Hash :
cd64e0b6
Author :
Date :
2023-03-26T16:31:18
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162
/*
Simple DirectMedia Layer
Copyright (C) 1997-2023 Sam Lantinga <slouken@libsdl.org>
This software is provided 'as-is', without any express or implied
warranty. In no event will the authors be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not
claim that you wrote the original software. If you use this software
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
*/
#include "../SDL_internal.h"
#include "SDL_video.h"
#include "SDL_blit.h"
#include "SDL_blit_copy.h"
#ifdef __SSE__
/* This assumes 16-byte aligned src and dst */
static SDL_INLINE void SDL_memcpySSE(Uint8 *dst, const Uint8 *src, int len)
{
int i;
__m128 values[4];
for (i = len / 64; i--;) {
_mm_prefetch((const char *)src, _MM_HINT_NTA);
values[0] = *(__m128 *)(src + 0);
values[1] = *(__m128 *)(src + 16);
values[2] = *(__m128 *)(src + 32);
values[3] = *(__m128 *)(src + 48);
_mm_stream_ps((float *)(dst + 0), values[0]);
_mm_stream_ps((float *)(dst + 16), values[1]);
_mm_stream_ps((float *)(dst + 32), values[2]);
_mm_stream_ps((float *)(dst + 48), values[3]);
src += 64;
dst += 64;
}
if (len & 63) {
SDL_memcpy(dst, src, len & 63);
}
}
#endif /* __SSE__ */
#ifdef __MMX__
#ifdef _MSC_VER
#pragma warning(disable : 4799)
#endif
static SDL_INLINE void SDL_memcpyMMX(Uint8 *dst, const Uint8 *src, int len)
{
int remain = len & 63;
int i;
__m64 *d64 = (__m64 *)dst;
__m64 *s64 = (__m64 *)src;
for (i = len / 64; i--;) {
d64[0] = s64[0];
d64[1] = s64[1];
d64[2] = s64[2];
d64[3] = s64[3];
d64[4] = s64[4];
d64[5] = s64[5];
d64[6] = s64[6];
d64[7] = s64[7];
d64 += 8;
s64 += 8;
}
if (remain) {
const int skip = len - remain;
dst += skip;
src += skip;
while (remain--) {
*dst++ = *src++;
}
}
}
#endif /* __MMX__ */
void SDL_BlitCopy(SDL_BlitInfo *info)
{
SDL_bool overlap;
Uint8 *src, *dst;
int w, h;
int srcskip, dstskip;
w = info->dst_w * info->dst_fmt->BytesPerPixel;
h = info->dst_h;
src = info->src;
dst = info->dst;
srcskip = info->src_pitch;
dstskip = info->dst_pitch;
/* Properly handle overlapping blits */
if (src < dst) {
overlap = (dst < (src + h * srcskip));
} else {
overlap = (src < (dst + h * dstskip));
}
if (overlap) {
if (dst < src) {
while (h--) {
SDL_memmove(dst, src, w);
src += srcskip;
dst += dstskip;
}
} else {
src += ((h - 1) * srcskip);
dst += ((h - 1) * dstskip);
while (h--) {
SDL_memmove(dst, src, w);
src -= srcskip;
dst -= dstskip;
}
}
return;
}
#ifdef __SSE__
if (SDL_HasSSE() &&
!((uintptr_t)src & 15) && !(srcskip & 15) &&
!((uintptr_t)dst & 15) && !(dstskip & 15)) {
while (h--) {
SDL_memcpySSE(dst, src, w);
src += srcskip;
dst += dstskip;
}
return;
}
#endif
#ifdef __MMX__
if (SDL_HasMMX() && !(srcskip & 7) && !(dstskip & 7)) {
while (h--) {
SDL_memcpyMMX(dst, src, w);
src += srcskip;
dst += dstskip;
}
_mm_empty();
return;
}
#endif
while (h--) {
SDL_memcpy(dst, src, w);
src += srcskip;
dst += dstskip;
}
}
/* vi: set ts=4 sw=4 expandtab: */