297565aa22
Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
30 lines
1.1 KiB
C
30 lines
1.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* Optimized RAID-5 checksumming functions for IA-64.
|
|
*/
|
|
|
|
|
|
extern void xor_ia64_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2);
|
|
extern void xor_ia64_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3);
|
|
extern void xor_ia64_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4);
|
|
extern void xor_ia64_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);
|
|
|
|
static struct xor_block_template xor_block_ia64 = {
|
|
.name = "ia64",
|
|
.do_2 = xor_ia64_2,
|
|
.do_3 = xor_ia64_3,
|
|
.do_4 = xor_ia64_4,
|
|
.do_5 = xor_ia64_5,
|
|
};
|
|
|
|
#define XOR_TRY_TEMPLATES xor_speed(&xor_block_ia64)
|