From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Original-To: caml-list@yquem.inria.fr Delivered-To: caml-list@yquem.inria.fr Received: from concorde.inria.fr (concorde.inria.fr [192.93.2.39]) by yquem.inria.fr (Postfix) with ESMTP id 2F27EBB83 for ; Wed, 19 Apr 2006 10:24:54 +0200 (CEST) Received: from pauillac.inria.fr (pauillac.inria.fr [128.93.11.35]) by concorde.inria.fr (8.13.0/8.13.0) with ESMTP id k3J8Or1s019559 for ; Wed, 19 Apr 2006 10:24:53 +0200 Received: from concorde.inria.fr (concorde.inria.fr [192.93.2.39]) by pauillac.inria.fr (8.7.6/8.7.3) with ESMTP id KAA30662 for ; Wed, 19 Apr 2006 10:24:53 +0200 (MET DST) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by concorde.inria.fr (8.13.0/8.13.0) with ESMTP id k3J8OqXa019554 (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NO) for ; Wed, 19 Apr 2006 10:24:52 +0200 Received: from list by ciao.gmane.org with local (Exim 4.43) id 1FW7zP-00006l-U2 for caml-list@inria.fr; Wed, 19 Apr 2006 10:24:43 +0200 Received: from vpn-epfl-b071.epfl.ch ([128.178.84.171]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 19 Apr 2006 10:24:43 +0200 Received: from Michel.Schinz by vpn-epfl-b071.epfl.ch with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 19 Apr 2006 10:24:43 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: caml-list@inria.fr From: Michel Schinz Subject: Re: Performance of threaded interpreter on hyper-threaded CPU Date: Wed, 19 Apr 2006 10:24:21 +0200 Message-ID: References: <4444A46C.5000102@inria.fr> <44451158.8020004@inria.fr> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: vpn-epfl-b071.epfl.ch User-Agent: Gnus/5.11 (Gnus v5.11) Emacs/22.0.50 (darwin) Cancel-Lock: sha1:GmwkuBWmgXvhbFHqnPGSn5LpUYU= Sender: news X-Miltered: at concorde with ID 4445F3D5.001 by Joe's j-chkmail (http://j-chkmail.ensmp.fr)! X-Miltered: at concorde with ID 4445F3D4.000 by Joe's j-chkmail (http://j-chkmail.ensmp.fr)! X-Spam: no; 0.00; schinz:01 schinz:01 epfl:01 model:01 ocaml:01 speedup:01 ocaml:01 writes:01 michel:01 michel:01 consistent:02 suggestion:03 threaded:03 threaded:03 processors:04 X-Spam-Checker-Version: SpamAssassin 3.0.3 (2005-04-27) on yquem.inria.fr X-Spam-Level: X-Spam-Status: No, score=0.0 required=5.0 tests=none autolearn=disabled version=3.0.3 Xavier Leroy writes: [...] > The P4 microarchitecture is known for its weird performance model: > some code runs very fast, some similar code very slow. > In my experience, AMD processors as well as the Pentium-M are > much more consistent performance-wise. Ok, I wasn't aware of this. I don't have access to machines using AMD or Pentium-M processors, unfortunately. Anyway, the timing of the OCaml VM was just a side experiment for me: I wanted to see whether the speedup provided by threaded code in the OCaml VM was similar to the one it provides in a VM we develop for a course. Now that I've answered that question, I think I'll leave it at that. Thank you for your suggestion about VTUNE, I'll think about it if I ever need a detailed analysis tool. Michel.