On Mon, 2009-06-22 at 23:41 +0200, Jörn Engel wrote: > Four loops doing the same increment with different data types: long, > u64, we32 (wrong-endian) and we64. Compile with _no_ optimizations. That's a bit of a poor test then. Especially on architectures with a load-and-swap instruction where it really shouldn't be any slower at all. (Although since GCC doesn't have an __attribute__((littleendian)) I'm not entirely sure how to entice it into _using_ said instruction for the purpose of the test... I think the kernel does manage somehow though, if you get the sources _just_ right.) -- David Woodhouse Open Source Technology Centre David.Woodhouse@xxxxxxxxx Intel Corporation -- To unsubscribe from this list: send the line "unsubscribe linux-embedded" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
