|
|
@@ -6,8 +6,8 @@ H1 { padding-left: 10px; padding-right: 0px; padding-top: 10px; padding-bottom
|
|
|
H2 { padding-left: 10px; padding-right: 0px; padding-top: 10px; padding-bottom: 0px; font-size: 1.2rem; }
|
|
|
blockquote {
|
|
|
tab-size: 3rem;
|
|
|
- color: #FFFFFF; background: #000000;
|
|
|
- font-size: 1.2rem; font-family: monospace;
|
|
|
+ color: #88FF88; background: #000000;
|
|
|
+ font-size: 0.95rem; font-family: monospace;
|
|
|
padding-left: 5px; padding-right: 5px;
|
|
|
padding-top: 5px; padding-bottom: 5px;
|
|
|
}
|
|
|
@@ -252,7 +252,7 @@ When adding an integer to a pointer, the address offset is multiplied by the poi
|
|
|
This means that a pointers of uint32_t for a color pixel only needs to add 4 elements to the pointer to move 16 bytes, while pointers of uint16_t moves 8 elements and pointers of uint8_t moves 16 elements.
|
|
|
|
|
|
</P><P>
|
|
|
-Adding two grayscale images using SIMD vectorization</B>:
|
|
|
+Adding two grayscale images using <B>SIMD vectorization</B>:
|
|
|
<PRE><BLOCKQUOTE>void addImages_simd(AlignedImageU8 targetImage, AlignedImageU8 imageA, AlignedImageU8 imageB) {
|
|
|
int width = image_getWidth(targetImage);
|
|
|
int height = image_getHeight(targetImage);
|
|
|
@@ -289,5 +289,69 @@ Adding two grayscale images using SIMD vectorization</B>:
|
|
|
</BLOCKQUOTE></PRE>
|
|
|
</P><P>
|
|
|
</P><IMG SRC="Images/Border.png"><P>
|
|
|
+
|
|
|
+</P><P>
|
|
|
+</P><H2> Loops with the arbitrary X vector size (faster for heavy calculations)</H2><P>
|
|
|
+</P><P>
|
|
|
+<B>Source/DFPSR/base/simd.h</B> contains F32xX, a SIMD vector storing laneCountX_32Bit 32-bit floats.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+<B>Source/DFPSR/base/simd.h</B> contains I32xX, a SIMD vector storing laneCountX_32Bit signed 32-bit integers.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+<B>Source/DFPSR/base/simd.h</B> contains U32xX, a SIMD vector storing laneCountX_32Bit unsigned 32-bit integers.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+<B>Source/DFPSR/base/simd.h</B> contains U16xX, a SIMD vector storing laneCountX_16Bit unsigned 16-bit integers.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+<B>Source/DFPSR/base/simd.h</B> contains U8xX, a SIMD vector storing laneCountX_8Bit unsigned 8-bit integers.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+Then you might want to take advantage of 256-bit SIMD vectors, but don't want to copy and paste code to use both U8x16 and U8x32.
|
|
|
+For functions working directly on values without reading nor writing, you can use templates to have multiple vector lengths supported at the same time.
|
|
|
+For a filter however, you only need to generate the code for the biggest available vector size, so we use U8xX and laneCountX_8Bit for processing 8-bit monochrome images using type aliases.
|
|
|
+When building with AVX2 (-mavx2 for g++), the X vector types (F32xX, I32xX, U32xX, U16xX, U8xX) change size from 128 bits to 256 bits and their lane counts (laneCountX_32Bit, laneCountX_16Bit, laneCountX_8Bit) also double.
|
|
|
+If you do not have AVX2 on your computer for testing this, you can force the X vector to be at least 256 bits by defining the macro EMULATE_256BIT_X_SIMD globally.
|
|
|
+The aligned image types and buffers allocated by the library are always aligned with at least the X vector's DSR_DEFAULT_ALIGNMENT, so you can safely use the X vector on any aligned image and most of the buffers.
|
|
|
+
|
|
|
+</P><P>
|
|
|
+Replaced <B>U8x16</B> with <B>U8xX</B> and <B>16</B> with <B>laneCountX_8Bit</B> to work with any future SIMD vector length:
|
|
|
+<PRE><BLOCKQUOTE>void addImages_simd(AlignedImageU8 targetImage, AlignedImageU8 imageA, AlignedImageU8 imageB) {
|
|
|
+ int width = image_getWidth(targetImage);
|
|
|
+ int height = image_getHeight(targetImage);
|
|
|
+ SafePointer<uint8_t> targetRow = image_getSafePointer(targetImage);
|
|
|
+ SafePointer<uint8_t> rowA = image_getSafePointer(imageA);
|
|
|
+ SafePointer<uint8_t> rowB = image_getSafePointer(imageB);
|
|
|
+ int targetStride = image_getStride(targetImage);
|
|
|
+ int strideA = image_getStride(imageA);
|
|
|
+ int strideB = image_getStride(imageB);
|
|
|
+ for (int y = 0; y < height; y++) {
|
|
|
+ SafePointer<uint8_t> targetPixel = targetRow;
|
|
|
+ SafePointer<uint8_t> pixelA = rowA;
|
|
|
+ SafePointer<uint8_t> pixelB = rowB;
|
|
|
+ // Assuming that we have ownership of any padding pixels
|
|
|
+ for (int x = 0; x < width; x += laneCountX_8Bit) {
|
|
|
+ // Read multiple source pixels at a time
|
|
|
+ U8xX a = U8xX::readAligned(pixelA, "addImages: reading pixelA");
|
|
|
+ U8xX b = U8xX::readAligned(pixelB, "addImages: reading pixelB");
|
|
|
+ // Saturated operations replace conditional move
|
|
|
+ U8xX result = saturatedAddition(a, b);
|
|
|
+ // Write the result multiple pixels at a time
|
|
|
+ result.writeAligned(targetPixel, "addImages: writing result");
|
|
|
+ // Move pixel pointers to the next pixel
|
|
|
+ targetPixel += laneCountX_8Bit;
|
|
|
+ pixelA += laneCountX_8Bit;
|
|
|
+ pixelB += laneCountX_8Bit;
|
|
|
+ }
|
|
|
+ // Move row pointers to the next row
|
|
|
+ targetRow.increaseBytes(targetStride);
|
|
|
+ rowA.increaseBytes(strideA);
|
|
|
+ rowB.increaseBytes(strideB);
|
|
|
+ }
|
|
|
+}
|
|
|
+</BLOCKQUOTE></PRE>
|
|
|
+</P><P>
|
|
|
+</P><IMG SRC="Images/Border.png"><P>
|
|
|
</P>
|
|
|
</BODY> </HTML>
|
David Piuva