Re: [PATCH -tip v3 09/11] data_race: Avoid nested statement expression

From: Stephen Rothwell
Date: Thu May 28 2020 - 08:53:45 EST

Hi Arnd,

On Wed, 27 May 2020 11:26:51 +0200 Arnd Bergmann <arnd@xxxxxxxx> wrote:
> Right. I think there is still room for optimization around here, but
> for v5.8 I'm happy enough with Marco's__unqual_scalar_typeof()
> change. Stephen Rothwell is probably the one who's most affected
> by compile speed, so it would be good to get an Ack/Nak from him
> on whether this brings speed and memory usage back to normal
> for him as well.

Assuming you meant "[PATCH -tip] compiler_types.h: Optimize
__unqual_scalar_typeof compilation time"

I did some x86_64 allmodconfig builds (as I do all day):

Linus' tree:

36884.15user 1439.31system 9:05.46elapsed 7025%CPU (0avgtext+0avgdata 500416maxresident)k
0inputs+128outputs (0major+64821256minor)pagefaults 0swaps
36878.19user 1436.60system 9:05.37elapsed 7025%CPU (0avgtext+0avgdata 494656maxresident)k
0inputs+128outputs (0major+64771097minor)pagefaults 0swaps


42378.58user 1513.34system 9:59.33elapsed 7323%CPU (0avgtext+0avgdata 537920maxresident)k
0inputs+384outputs (0major+65102976minor)pagefaults 0swaps
42378.38user 1509.52system 9:59.12elapsed 7325%CPU (0avgtext+0avgdata 535360maxresident)k
0inputs+384outputs (0major+65102513minor)pagefaults 0swaps


39090.54user 1464.71system 9:17.36elapsed 7276%CPU (0avgtext+0avgdata 520576maxresident)k
0inputs+384outputs (0major+62226026minor)pagefaults 0swaps
39101.66user 1471.55system 9:18.13elapsed 7269%CPU (0avgtext+0avgdata 513856maxresident)k
0inputs+384outputs (0major+62243972minor)pagefaults 0swaps

So, it is a bit better than current linux-next, but not quita back to
Linus' tree (but that is not unexpected as there are over 12000 new
commits in -next).

$ x86_64-linux-gnu-gcc --version
x86_64-linux-gnu-gcc (Debian 9.3.0-8) 9.3.0

80 thread Power8 using -j100

Stephen Rothwell

Attachment: pgpER7OergYD1.pgp
Description: OpenPGP digital signature