Date: Tue, 2 Jul 2002 18:06:27 -0700 (PDT) From: Matthew Dillon <dillon@apollo.backplane.com> To: "David O'Brien" <dev-null@NUXI.com> Cc: FreeBSD current users <current@FreeBSD.ORG> Subject: Re: -current results (was something funny with soft updates?) Message-ID: <200207030106.g6316Rwp008905@apollo.backplane.com> References: <Pine.BSF.4.21.0206281233500.75410-100000@InterJet.elischer.org> <200207020314.g623Eke5038019@apollo.backplane.com> <20020702164756.E70767@dragon.nuxi.com>
next in thread | previous in thread | raw e-mail | index | archive | help
:You really cannot say this -- GCC 3.1 does things 2.95 doesn't. 3.1 has
:a totally rewritten code scheduler. People can't get Pentium-4 and
:Athlon tbird specific optimizations for free.
:
:You almost seem to be making a claim on the quality of generated code,
:vs. just the run-time of the compiler. The two are different.
:
I am making no such claim. I began this investigation when Julian
forwarded some reports, and his own observations, that softupdates
did not seem to have the huge improvement in performance for buildworlds
in -current verses -stable. My analysis is about softupdates, the only
observation I made in regards to GCC3 was that it was taking far longer
to compile the same source. I made no statements on GCC3's code
generation quality vs GCC2.
-
However, since you asked, I will say that I am not at all impressed with
GCC3 vs GCC2. I've looked at a considerable amount of code with objdump
between -stable and -current and GCC3 doesn't really seem to improve
things much at all and in some run-time tests it seems to produce even
worse code then GCC2 did.... and GCC2 produced pretty bad code. I see
no improvement in cpu-intensive applications when I run a GCC2-generated
binary and a GCC3-generated binary on the same machine, side by side.
-Matt
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200207030106.g6316Rwp008905>