This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH 0/6 rth/hpt] hp-timing cleanups
- From: David Miller <davem at davemloft dot net>
- To: rth at twiddle dot net
- Cc: libc-alpha at sourceware dot org, azanella at linux dot vnet dot ibm dot com, marcus dot shawcroft at arm dot com
- Date: Wed, 25 Jun 2014 22:21:41 -0700 (PDT)
- Subject: Re: [PATCH 0/6 rth/hpt] hp-timing cleanups
- Authentication-results: sourceware.org; auth=none
- References: <1403735086-21797-1-git-send-email-rth at twiddle dot net> <20140625 dot 153822 dot 52261450159233067 dot davem at davemloft dot net> <53ABA37F dot 4040405 at twiddle dot net>
From: Richard Henderson <rth@twiddle.net>
Date: Wed, 25 Jun 2014 21:37:19 -0700
> On 06/25/2014 03:38 PM, David Miller wrote:
>> No objections, but it's a shame that the overhead value is not used
>> instead of being accounted for when timings are made.
>
> How large is the value for sparc?
>
> It's zero for aarch64 and alpha; perhaps 10 cycles for x86_64.
> Which, when we're timing anything in ld.so is definitely lost
> in the noise.
Yeah it's 10 cycles or less on sparc.