From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 27467 invoked by alias); 29 Jul 2010 19:23:48 -0000 Received: (qmail 27456 invoked by uid 22791); 29 Jul 2010 19:23:47 -0000 X-SWARE-Spam-Status: No, hits=-2.0 required=5.0 tests=AWL,BAYES_00,T_RP_MATCHES_RCVD X-Spam-Check-By: sourceware.org Received: from smtp.gentoo.org (HELO smtp.gentoo.org) (140.211.166.183) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Thu, 29 Jul 2010 19:23:43 +0000 Received: from vapier.localnet (localhost [127.0.0.1]) by smtp.gentoo.org (Postfix) with ESMTP id 59B021B403F; Thu, 29 Jul 2010 19:23:41 +0000 (UTC) From: Mike Frysinger To: gdb-patches@sourceware.org Subject: Re: [rx sim] add decode cache Date: Thu, 29 Jul 2010 19:23:00 -0000 User-Agent: KMail/1.13.1 (Linux/2.6.34; KDE/4.4.5; x86_64; ; ) Cc: DJ Delorie References: <201007291841.o6TIfcgn017022@greed.delorie.com> In-Reply-To: <201007291841.o6TIfcgn017022@greed.delorie.com> MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1408193.RxhMRR2mMU"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <201007291523.07679.vapier@gentoo.org> X-IsSubscribed: yes Mailing-List: contact gdb-patches-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: gdb-patches-owner@sourceware.org X-SW-Source: 2010-07/txt/msg00550.txt.bz2 --nextPart1408193.RxhMRR2mMU Content-Type: Text/Plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-length: 1074 On Thursday, July 29, 2010 14:41:38 DJ Delorie wrote: > This patch is a performance improvement for the RX simulator. It > stores the opcode decode information from libopcodes so that any given > opcode need not be decoded more than once. This, and some > optimizations in the previous patch, results in the simulator taking > about 60% of the time it used to take to run a given program. On a > 3.2GHz desktop, I get an effective 12.5MHz simulated time with full > cycle stats, 14.5MHz with just cycle tracking, and 16MHz without cycle > tracking. if the rx sim is ultimately built on top of opc2c, and you're caching the=20 results of that, then shouldnt it be possible to keep the cache in a generi= c=20 place where everyone using opc2c would be able to leverage it ? also, on a semi-related note, i cant find any documentation or info in the= =20 archives on opc2c. it seems to have been quietly merged with the rx port a= nd=20 not really given any public info. looking at the rx opc file, it seems lik= e=20 it'd be useful to port some peeps over to it. -mike --nextPart1408193.RxhMRR2mMU Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part. Content-length: 836 -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.15 (GNU/Linux) iQIcBAABAgAGBQJMUdUbAAoJEEFjO5/oN/WB3hoP/R7a9FMzZtqZ7tZt9ALPUyiE 1ahnfNLPHdD6u7pREWUSxXmXbRfTd4s6EBhexTbdUWypEN4fmP5EpFHyV7ZWm9D/ nzfZfq6plt6W69opjK62wQbZ7QYpOCJn0DaLqWTodn60/2EVgYWg6xwfj9vKfTgi BX00JGrqRFUKTxOY6JaK4MDQXyd1a/VcjPkpmY2pzwzGyqxJd0vdp4x1+7zGNmYA Tr+mYJrCPv1Y4zem9i3mPkEXdaoTRVhPTdXgEWEpJFzAci4oGApKDBHdzPTIBlSm VsVAGd9OWz6M/rn629phgVCwbAs/tpLcZJJN7iqscceQZ3j4JHNf0V5DNhATijA1 X68HKeIO0dY6qzLvPHlAIWLExS8wSon0ig293XTbUrH3DBVloN5CJpomwwXzACVS aeTzInxvXIvdT3V2N1HPtecTaDhZyr/a5sjcInWYhsNV9iOeGYPf5u58zyoxLWFF SZZ5wg7lWsu2yJ46xntYCeIFNhbtl8ZEP9SdPfvkNXXa/QelK6I22dEt5yEAWrvX vQxlStNV1Fp9ZmVuCSBMRLX/3pNGBLOUHjowN533Q4GzxzZgOug2DSK0JIUdbNYC /m6Qg35ktiiotkcVLWSAcDnuBwmIy9L0HMEtUc1MM38nOAZlXWCh3arbXByvEZ7O 2CTcv1eCw8o6/WL7vYuL =AGiQ -----END PGP SIGNATURE----- --nextPart1408193.RxhMRR2mMU--