From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me X-Spam-Level: X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00 autolearn=ham autolearn_force=no version=3.4.4 X-Google-Thread: 103376,8de7eedad50552f1 X-Google-Attributes: gid103376,public X-Google-Language: ENGLISH,ASCII-7-bit Path: g2news1.google.com!news1.google.com!news.maxwell.syr.edu!stargate.gts.cz!news.freedom2surf.net!nntp-peering.plus.net!ptn-nntp-feeder01.plus.net!ptn-nntp-spool02.plus.net!ptn-nntp-reader01.plus.net!not-for-mail User-Agent: Microsoft-Entourage/10.1.6.040913.0 Date: Mon, 21 Mar 2005 15:00:25 +0000 Subject: Re: Ada bench From: "(see below)" Newsgroups: comp.lang.ada Message-ID: References: <87vf7n5njs.fsf@code-hal.de> <87u0n6mzas.fsf@code-hal.de> <2huslr9uto15$.nbw7z2uaceua.dlg@40tude.net> Mime-version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Organization: Customer of PlusNet plc (http://www.plus.net) NNTP-Posting-Host: e42355a2.ptn-nntp-reader01.plus.net X-Trace: DXC=AldZJQi5fgBCC3f?<3cV>Gigd3Y`7Rb;NYZmCHj47lfEeLPAa3J]X2Ifmc@[041FNFGfERDVJn48@[8GhaLQiNFL\:m3;ElMnkN?\1ONMBdjLMDKeZeglVEo@ X-Complaints-To: abuse@plus.net Xref: g2news1.google.com comp.lang.ada:9672 Date: 2005-03-21T15:00:25+00:00 List-Id: I said: > In that spirit I therefore looked at ackermann. > > At a first cut, on my machine, the C program takes about 8.9s. > (This seems very slow by comparison with the Shootout's hardware!) I've had a closer look at this and it seems to be a cache effect. For this test, the stack size increases as 2**N. For N>7 on my machine it swamped the 256K L2 cache. There will be an N that does the same on the Shootout machine, of course, so that higher values of N test only RAM bandwidth. -- Bill