Question

so i’m working with a bunch of 2048×2048 sprite sheets which fill up memory rather quickly. As is, i’m using the following method (via Ray Wenderlich) to load a texture:

- (GLuint)setupTexture:(NSString *)fileName 
{    
    CGImageRef spriteImage = [UIImage imageNamed:fileName].CGImage;
    if (!spriteImage) 
    {
        NSLog(@"Failed to load image %@", fileName);
        exit(1);
    }
    size_t width = CGImageGetWidth(spriteImage);
    size_t height = CGImageGetHeight(spriteImage);
    GLubyte * spriteData = (GLubyte *) calloc(width*height*4, sizeof(GLubyte));
    CGContextRef spriteContext = CGBitmapContextCreate(spriteData, width, height, 8,     width*4,CGImageGetColorSpace(spriteImage), kCGImageAlphaPremultipliedLast);    
    CGContextDrawImage(spriteContext, CGRectMake(0, 0, width, height), spriteImage);
    CGContextRelease(spriteContext);
    GLuint texName;
    glGenTextures(1, &texName);
    glBindTexture(GL_TEXTURE_2D, texName);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST); 
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
    glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA, width, height, 0, GL_RGBA, GL_UNSIGNED_BYTE, spriteData);
    GLenum err = glGetError();
    if (err != GL_NO_ERROR)
        NSLog(@"Error uploading texture. glError: 0x%04X", err);    
    free(spriteData);        
    return texName;    
}

so my question is, how do i discard alpha information from the CGImage, then “downsample” the image to fewer bits per pixel, and finally tell OpenGL about it?

Answer 1

I use this code to convert the data written by CGContextDrawImage to RGB565. It uses optimized NEON code to process 8 pixels at a time on devices with support NEON (every iOS device that runs armv7 code has such a chip). The data pointer that you see there is the same as your spriteData pointer, I was just too lazy to rename it.

void *temp = malloc(width * height * 2);
uint32_t *inPixel32  = (uint32_t *)data;
uint16_t *outPixel16 = (uint16_t *)temp;
uint32_t pixelCount = width * height;

#ifdef __ARM_NEON__
for(uint32_t i=0; i<pixelCount; i+=8, inPixel32+=8, outPixel16+=8)
{
    uint8x8x4_t rgba  = vld4_u8((const uint8_t *)inPixel32);

    uint8x8_t r = vshr_n_u8(rgba.val[0], 3);
    uint8x8_t g = vshr_n_u8(rgba.val[1], 2);
    uint8x8_t b = vshr_n_u8(rgba.val[2], 3);

    uint16x8_t r16 = vmovl_u8(r);
    uint16x8_t g16 = vmovl_u8(g);
    uint16x8_t b16 = vmovl_u8(b);

    r16 = vshlq_n_u16(r16, 11);
    g16 = vshlq_n_u16(g16, 5);

    uint16x8_t rg16 = vorrq_u16(r16, g16);
    uint16x8_t result = vorrq_u16(rg16, b16);

    vst1q_u16(outPixel16, result);
}
#else                
for(uint32_t i=0; i<pixelCount; i++, inPixel32++)
{
    uint32_t r = (((*inPixel32 >> 0)  & 0xFF) >> 3);
    uint32_t g = (((*inPixel32 >> 8)  & 0xFF) >> 2);
    uint32_t b = (((*inPixel32 >> 16) & 0xFF) >> 3);

    *outPixel16++ = (r << 11) | (g << 5) | (b << 0);               
}
#endif

free(data);
data = temp;