This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: RFC: Run libm tests separately for each function
* Joseph Myers:
> On Fri, 17 Feb 2017, Joseph Myers wrote:
>
>> I'd expect this patch to improve test time for sufficiently high
>> parallelism, where the move from 17 separately built large tests to 1137
>> smaller tests (on x86_64) allows more parallelism that outweighs the
>> overheads of running more tests separately from the makefile. And of
>> course if you compare with 2.25, that had serialization for the run of
>> gen-libm-test.pl (which happened unnecessarily as part of the build rather
>> than only when testing because of the before-compile setting).
>
> A single -j12 run before and after the patch (based on current mainline,
> so with my move of more functions to auto-libm-test-*) gives timings
> before
>
> real 0m27.193s
> user 4m27.496s
> sys 0m7.988s
>
> and after
>
> real 0m33.617s
> user 5m11.500s
> sys 0m22.392s
>
> which I consider acceptable (and as noted I'd expect test time to improve
> for sufficiently high parallelism on systems with enough CPU cores where
> the previous 17 compilations of 50 MB of code had a serializing effect).
Agreed, these numbers look reasonable.