Where can I find about optimization of assembly code?
I want to find a source of tips as:
Using DEC and JZ is faster than using LOOP...
Using SHL when multiplying for a power of two is a faster way of doing that...
Thanks
Julio
http://www.agner.org/
for amd
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/25112.PDF
you can see a loop take 8 cycle a dec 1 a jnz 1 and i think dec +jnz only 1