From owner-freebsd-ia64@FreeBSD.ORG Sat Apr 26 07:53:14 2003 Return-Path: Delivered-To: freebsd-ia64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6B1EE37B401 for ; Sat, 26 Apr 2003 07:53:14 -0700 (PDT) Received: from parmenides.zen.co.uk (parmenides.zen.co.uk [212.23.8.69]) by mx1.FreeBSD.org (Postfix) with SMTP id 2E60543F85 for ; Sat, 26 Apr 2003 07:53:13 -0700 (PDT) (envelope-from tony@ubik.demon.co.uk) Received: (qmail 9314 invoked from network); 26 Apr 2003 14:53:11 -0000 Received: from protagoras.zen.co.uk (212.23.8.61) by parmenides.zen.co.uk with QMQP; 26 Apr 2003 14:53:11 -0000 Received: from dsl-217-155-183-134.zen.co.uk (HELO ubik.demon.co.uk) (217.155.183.134) by protagoras.zen.co.uk with SMTP; 26 Apr 2003 14:53:11 -0000 X-Zen-Trace: 217.155.183.134 Message-ID: Date: Sat, 26 Apr 2003 14:52:11 +0000 To: Marcel Moolenaar From: Anthony Naggs References: <20030426073334.GA85139@rot13.obsecurity.org> <20030426094135.GA970@dhcp01.pn.xcllnt.net> In-Reply-To: <20030426094135.GA970@dhcp01.pn.xcllnt.net> MIME-Version: 1.0 X-Mailer: Turnpike Integrated Version 5.01 U cc: ia64@freebsd.org cc: Kris Kennaway Subject: Re: InformationWeek: Intel Sees A 32-Bit Hole In Itanium X-BeenThere: freebsd-ia64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the IA-64 List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 26 Apr 2003 14:53:14 -0000 In article <20030426094135.GA970@dhcp01.pn.xcllnt.net>, Marcel Moolenaar writes >On Sat, Apr 26, 2003 at 12:33:34AM -0700, Kris Kennaway wrote: >> IA-32 Execution Layer will take 32-bit code and convert it to 64-bit >> code that the Itanium processor can run, an Intel spokeswoman >> says. > >I wonder why the conversion if ia64 can already run ia32 applications. Quite slow, and Intel need to address AMD64's (perceived) lower risk migration for x86 users. AIUI native IA-32 execution doesn't support instruction extensions introduced on later Pentium models such as SSE, (since Pentium III). >Maybe Intel is planning to retire the ia32 execution unit early to >make room for caches and additional functional units? The IA-32 support takes little space at the moment, this would change somewhat if Intel were pushed into including a Xeon with 4 (say) way Hyper-Threading. So removing IA-32 wont yield much die space, but it means Intel don't have to keep taking more space to give IA-32 support comparable to their higher spec Pentium family. It also means Intel aren't committed to including IA-32 execution forever more. >> Is this something that FreeBSD can/should get involved with? > >I think it will be a waste of time. We already have ia32 support >that we probably don't maintain enough. Something else only adds >to the workload and it's not that we have people lining up :-) There is little information about the IA-32 Execution Layer as yet so one must speculate a little: Intel have committed a lot of development effort to this, and so wont to let it out of their control (or e.g. to let Transmeta see the source). So including IA-32 EL will require working through Non-Disclosure Agreements and around the need to only (mostly) have executable code to include in FreeBSD. Given all that, it seems like a very nice thing to have, (in the same way as 'Linux compatibility'), and a safeguard against the day Intel drop native IA-32 from Itaniums. Writing a translator from IA-32 to reasonably optimized IA-64 would be quite challenging. Porting Intel's IA-32 EL should not be too hard, given the opportunity. >I think we should allocate our spare resources to work on native >ia64 and native FreeBSD and make it a kick-ass server. If we get >bored after that, we can always take on the battle with i386 and >amd64 by adding compatibility layers and emulation fodder. > >Just my $0.02 If anyone has contacts at Intel perhaps they could try to find out if access to IA-32 EL for porting to FreeBSD would be possible. Tony