| Server IP : 54.233.248.239 / Your IP : 172.28.20.13 Web Server : Apache System : Linux ip-172-28-29-189 6.5.0-1014-aws #14~22.04.1-Ubuntu SMP Thu Feb 15 15:27:06 UTC 2024 x86_64 User : www-data ( 33) PHP Version : 7.2.34-43+ubuntu22.04.1+deb.sury.org+1 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals, MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON Directory : /usr/lib/modules/6.8.0-1042-aws/build/arch/x86/include/asm/ |
Upload File : |
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_X86_XOR_AVX_H
#define _ASM_X86_XOR_AVX_H
/*
* Optimized RAID-5 checksumming functions for AVX
*
* Copyright (C) 2012 Intel Corporation
* Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
*
* Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
*/
#include <linux/compiler.h>
#include <asm/fpu/api.h>
#define BLOCK4(i) \
BLOCK(32 * i, 0) \
BLOCK(32 * (i + 1), 1) \
BLOCK(32 * (i + 2), 2) \
BLOCK(32 * (i + 3), 3)
#define BLOCK16() \
BLOCK4(0) \
BLOCK4(4) \
BLOCK4(8) \
BLOCK4(12)
static void xor_avx_2(unsigned long bytes, unsigned long * __restrict p0,
const unsigned long * __restrict p1)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
}
kernel_fpu_end();
}
static void xor_avx_3(unsigned long bytes, unsigned long * __restrict p0,
const unsigned long * __restrict p1,
const unsigned long * __restrict p2)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
}
kernel_fpu_end();
}
static void xor_avx_4(unsigned long bytes, unsigned long * __restrict p0,
const unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p3[i / sizeof(*p3)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16();
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
p3 = (unsigned long *)((uintptr_t)p3 + 512);
}
kernel_fpu_end();
}
static void xor_avx_5(unsigned long bytes, unsigned long * __restrict p0,
const unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3,
const unsigned long * __restrict p4)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p4[i / sizeof(*p4)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p3[i / sizeof(*p3)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
p3 = (unsigned long *)((uintptr_t)p3 + 512);
p4 = (unsigned long *)((uintptr_t)p4 + 512);
}
kernel_fpu_end();
}
static struct xor_block_template xor_block_avx = {
.name = "avx",
.do_2 = xor_avx_2,
.do_3 = xor_avx_3,
.do_4 = xor_avx_4,
.do_5 = xor_avx_5,
};
#define AVX_XOR_SPEED \
do { \
if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE)) \
xor_speed(&xor_block_avx); \
} while (0)
#define AVX_SELECT(FASTEST) \
(boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)
#endif