Re: [PATCH v3 net-next] net: Implement fast csum_partial for x86_64

On Thu, Feb 4, 2016 at 12:59 PM, Tom Herbert [off-list ref] wrote:

On Thu, Feb 4, 2016 at 9:09 AM, David Laight [off-list ref] wrote:

quoted

From: Tom Herbert
...

quoted

quoted

If nothing else reducing the size of this main loop may be desirable.
I know the newer x86 is supposed to have a loop buffer so that it can
basically loop on already decoded instructions.  Normally it is only
something like 64 or 128 bytes in size though.  You might find that
reducing this loop to that smaller size may improve the performance
for larger payloads.

I saw 128 to be better in my testing. For large packets this loop does
all the work. I see performance dependent on the amount of loop
overhead, i.e. we got it down to two non-adcq instructions but it is
still noticeable. Also, this helps a lot on sizes up to 128 bytes
since we only need to do single call in the jump table and no trip
through the loop.

But one of your 'loop overhead' instructions is 'loop'.
Look at http://www.agner.org/optimize/instruction_tables.pdf
you don't want to be using 'loop' on intel cpus.

I'm not following. We can replace loop with decl %ecx and jg, but why
is that better?

Because loop takes something like 7 cycles whereas the decl/jg
approach takes 2 or 3.  It is probably one of the reasons things look
so much better with the loop unrolled.

- Alex