Re: Faster way to test pixels?

FROM : Jens Alfke
DATE : Sun May 25 18:58:46 2008

On 25 May '08, at 8:14 AM, Steve Christensen wrote:

> Unless you know for a fact that your bitmap data is packed such that 
> each row begins immediately after the previous row, you'll need to 
> do a bit more work. Bitmaps can be created with [bits bytesPerRow] > 
> bytesPerPixel * [bits pixelsWide]. In that case you could have some 
> uninitialized bytes between the end of one row and the beginning of 
> the next, which could affect the outcome of your test.


I agree — I've been burned by this in the past. RowBytes often seems 
to get rounded up to multiples of a power of 2, such as 8 or 16, 
probably for better cache coherency or because GPUs are optimized for 
it.

—Jens