1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-12 19:18:44 +02:00
FFmpeg/libavcodec/mips/mathops.h
ZhouXiaoyong 0ace686ae8 avcodec: optimize mathops for Loongson-3 v1
HAVE_LOONGSON is replaced by HAVE_LOONGSON3. Even Loongson-2E and 2F support
Loongson SIMD instructs but have low performance for decoding. We plan to focus
on optimizing Loongson-3A1000, 3B1500 and 3A1500, and modify the configure file
to support Loongson-2 series later by adding HAVE_LOONGSON2.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-04-27 02:25:12 +02:00

119 lines
3.1 KiB
C

/*
* Copyright (c) 2009 Mans Rullgard <mans@mansr.com>
* Copyright (c) 2015 Zhou Xiaoyong <zhouxiaoyong@loongson.cn>
*
* 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
*/
#ifndef AVCODEC_MIPS_MATHOPS_H
#define AVCODEC_MIPS_MATHOPS_H
#include <stdint.h>
#include "config.h"
#include "libavutil/common.h"
#if HAVE_INLINE_ASM
#if HAVE_LOONGSON3
#define MULH MULH
static inline av_const int MULH(int a, int b)
{
int c;
__asm__ ("dmult %1, %2 \n\t"
"mflo %0 \n\t"
"dsrl %0, %0, 32 \n\t"
: "=r"(c)
: "r"(a),"r"(b)
: "hi", "lo");
return c;
}
#define UMULH UMULH
static inline av_const unsigned UMULH(unsigned a, unsigned b)
{
unsigned c;
__asm__ ("dmultu %1, %2 \n\t"
"mflo %0 \n\t"
"dsrl %0, %0, 32 \n\t"
: "=r"(c)
: "r"(a),"r"(b)
: "hi", "lo");
return c;
}
#define mid_pred mid_pred
static inline av_const int mid_pred(int a, int b, int c)
{
int t = b;
__asm__ ("sgt $8, %1, %2 \n\t"
"movn %0, %1, $8 \n\t"
"movn %1, %2, $8 \n\t"
"sgt $8, %1, %3 \n\t"
"movz %1, %3, $8 \n\t"
"sgt $8, %0, %1 \n\t"
"movn %0, %1, $8 \n\t"
: "+&r"(t),"+&r"(a)
: "r"(b),"r"(c)
: "$8");
return t;
}
#define ff_sqrt ff_sqrt
static inline av_const unsigned int ff_sqrt(unsigned int a)
{
unsigned int b;
__asm__ ("ctc1 %1, $f0 \n\t"
"sqrt.s $f2, $f0 \n\t"
"cvt.w.s $f0, $f2 \n\t"
"cfc1 %0, $f0 \n\t"
: "=r"(b)
: "r"(a));
return b;
}
static inline av_const int64_t MAC64(int64_t d, int a, int b)
{
int64_t m;
__asm__ ("dmult %2, %3 \n\t"
"mflo %1 \n\t"
"daddu %0, %0, %1 \n\t"
: "+r"(d), "=&r"(m) : "r"(a), "r"(b)
: "hi", "lo");
return d;
}
#define MAC64(d, a, b) ((d) = MAC64(d, a, b))
static inline av_const int64_t MLS64(int64_t d, int a, int b)
{
int64_t m;
__asm__ ("dmult %2, %3 \n\t"
"mflo %1 \n\t"
"dsubu %0, %0, %1 \n\t"
: "+r"(d), "=&r"(m) : "r"(a), "r"(b)
: "hi", "lo");
return d;
}
#define MLS64(d, a, b) ((d) = MLS64(d, a, b))
#endif /* HAVE_LOONGSON3 */
#endif /* HAVE_INLINE_ASM */
#endif /* AVCODEC_MIPS_MATHOPS_H */