Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 1 Aug 2002 20:05:26 -0700
From:      Bill Huey (Hui) <billh@gnuppy.monkey.org>
To:        Calvin Austin <calvin.austin@sun.com>
Cc:        freebsd-java@freebsd.org, "Bill Huey (Hui)" <billh@gnuppy.monkey.org>
Subject:   Re: FreeBSD HotSpot speed
Message-ID:  <20020802030526.GA3544@gnuppy.monkey.org>
In-Reply-To: <20020801235356.GA2902@gnuppy.monkey.org>
References:  <20020714231141.GA2242@gnuppy.monkey.org> <3D330C11.5B9631E7@sun.com> <20020715221518.GA2820@gnuppy.monkey.org> <3D488314.1726D67B@sun.com> <20020801004920.GA2629@gnuppy.monkey.org> <3D488BC4.C4696AA2@sun.com> <20020801031438.GA2861@gnuppy.monkey.org> <3D493BDB.437924AD@sun.com> <20020801235356.GA2902@gnuppy.monkey.org>

next in thread | previous in thread | raw e-mail | index | archive | help

Hey,

In a mail to Calvin Austin at Sun Microsystems....

	On Thu, Aug 01, 2002 at 04:53:56PM -0700, Bill Huey wrote:
	> [HotSpot]
	> 
	> I didn't get a chance to hack on that threading issue last night since I
	> was updating all my machine packages. The benchmarks that I've seen
	> demand money from you before you can use it. I'm probably either going
	> to write my own or adapt some other C language benchmark. It should be
	> trivial and I report back with the results after that.

Dammmmn... "compiler1" was about 10x faster than "core" and competitive with gcc
with -O0 with both of them coming in at around 3 seconds. "-O3" was 3x faster than
both of those at about 0.97 seconds.

HotSpot is definitely working and executing code very fast, so it's got to be a
thread contention issue like you (Calvin Austin) mentioned before. This is really
encouraging though. ;)

Thanks for the clue.

bill


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-java" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020802030526.GA3544>