Re: [Monotone-devel] Re: zlib vs gzip

[Zack Weinberg]

On Oct 31, 2007 8:15 AM, Jack Lloyd <address@hidden> wrote:
> > I'd like to point out that the #1 easiest thing anyone could do right
> > now to speed up monotone is get hand-optimized assembly SHA1
> > implementations into our copy of botan.  That one function shows up as
> > at least 7% of runtime every single time I profile it, doesn't matter
> > what the task is.
>
> To confirm: that one function == SHA_160::hash() ? Or calculate_ident?

SHA_160::hash.

> Do you see a measurable change here if you switch to the (current) asm
> version and/or using the OpenSSL engine? Do you see a change if you
> manually unroll the two loops in SHA_160::hash?

I haven't tried these, but I will when I get a chance.

> What CPU(s) are you profiling on? What compiler and version?

x86 and x86_64, gcc 4.1 and 4.2, at various times.

zw