This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH v2] Single threaded stdio optimization
On Fri, 2017-06-30 at 20:54 +0530, Siddhesh Poyarekar wrote:
> On Friday 30 June 2017 08:48 PM, Torvald Riegel wrote:
> > What's interesting here is that your high-level optimization is faster
> > than doing the single-thread check in the low-level lock (x86 has it
> > already in the low-level lock).
>
> Cache locality might be a factor - the fp struct may already be in cache
> as opposed to the TLS block from which one gets the value of
> multiple_threads.
And the check can happen earlier in the code, and at a higher level.