Date: Mon, 24 Jun 2013 16:54:45 +0200 From: Katja Malvoni <kmalvoni@...il.com> To: john-dev@...ts.openwall.com Subject: Re: Parallella: bcrypt Hello, On Tue, May 28, 2013 at 1:58 AM, Solar Designer <solar@...nwall.com> wrote: > Katja, Yaniv - > > On Sun, May 26, 2013 at 07:37:55PM -0400, Yaniv Sapir wrote: > > Here's a couple command line options you can try when compiling the code. > > Please look at the manual for further details. > > > > -mfp-mode=int # this sets the FPU mode to integer. However, please > > make sure that the generated code does not re-program the CONFIG register > > before every integer operation > > Let's definitely try this. I was afraid we'd have to resort to assembly > code to use the FPU in integer mode - it's great news to me that we seem > not to have to. > Unfortunately, this doesn't help a lot... Execution speed with -02 is 45.969000 ms and with -mfp-mode=int is 45.951000 ms. I checked generated assembly code it seems that CONFIG register isn't re-programmed before every integer operation. > > > -O3 > > -Ofast # e-gcc supports this level too > > We can try these too, but I don't expect much/any advantage over -O2. > Actually these two made it even slower, 50.725000 ms with -O3 and 50.688000 ms with -Ofast > > -falign-loops=8 and -falign-functions=8 are worth trying. (The latter > should only make a measurable difference with the size-optimized > implementation, where a portion of code has been moved into a separate > function that is called from several places.) > > These also didn't help - 46.504000 ms with -falign-loops=8 and 46.542000 ms with -falign-functions=8 I attached output for every used command line option with code sizes. Katja Content of type "text/html" skipped View attachment "execution_speeds.txt" of type "text/plain" (2106 bytes)
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.