从 SDK 中,我得到了像素格式 BGR 打包的图像,即BGRBGRBGR
. 对于另一个应用程序,我需要将此格式转换为 RGB 平面RRRGGGBBB
。我不想只为这个任务使用额外的库,所以我必须使用自己的代码在格式之间进行转换。
我正在使用 C# .NET 4.5 32bit 并且数据位于具有相同大小的字节数组中。
现在我正在遍历数组源并将 BGR 值分配到目标数组中的适当位置,但这需要太长时间(1.3 兆像素图像需要 250 毫秒)。运行代码的处理器是 Intel Atom E680,可以访问 MMX、SSE、SSE2、SSE3、SSSE3。
不幸的是,我不了解内在函数,也无法将代码转换为类似问题的代码,例如快速方法通过翻译复制内存 - ARGB 到 BGR以满足我的需要。
我目前用来在像素格式之间转换的代码是:
// the array with the BGRBGRBGR pixel data
byte[] source;
// the array with the RRRGGGBBB pixel data
byte[] result;
// the amount of pixels in one channel, width*height
int imageSize;
for (int i = 0; i < source.Length; i += 3)
{
result[i/3] = source[i + 2]; // R
result[i/3 + imageSize] = source[i + 1]; // G
result[i/3 + imageSize * 2] = source[i]; // B
}
我尝试将源数组的访问分成三个循环,每个通道一个,但这并没有真正帮助。所以我愿意接受建议。
for (int i = 0; i < source.Length; i += 3)
{
result[i/3] = source[i + 2]; // R
}
for (int i = 0; i < source.Length; i += 3)
{
result[i/3 + imageSize] = source[i + 1]; // G
}
for (int i = 0; i < source.Length; i += 3)
{
result[i/3 + imageSize * 2] = source[i]; // B
}
编辑:通过像这样删除除法和乘法,我把它降低到 180 毫秒,但是有没有办法让它更快?我猜它仍然很慢,因为内存读/写不是非常理想。
int targetPosition = 0;
int imageSize2 = imageSize * 2;
for (int i = 0; i < source.Length; i += 3)
{
result[targetPosition] = source[i + 2]; // R
targetPosition++;
}
targetPosition = 0;
for (int i = 0; i < source.Length; i += 3)
{
result[targetPosition + imageSize] = source[i + 1]; // G
targetPosition++;
}
targetPosition = 0;
for (int i = 0; i < source.Length; i += 3)
{
result[targetPosition + imageSize2] = source[i]; // B
targetPosition++;
}
感谢 MBo 的回答,我能够将时间从 180 毫秒减少到 90 毫秒!这是代码:
转换器.cpp:
#include "stdafx.h"
BOOL __stdcall DllMain(HINSTANCE hInst, DWORD dwReason, LPVOID lpReserved) {
return TRUE;
}
const unsigned char Mask[] = { 0, 3, 6, 9,
1, 4, 7, 10,
2, 5, 8, 11,
12, 13, 14, 15};
extern "C" __declspec(dllexport) char* __stdcall ConvertPixelFormat(unsigned char* source, unsigned char *target, int imgSize) {
_asm {
//interleave r1g1b1 r2g2b2 r3g3b3 r4b4g4 r5b5g5 r6... to planar
// r1r2r3r4r5..... g1g2g3g4g5... b1b2b3b4b5...
push edi
push esi
mov eax, source //A address
mov edx, target //B address
mov ecx, imgSize
movdqu xmm5, Mask //load shuffling mask
mov edi, imgSize //load interleave step
mov esi, eax
add esi, edi
add esi, edi
add esi, edi
shr ecx, 2 //divide count by 4
dec ecx //exclude last array chunk
jle Rest
Cycle:
movdqu xmm0, [eax] //load 16 bytes
pshufb xmm0, xmm5 //shuffle bytes, we are interested in 12 ones
movd [edx], xmm0 //store 4 bytes of R
psrldq xmm0, 4 //shift right register, now G is on the end
movd [edx + edi], xmm0 //store 4 bytes of G to proper place
psrldq xmm0, 4 //do the same for B
movd [edx + 2 * edi], xmm0
add eax, 12 //shift source index to the next portion
add edx, 4 //shift destination index
loop Cycle
Rest: //treat the rest of array
cmp eax, esi
jae Finish
mov ecx, [eax]
mov [edx], cl //R
mov [edx + edi], ch //G
shr ecx, 16
mov [edx + 2 * edi], cl //B
add eax, 3
add edx, 1
jmp Rest
Finish:
pop esi
pop edi
}
}
C# 文件:
// Code to define the method
[DllImport("Converter.dll")]
unsafe static extern void ConvertPixelFormat(byte* source, byte* target, int imgSize);
// Code to execute the conversion
unsafe
{
fixed (byte* sourcePointer = &source[0])
{
fixed (byte* resultPointer = &result[0])
{
ConvertPixelFormat(sourcePointer, resultPointer, imageSize);
}
}
}