AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-12-25 04:01:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
4482ff226e
glibc/sysdeps/tile/memcopy.h

34 lines
1.3 KiB
C
Raw Normal View History

Optimize tile (mostly tilegx) memcpy and memmove performance. - Override <memcopy.h> so we use full 8-byte word copies on tilegx32 for memmove, then use op_t in memcpy instead of the previous locally-defined word_t just to avoid proliferating identical types. - Fix bug in memcpy prefetch that caused us to never prefetch past the first cache line. - Optimize misaligned memcpy by inlining _wordcopy_fwd_dest_aligned instead of just doing a dumb word-at-a-time copy. - Make memcpy safe for forward copies by doing all the loads from a given cache line prior to doing a wh64 (cache line zero-fill) on the destination. Remove now-redundant src == dst check. - Copy and optimize the generic wordcopy.c routines to use the tile "double align" instruction instead of the MERGE macro; to avoid offset addressing mode (which tile doesn't have) by rewriting the pointer math to load and store with a zero index; and to use post-increment addresses in the inner loops to improve scheduling.
2012-11-02 16:53:57 +00:00
/* memcopy.h -- definitions for memory copy functions. Tile version.
Update copyright dates with scripts/update-copyrights.
2016-01-04 16:05:18 +00:00
Copyright (C) 2012-2016 Free Software Foundation, Inc.
Optimize tile (mostly tilegx) memcpy and memmove performance. - Override <memcopy.h> so we use full 8-byte word copies on tilegx32 for memmove, then use op_t in memcpy instead of the previous locally-defined word_t just to avoid proliferating identical types. - Fix bug in memcpy prefetch that caused us to never prefetch past the first cache line. - Optimize misaligned memcpy by inlining _wordcopy_fwd_dest_aligned instead of just doing a dumb word-at-a-time copy. - Make memcpy safe for forward copies by doing all the loads from a given cache line prior to doing a wh64 (cache line zero-fill) on the destination. Remove now-redundant src == dst check. - Copy and optimize the generic wordcopy.c routines to use the tile "double align" instruction instead of the MERGE macro; to avoid offset addressing mode (which tile doesn't have) by rewriting the pointer math to load and store with a zero index; and to use post-increment addresses in the inner loops to improve scheduling.
2012-11-02 16:53:57 +00:00
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
#include <sysdeps/generic/memcopy.h>
#include <bits/wordsize.h>
Fix Wundef warning for MEMCPY_OK_FOR_FWD_MEMMOVE Define MEMCPY_OK_FOR_FWD_MEMMOVE in memcopy.h and let arch-specific implementations of that file override the value if necessary. This override is only useful for tile and moving this macro to memcopy.h allows us to remove the tile-specific memmove.c.
2014-06-28 00:35:24 +00:00
/* The tilegx implementation of memcpy is safe to use for memmove. */
#ifdef __tilegx__
# undef MEMCPY_OK_FOR_FWD_MEMMOVE
# define MEMCPY_OK_FOR_FWD_MEMMOVE 1
#endif
Optimize tile (mostly tilegx) memcpy and memmove performance. - Override <memcopy.h> so we use full 8-byte word copies on tilegx32 for memmove, then use op_t in memcpy instead of the previous locally-defined word_t just to avoid proliferating identical types. - Fix bug in memcpy prefetch that caused us to never prefetch past the first cache line. - Optimize misaligned memcpy by inlining _wordcopy_fwd_dest_aligned instead of just doing a dumb word-at-a-time copy. - Make memcpy safe for forward copies by doing all the loads from a given cache line prior to doing a wh64 (cache line zero-fill) on the destination. Remove now-redundant src == dst check. - Copy and optimize the generic wordcopy.c routines to use the tile "double align" instruction instead of the MERGE macro; to avoid offset addressing mode (which tile doesn't have) by rewriting the pointer math to load and store with a zero index; and to use post-increment addresses in the inner loops to improve scheduling.
2012-11-02 16:53:57 +00:00
/* Support more efficient copying on tilegx32, which supports
long long as a native 64-bit type. */
#if defined (__tilegx__) && __WORDSIZE == 32
# undef op_t
# define op_t unsigned long long int
#endif
Reference in New Issue Copy Permalink