view arm/asm.S @ 10644:5da7180afadf libavcodec

refactor and optimize scalarproduct 29-105% faster apply_filter, 6-90% faster ape decoding on core2 (Any x86 other than core2 probably gets much less, since this is mostly due to ssse3 cachesplit avoidance and I haven't written the full gamut of other cachesplit modes.) 9-123% faster ape decoding on G4.

/*
 * Copyright (c) 2008 Mans Rullgard <[e-mail]>
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg 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.
 *
 * FFmpeg 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 FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "config.h"

#ifdef __ELF__
#   define ELF
#else
#   define ELF @
#endif

        .macro require8, val=1
ELF     .eabi_attribute 24, \val
        .endm

        .macro preserve8, val=1
ELF     .eabi_attribute 25, \val
        .endm

        .macro function name, export=0
.if \export
        .global EXTERN_ASM\name
EXTERN_ASM\name:
.endif
ELF     .type   \name, %function
        .func   \name
\name:
        .endm

        .macro movrel rd, val
#if HAVE_ARMV6T2 && !CONFIG_PIC
        movw            \rd, #:lower16:\val
        movt            \rd, #:upper16:\val
#else
        ldr             \rd, =\val
#endif
        .endm

#if HAVE_VFP_ARGS
        .eabi_attribute 28, 1
#   define VFP
#   define NOVFP @
#else
#   define VFP   @
#   define NOVFP
#endif

#define GLUE(a, b) a ## b
#define JOIN(a, b) GLUE(a, b)
#define X(s) JOIN(EXTERN_ASM, s)