kernel_optimize_test/lib/raid6/neon.c
Ard Biesheuvel 0e833e697b md/raid6: delta syndrome for ARM NEON
This implements XOR syndrome calculation using NEON intrinsics.
As before, the module can be built for ARM and arm64 from the
same source.

Relative performance on a Cortex-A57 based system:

  raid6: int64x1  gen()   905 MB/s
  raid6: int64x1  xor()   881 MB/s
  raid6: int64x2  gen()  1343 MB/s
  raid6: int64x2  xor()  1286 MB/s
  raid6: int64x4  gen()  1896 MB/s
  raid6: int64x4  xor()  1321 MB/s
  raid6: int64x8  gen()  1773 MB/s
  raid6: int64x8  xor()  1165 MB/s
  raid6: neonx1   gen()  1834 MB/s
  raid6: neonx1   xor()  1278 MB/s
  raid6: neonx2   gen()  2528 MB/s
  raid6: neonx2   xor()  1942 MB/s
  raid6: neonx4   gen()  2888 MB/s
  raid6: neonx4   xor()  2334 MB/s
  raid6: neonx8   gen()  2957 MB/s
  raid6: neonx8   xor()  2232 MB/s
  raid6: using algorithm neonx8 gen() 2957 MB/s
  raid6: .... xor() 2232 MB/s, rmw enabled

Cc: Markus Stockhausen <stockhausen@collogia.de>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NeilBrown <neilb@suse.com>
2015-08-31 19:29:05 +02:00

71 lines
2.1 KiB
C

/*
* linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics
*
* Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/raid/pq.h>
#ifdef __KERNEL__
#include <asm/neon.h>
#else
#define kernel_neon_begin()
#define kernel_neon_end()
#define cpu_has_neon() (1)
#endif
/*
* There are 2 reasons these wrappers are kept in a separate compilation unit
* from the actual implementations in neonN.c (generated from neon.uc by
* unroll.awk):
* - the actual implementations use NEON intrinsics, and the GCC support header
* (arm_neon.h) is not fully compatible (type wise) with the kernel;
* - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
* and we have to make sure that we never use *any* NEON/VFP instructions
* outside a kernel_neon_begin()/kernel_neon_end() pair.
*/
#define RAID6_NEON_WRAPPER(_n) \
static void raid6_neon ## _n ## _gen_syndrome(int disks, \
size_t bytes, void **ptrs) \
{ \
void raid6_neon ## _n ## _gen_syndrome_real(int, \
unsigned long, void**); \
kernel_neon_begin(); \
raid6_neon ## _n ## _gen_syndrome_real(disks, \
(unsigned long)bytes, ptrs); \
kernel_neon_end(); \
} \
static void raid6_neon ## _n ## _xor_syndrome(int disks, \
int start, int stop, \
size_t bytes, void **ptrs) \
{ \
void raid6_neon ## _n ## _xor_syndrome_real(int, \
int, int, unsigned long, void**); \
kernel_neon_begin(); \
raid6_neon ## _n ## _xor_syndrome_real(disks, \
start, stop, (unsigned long)bytes, ptrs); \
kernel_neon_end(); \
} \
struct raid6_calls const raid6_neonx ## _n = { \
raid6_neon ## _n ## _gen_syndrome, \
raid6_neon ## _n ## _xor_syndrome, \
raid6_have_neon, \
"neonx" #_n, \
0 \
}
static int raid6_have_neon(void)
{
return cpu_has_neon();
}
RAID6_NEON_WRAPPER(1);
RAID6_NEON_WRAPPER(2);
RAID6_NEON_WRAPPER(4);
RAID6_NEON_WRAPPER(8);