1[2] ^= p2[2];
|
|
p1[3] ^= p2[3];
|
|
p1[4] ^= p2[4];
|
|
p1[5] ^= p2[5];
|
|
p1[6] ^= p2[6];
|
|
p1[7] ^= p2[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0];
|
|
p1[1] ^= p2[1] ^ p3[1];
|
|
p1[2] ^= p2[2] ^ p3[2];
|
|
p1[3] ^= p2[3] ^ p3[3];
|
|
p1[4] ^= p2[4] ^ p3[4];
|
|
p1[5] ^= p2[5] ^ p3[5];
|
|
p1[6] ^= p2[6] ^ p3[6];
|
|
p1[7] ^= p2[7] ^ p3[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
static void
|
|
xor_8regs_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5)
|
|
{
|
|
long lines = bytes / (sizeof (long)) / 8;
|
|
|
|
do {
|
|
p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
|
|
p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
|
|
p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
|
|
p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
|
|
p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
|
|
p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
|
|
p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
|
|
p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
|
|
p1 += 8;
|
|
p2 += 8;
|
|
p3 += 8;
|
|
p4 += 8;
|
|
p5 += 8;
|
|
} while (--lines > 0);
|
|
}
|
|
|
|
DO_XOR_BLOCKS(8regs, xor_8regs_2, xor_8regs_3, xor_8regs_4, xor_8regs_5);
|
|
|
|
struct xor_block_template xor_block_8regs = {
|
|
.name = "8regs",
|
|
.xor_gen = xor_gen_8regs,
|
|
};
|