On Thu, Sep 26, 2013 at 09:20:29PM +0200, Torbjorn Granlund wrote: > For the last few months, I have been working on writing and rewriting > basecase code for X64-64 processors. The result is now in the > mainline GMP repo. > I am writing a tool that might be useful, a simple optimizer of assembly routines. You need to write a benchmark that measures performance and prints elapsed time and assembly file. Currently it has two optimization patterns, first is enclosing block of code without control flow instructions in
# EVOLVE_START code # EVOLVE_END and evolver will try different schedulings to find optimal one. Second one is when you choose between different instructions, where you write alternatives by following form. cmp $1, %rax #| cmp $1, %al A sequences can be done in following way cmp $1, %rax; ja .foo #| test %eax, %eax; jne .foo sounds interesting? _______________________________________________ gmp-devel mailing list gmp-devel@gmplib.org http://gmplib.org/mailman/listinfo/gmp-devel