From owner-freebsd-java Thu Feb 28 6:29:12 2002 Delivered-To: freebsd-java@freebsd.org Received: from l04.research.kpn.com (l04.research.kpn.com [139.63.192.204]) by hub.freebsd.org (Postfix) with ESMTP id 0B23337B435 for ; Thu, 28 Feb 2002 06:28:52 -0800 (PST) Received: by l04.research.kpn.com with Internet Mail Service (5.5.2653.19) id <1Z1F8AB8>; Thu, 28 Feb 2002 15:28:51 +0100 Message-ID: <59063B5B4D98D311BC0D0001FA7E452205FDA3C7@l04.research.kpn.com> From: "Koster, K.J." To: 'Mike Gratton' Cc: freebsd-java@FreeBSD.ORG Subject: RE: Ugrade from linux-jdk to native Date: Thu, 28 Feb 2002 15:28:48 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain; charset="iso-8859-1" Sender: owner-freebsd-java@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Dear Mike, > > I don't know under which circumstances it is true, but > apparently using > Hotspot can make Java bytecode execute as fast as or faster than > natively compiled C++ code. Sorry, no references, this is just what I > heard around it's introduction. > Would you introduce a JIT, saying it is slower than its predecessors? :-) HP has written an HP9000 emu that runs code faster than the host it runs on(!). I believe it's arstechnica.com that had an article on this. Slashdot carries a few references to articles, but I have no time to search for them. In a project with text parsers I have seen a quick 'n dirty interpreted parser run rings around a carefully handtuned C parser. We found out the interpreted parser fit entirely into the instruction cache of the host, while the C parser was several times larger than that cache. Kees Jan ===================================================== You can't have everything. Where would you put it? [Steven Wright] To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-java" in the body of the message