From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 13:39:16 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 133DB106564A for ; Mon, 12 Mar 2012 13:39:16 +0000 (UTC) (envelope-from nec556@retena.com) Received: from resmaa12.ono.com (smtp12.ono.com [62.42.230.20]) by mx1.freebsd.org (Postfix) with ESMTP id A06D28FC0A for ; Mon, 12 Mar 2012 13:39:15 +0000 (UTC) Received: from GogPortatil.retena.com (85.219.71.186) by resmaa12.ono.com (8.5.113) (authenticated as nec556@retena.com) id 4EFDA3B50106FD24 for freebsd-performance@freebsd.org; Mon, 12 Mar 2012 14:33:43 +0100 Message-ID: <4EFDA3B50106FD24@> (added by postmaster@resmaa12.ono.com) X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Mon, 12 Mar 2012 14:34:03 +0100 To: freebsd-performance@freebsd.org From: Eduardo Morras In-Reply-To: References: <4F59EB20.3060500@mail.zedat.fu-berlin.de> <4F5A3E54.2080909@mail.zedat.fu-berlin.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Antivirus: AVG for E-mail 2012.0.1913 [2114/4866] Subject: Re: OpenCL backend for LLVM X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 13:39:16 -0000 At 19:16 09/03/2012, Adrian Chadd wrote: >On 9 March 2012 09:31, O. Hartmann wrote: > > Well, having to pick up existing ideas and incarntions of those for > > Linux is always a pain in the ass, but necessary at the moment. The > > "experts" neglected long time the need for keeping FBSD on par with KMS > > stuff or all the other development done in that area. Hope "we" > > (FreeBSD) will get such a thing on a high performance base soon in > > FreeBSD. Or things change again and there is a real platform-independent > > standard, not necessaryly bound to Linux (which is not very realistic). > >When you say experts, you really mean "users who can code." Companies >wrote those funny graphics memory API things for Linux. They didn't >have a market for BSD. > >If you want a market for BSD you have to create it. :) Yes, it's "snake-selfbite-tail" circle, no market no development, no development no market. I know i'm part of the problem because i should had showed some development and examples of cuda apps on freebsd and made it more visible as hpc platfrom. >I've met some developers at nvidia. They all think the GPU offload >stuff is _in_ the FreeBSD nvidia driver. So someone needs to figure >out what's (still) missing from at least running workloads on FreeBSD. Sorry, i don't understand what you want to say here. Exactly, what do they need? development/alpha/beta/final testers? I can port cuda examples from linux to freebsd or develop new ones, but currently there's no SDK for freebsd, only the cuda runtime. Don't know what's the current status of the freebsd nvidia driver on cuda/opencl, before i used the recipe from here http://blogs.freebsdish.org/jhb/2010/07/20/using-cuda-with-the-native-freebsdamd64-nvidia-driver/ to run cuda apps on freebsd, it worked for 32bits app but the approach posted on second comment by Jacob Frelinger never worked for me. >Same deal goes for workload issues that people have. Keep posting >scheduler traces, keep doing the investigations and don't be afraid to >think up solutions. I'm going to try again, not only cuda but opencl too on a freebsd 8.2 with production data and last nvidia drivers to get (if works) real numbers. >The rest of us are mostly just users who hack on this stuff for fun. :-) Keep doing this great hacking and having fun :) >Adrian >(Who is hacking on this stuff (FreeBSD) for fun.) From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 15:31:54 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4DC04106566B for ; Mon, 12 Mar 2012 15:31:54 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id E60638FC16 for ; Mon, 12 Mar 2012 15:31:53 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1S77E0-00012B-Tb>; Mon, 12 Mar 2012 16:31:53 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1S77E0-00049o-Pn>; Mon, 12 Mar 2012 16:31:52 +0100 Message-ID: <4F5E16E2.5020001@mail.zedat.fu-berlin.de> Date: Mon, 12 Mar 2012 16:31:46 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120311 Thunderbird/10.0.2 MIME-Version: 1.0 To: Eduardo Morras References: <4F59EB20.3060500@mail.zedat.fu-berlin.de> <4F5A3E54.2080909@mail.zedat.fu-berlin.de> <4EFDA3B50106FD24@> (added by postmaster@resmaa12.ono.com) In-Reply-To: <4EFDA3B50106FD24@> (added by postmaster@resmaa12.ono.com) X-Enigmail-Version: 1.4 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig57F3C2AE3C198A43EC3A55CF" X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Mon, 12 Mar 2012 15:42:57 +0000 Cc: freebsd-performance@freebsd.org Subject: Re: OpenCL backend for LLVM X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 15:31:54 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig57F3C2AE3C198A43EC3A55CF Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 03/12/12 14:34, Eduardo Morras wrote: > At 19:16 09/03/2012, Adrian Chadd wrote: >> On 9 March 2012 09:31, O. Hartmann >> wrote: >> > Well, having to pick up existing ideas and incarntions of those for >> > Linux is always a pain in the ass, but necessary at the moment. The >> > "experts" neglected long time the need for keeping FBSD on par with = KMS >> > stuff or all the other development done in that area. Hope "we" >> > (FreeBSD) will get such a thing on a high performance base soon in >> > FreeBSD. Or things change again and there is a real >> platform-independent >> > standard, not necessaryly bound to Linux (which is not very realisti= c). >> >> When you say experts, you really mean "users who can code." Companies >> wrote those funny graphics memory API things for Linux. They didn't >> have a market for BSD. >> >> If you want a market for BSD you have to create it. :) >=20 > Yes, it's "snake-selfbite-tail" circle, no market no development, no > development no market. I know i'm part of the problem because i should > had showed some development and examples of cuda apps on freebsd and > made it more visible as hpc platfrom. This "circle" is typical and follows something well known I want to name here. And by the way, it is "stupid". FreeBSD has its roots based on BSD and BSD is born in an academic environment. Money/funding yes, but "no market". "Market" is a term of those which are incapable of managing the future - my personal opinion and this opinion does not imply that I'm reject capitalism (and this doesn't also imply I'm a socialst or communist!). I follow some thoughts of Hegel and Kant. Look at the Linux development the first days: done also by volunteers WITHOUT MARKET. A bit digging in the history, a bit looking who developed when a piece and even the blind will reveal that something has dramatically changed for FreeBSD. There is a lot of engineering today - but less scientific development. I'm still amazed by the power, elan and spirit Mathew Dillon is pushing his project even with a new filesystem while freeBSD incorporates and engineers an already existing filesystem. This is my try to explain what I mean, no complain about ZFS. I'm not a native English speaker. >=20 >> I've met some developers at nvidia. They all think the GPU offload >> stuff is _in_ the FreeBSD nvidia driver. So someone needs to figure >> out what's (still) missing from at least running workloads on FreeBSD.= >=20 > Sorry, i don't understand what you want to say here. Exactly, what do > they need? development/alpha/beta/final testers? I can port cuda > examples from linux to freebsd or develop new ones, but currently > there's no SDK for freebsd, only the cuda runtime. >=20 > Don't know what's the current status of the freebsd nvidia driver on > cuda/opencl, before i used the recipe from here > http://blogs.freebsdish.org/jhb/2010/07/20/using-cuda-with-the-native-f= reebsdamd64-nvidia-driver/ > to run cuda apps on freebsd, it worked for 32bits app but the approach > posted on second comment by Jacob Frelinger never worked for me. The receipt is outdated and it needs Linux stuff to work. And by the way, it didn't work for me ever, since the Linuxulator gets very fast ways out of sync of the development on Linux/CUDA. I started off a thread once because I felt enthusiastic about having the opportunity with LLVM and the native 64bit nVidia drivers, which are, definitely, the fundamental thing one need to run CUDA, or better, OpenCL= =2E then, a year ago, ther was a light/star at the horizon regarding HMPP. But it seems this was a bright supernova. CUDA is too narrow minded and nailed down to one architecture. We started over with OpenCL and feel really happy with our scientific stuff. But there are issues not dealt with properly when it comes to OpenCL kernels. They can not be "compiled" and being made binary without shooting the platform independend concept and this is for many companies a problem - but in most cases not for scientists. So far, FreeBSD does have the support of a native driver by nVidia. But there are no compatible FreeBSD VUDA libraries, there is no working "compiler" (nvcc does only run on Linux and expects still in conjunction with the CUDA SDK 4.1 a gcc < 4.6) and LLVM is far away from having a suitable PTX backend - a "sine conditio qua non" as I was said once. Some guy from Universit=E4t Saarbr=FCcken proposed in his final thesis so= em stuff, but it hasn't been picked up by BSD people. Linux folks did already. Well, there is also NO MARKET for the Linux people, but they obviously feel better with it ... I do not know. To stand my ground and make statements, I need to dig deeper into history and analyse the development over the past 15 years of FreeBSD. I have the strange feeling that since X11 get out of hand being a "open platform graphical solution", ruled by "Linux" nailed heads, the spirit of platform independency got a serious crack. When I was responsible for the IT in my former department, we ordered a lot of mathematical stuff from NAG. Well, I got everything I could dream about for FreeBSD, C/C++ and Fortran compilers and a lot of mathematical libraries. Look at the offerings today and try to go back in time (for those which might much younger than myself and couln't have the experience in this development by time-continuum constraints in this realm of the universe). >=20 >> Same deal goes for workload issues that people have. Keep posting >> scheduler traces, keep doing the investigations and don't be afraid to= >> think up solutions. >=20 > I'm going to try again, not only cuda but opencl too on a freebsd 8.2 > with production data and last nvidia drivers to get (if works) real > numbers. If you have success, let me know. I tried on FreeBSD 9.0 and failed. And for our modelling software, we desperately need 64bit. The mix in having 64bit (pseudo) architecture on FreeBSD and then a portion of the software driven by 32bit Linuxulator drives me nuts. One of the most disturbing facts is, that cross compiling is hard and nearly impossible. The Linuxulator is not supposed to replace Linux, it is a convenient way to fill gaps. But using OpenCL/CUDA is not a "gap", it is a whole realm on modern platforms and we (FreeBSD users) start getting dried out. And as far as I understand, the use of HPC is now bound to GPGPU capable operating systems and this seems to be an issue of how good the OS is on par with several new concepts like KMS. I might be wrong, mea culpa, if it is the case. On the other hand, if the conclusion of some of the readers would be "then leave FreeBSD and go to Linux", they might be shut up, please. This would be MARKET(?) - 1. And do this n times, as it happend in the past, then you end up with NULL at the end. >=20 >> The rest of us are mostly just users who hack on this stuff for fun. := -) >=20 > Keep doing this great hacking and having fun :) My capabilities are bound to different things at the moment, but it would be nice to start doing hacking into LLVM/OpenCL stuff just for fun. Even if there is no MARKET. Science has no market, otherwise Galois wouldn't came up with his theory in numbers, like Krull, Abels and other, having built the fundaments of the simple application cryptography out of the number's theorie. Those who can think in the categories of a sales man, they should do so. I appreciate their doing, they make "money". But they do not invent. >=20 >=20 >> Adrian >> (Who is hacking on this stuff (FreeBSD) for fun.) >=20 >=20 Sorry if I have pissed off anybody, but I feel frustrated about the short view of myself and other guys ... --------------enig57F3C2AE3C198A43EC3A55CF Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) iQEcBAEBAgAGBQJPXhboAAoJEOgBcD7A/5N8RxwIAKsqvzL4vGaM+/e2SIfLK09E l/w5j9wc3BVU20VZXbjAqyim59FKjMw2BaIleSIV4FwRbwvvH8dE97s1tEw74flW q9z+Ll/M19s2/z5oVAVtNef+/uqN/YBW3OM9mQCdOmSFmgxNhfEMX+JSUaZE8WJR gES97inU3awwSTbxMTTuVWlltyeO9Da604FC4n1MZKFuNs9FilextUJbs1thRLLS v69cv2j7Q7mP4eEKfyfTBoOZbouxwUR3d+BDplUxhAGS5Xgliyk2Us3DhVTLmwLZ S7Gb4nY8runUs2Yr0u7FtHzIQynSdAu+NXm7xqk8s8IXhjdkkgpoQcxa1F8d44M= =raLe -----END PGP SIGNATURE----- --------------enig57F3C2AE3C198A43EC3A55CF-- From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 19:26:31 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 205371065675 for ; Mon, 12 Mar 2012 19:26:31 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-pz0-f54.google.com (mail-pz0-f54.google.com [209.85.210.54]) by mx1.freebsd.org (Postfix) with ESMTP id E93B38FC17 for ; Mon, 12 Mar 2012 19:26:30 +0000 (UTC) Received: by dald2 with SMTP id d2so6236413dal.13 for ; Mon, 12 Mar 2012 12:26:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=lC9Az3/dKJU+OwSB7zKszxRsoh6z2t2fZG9hDPxvTl0=; b=NEqyxL7wzaBMRqUF8th1TU0UUxwAglzV9qmCd+OEHviHLuQ+ayajV2m+WozyrAGFRO G2umLKwQ4ZGssa+09QsFGQFC9SknqSnhRQsiaD0n3UKHi3I8dTqiYIq5ie+0jh9stPS3 kK4yo8F+gXto4uSLW3Cfn0J8MhK1tVaqFNm1wX8a2Eca3GFmJ3mH9Lg3QaM1qbxY/YwL NXyfrNtKtWKlbtfZrRxICLP5Ar98PzfcWsQmLFe5aqDKn6k8af0MaShf7E/vFX853B0W 2wE2mY/BPqmTFWSRR654NekJWHAhsiBAjdHaEZThP+dyKU9xde3NQ0e6evhkLhTwtzDi Z/iw== MIME-Version: 1.0 Received: by 10.68.191.168 with SMTP id gz8mr2480399pbc.37.1331580390749; Mon, 12 Mar 2012 12:26:30 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.143.33.5 with HTTP; Mon, 12 Mar 2012 12:26:30 -0700 (PDT) In-Reply-To: <4F5E16E2.5020001@mail.zedat.fu-berlin.de> References: <4F59EB20.3060500@mail.zedat.fu-berlin.de> <4F5A3E54.2080909@mail.zedat.fu-berlin.de> <4F5E16E2.5020001@mail.zedat.fu-berlin.de> Date: Mon, 12 Mar 2012 12:26:30 -0700 X-Google-Sender-Auth: anKCByT_RtG9NuUjSN5Ng3oA6PU Message-ID: From: Adrian Chadd To: "O. Hartmann" Content-Type: text/plain; charset=ISO-8859-1 Cc: freebsd-performance@freebsd.org, Eduardo Morras Subject: Re: OpenCL backend for LLVM X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 19:26:31 -0000 A lot of the linux work is pushed not by hobbyists, but by large companies with customers that request support. Don't mislead yourself by thinking all this Linux work gets done by a large number of unpaid volunteers. Go look at the contribution statistics sometime. If people would like to see CUDA support on FreeBSD then the best thing they can do is to write up the exact state of things, say what works and what doesn't, then make it REALLY easy to Nvidia to throw some resources at it. Having them start at "hm, someone wants BSD support, no customers, erk" is a no brainer - there's no justification, there's noone internally championing BSD, so the chances of it happening are slim. On the other hand, if there's a very specific set of things that need to occur, if you as an organisation will state you'll publicly shift to using Nvidia hardware + CUDA on FreeBSD if/when Nvidia moves, AND you engage an org like the Foundation to work with NVidia to make this happen.. yes, you may find it occurs. Right now if there's a way to run 32 bit CUDA workloads on BSD then please wrap it up in a port and make it an absolute no brainer to do. If someone can identify how to make 64 bit CUDA stuff work - eg, if it only worked on 8.2 but not 9.0, then also please post instructions, wrap it up in a port and make it work on 8.2, help the rest of the community try to identify what broke in 9.0, etc. Thanks, Adrian From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 19:33:20 2012 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D3AA7106564A; Mon, 12 Mar 2012 19:33:20 +0000 (UTC) (envelope-from fidaj@ukr.net) Received: from fsm2.ukr.net (fsm2.ukr.net [195.214.192.121]) by mx1.freebsd.org (Postfix) with ESMTP id 65CB48FC1F; Mon, 12 Mar 2012 19:33:17 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=fsm; h=Content-Transfer-Encoding:Content-Type:Mime-Version:References:In-Reply-To:Message-ID:Subject:Cc:To:From:Date; bh=zDVuTKmA0Z7Rxh3qT7/gz20Wp15PdNYZREiBfOQGD64=; b=Lhv+UbPko5b87maygyVi2VutLWfhyqtLblgSyxL7zuJvtCcFo2fyGWMZZDGWD+mvGpwxIs1KAuSn+8zMNihLPSzbeIHqLu07xJpr0nIKhX+IlQyUNxJHVZ196QI2JHW2i1DNVOOwoPoZjreu2wAZyexqu3IssYW2Vh4cDwwjdvE=; Received: from [178.137.138.140] (helo=nonamehost.) by fsm2.ukr.net with esmtpsa ID 1S7AzV-00045V-MB ; Mon, 12 Mar 2012 21:33:10 +0200 Date: Mon, 12 Mar 2012 21:33:07 +0200 From: Ivan Klymenko To: Alexander Motin Message-ID: <20120312213307.2be6bdf9@nonamehost.> In-Reply-To: <4F5E4B57.1050605@FreeBSD.org> References: <4F5E4B57.1050605@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 19:33:20 -0000 =D0=92 Mon, 12 Mar 2012 21:15:35 +0200 Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > Hi. >=20 > I'd like to note that recent r232793 change to cpufreq(4) in HEAD > opened simple access to the Intel Turbo Boost status/control. I've > found that at least two of my desktop systems (based Nehalem and > SandyBridge Core i7s) with enabled Intel Turbo Boost in BIOS it is > not use it by default, unless powerd is enabled. And before this > change it was difficult to detect/fix. >=20 > ACPI reports extra performance level with frequency 1MHz above the=20 > nominal to control Intel Turbo Boost operation. It is not a bug, but=20 > feature: > dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... > In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. >=20 > After boot with default settings I see: > dev.cpu.0.freq: 2933 > , that means Turbo Boost is disabled. >=20 > Enabling powerd or just adding to rc.conf > performance_cpu_freq=3D"HIGH" > enables Turbo Boost and adds extra 10-20% to the system performance. >=20 > Turbo Boost operation can be monitored in run-time via the PMC with=20 > command that prints number or really executed cycles per CPU core: > pmcstat -s unhalted-core-cycles -w 1 >=20 Thank you very much! performance_cpu_freq=3D"HIGH" and as this option must be combined with state of the processor C1 C2 C3? performance_cx_lowest=3D"XX" economy_cx_lowest=3D"XX" From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:06:07 2012 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 68BBD106566B; Mon, 12 Mar 2012 20:06:07 +0000 (UTC) (envelope-from fidaj@ukr.net) Received: from fsm1.ukr.net (fsm1.ukr.net [195.214.192.120]) by mx1.freebsd.org (Postfix) with ESMTP id 4227E8FC12; Mon, 12 Mar 2012 20:06:06 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=fsm; h=Content-Transfer-Encoding:Content-Type:Mime-Version:References:In-Reply-To:Message-ID:Subject:Cc:To:From:Date; bh=f34tZFo4oY4E9VttcncVSiJMOivSoAzKRc8ciMfigbA=; b=oMZPNg/b8XnEMAvxCp2/jg3OxV37DbxIFatBfFL+So4qK7/Kdvc9bcrsu/PbAtWCo4KraaVtLKqpvqhwxGlKcEjzNqNbmaec+X5Xl8AapTrfFx/27sCybpPPm9o5kQyvDSdaHtn5p1y7JxBQ05ZyBweWct9ueUNfAzdkI/7ON5g=; Received: from [178.137.138.140] (helo=nonamehost.) by fsm1.ukr.net with esmtpsa ID 1S7BVG-0001S5-UF ; Mon, 12 Mar 2012 22:05:59 +0200 Date: Mon, 12 Mar 2012 22:05:56 +0200 From: Ivan Klymenko To: Alexander Motin Message-ID: <20120312220556.53f27d63@nonamehost.> In-Reply-To: <4F5E54A9.5050301@FreeBSD.org> References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:06:07 -0000 =D0=92 Mon, 12 Mar 2012 21:55:21 +0200 Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > On 03/12/12 21:33, Ivan Klymenko wrote: > > =D0=92 Mon, 12 Mar 2012 21:15:35 +0200 > > Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > >> I'd like to note that recent r232793 change to cpufreq(4) in HEAD > >> opened simple access to the Intel Turbo Boost status/control. I've > >> found that at least two of my desktop systems (based Nehalem and > >> SandyBridge Core i7s) with enabled Intel Turbo Boost in BIOS it is > >> not use it by default, unless powerd is enabled. And before this > >> change it was difficult to detect/fix. > >> > >> ACPI reports extra performance level with frequency 1MHz above the > >> nominal to control Intel Turbo Boost operation. It is not a bug, > >> but feature: > >> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... > >> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. > >> > >> After boot with default settings I see: > >> dev.cpu.0.freq: 2933 > >> , that means Turbo Boost is disabled. > >> > >> Enabling powerd or just adding to rc.conf > >> performance_cpu_freq=3D"HIGH" > >> enables Turbo Boost and adds extra 10-20% to the system > >> performance. > >> > >> Turbo Boost operation can be monitored in run-time via the PMC with > >> command that prints number or really executed cycles per CPU core: > >> pmcstat -s unhalted-core-cycles -w 1 > >> > > > > Thank you very much! > > performance_cpu_freq=3D"HIGH" > > and as this option must be combined with state of the processor C1 > > C2 C3? > > performance_cx_lowest=3D"XX" > > economy_cx_lowest=3D"XX" >=20 > The more CPU cores on package are sleeping and the deeper they are=20 > sleeping, the bigger will be boost for remaining active cores. > Without using deeper C-states boost is usually quite small (about > 100-200MHz for desktop chips). Enabling C-states increases it in few > times. >=20 I have a Core i5 c Turbo Boost technology (enabled in BIOS) After the following: sysctl dev.cpu.0.freq_levels dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/222= 65 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/995= 6 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 performance_cpu_freq=3D"HIGH" >> /etc/rc.conf /etc/rc.d/powerd restart sysctl dev.cpu.0.freq_levels dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/222= 65 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/995= 6 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 CPU frequency does not rise above 2300 Mhz What am I doing wrong? From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:22:22 2012 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 340121065673; Mon, 12 Mar 2012 20:22:22 +0000 (UTC) (envelope-from fidaj@ukr.net) Received: from fsm1.ukr.net (fsm1.ukr.net [195.214.192.120]) by mx1.freebsd.org (Postfix) with ESMTP id C0A9B8FC18; Mon, 12 Mar 2012 20:22:21 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=fsm; h=Content-Transfer-Encoding:Content-Type:Mime-Version:References:In-Reply-To:Message-ID:Subject:Cc:To:From:Date; bh=STjskjgmorJ3cLbxfvFmkPLo/Ebh9hC+L90WNxH7ABQ=; b=RjmYr1uZP0rkGEEBYM81iOQWUKaKDtfBhOb0VDRpILc+MpTQh6343es7UqpmKWiRXvAg6RMEyIR8b87N8abAkmif3J0mIguYmeGwK6jragOaCnCIH4scun+J0UhCou8eW4ueoPL0Jx5ZVk6VYx3IgVCywjP1H4SKFhcmSu+aKWA=; Received: from [178.137.138.140] (helo=nonamehost.) by fsm1.ukr.net with esmtpsa ID 1S7Bl6-0005Gj-Sl ; Mon, 12 Mar 2012 22:22:21 +0200 Date: Mon, 12 Mar 2012 22:22:19 +0200 From: Ivan Klymenko To: Alexander Motin Message-ID: <20120312222219.15fe2101@nonamehost.> In-Reply-To: <4F5E5870.8000600@FreeBSD.org> References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> <4F5E5870.8000600@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:22:22 -0000 =D0=92 Mon, 12 Mar 2012 22:11:28 +0200 Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > On 03/12/12 22:05, Ivan Klymenko wrote: > > =D0=92 Mon, 12 Mar 2012 21:55:21 +0200 > > Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > > > >> On 03/12/12 21:33, Ivan Klymenko wrote: > >>> =D0=92 Mon, 12 Mar 2012 21:15:35 +0200 > >>> Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > >>>> I'd like to note that recent r232793 change to cpufreq(4) in HEAD > >>>> opened simple access to the Intel Turbo Boost status/control. > >>>> I've found that at least two of my desktop systems (based > >>>> Nehalem and SandyBridge Core i7s) with enabled Intel Turbo Boost > >>>> in BIOS it is not use it by default, unless powerd is enabled. > >>>> And before this change it was difficult to detect/fix. > >>>> > >>>> ACPI reports extra performance level with frequency 1MHz above > >>>> the nominal to control Intel Turbo Boost operation. It is not a > >>>> bug, but feature: > >>>> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... > >>>> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. > >>>> > >>>> After boot with default settings I see: > >>>> dev.cpu.0.freq: 2933 > >>>> , that means Turbo Boost is disabled. > >>>> > >>>> Enabling powerd or just adding to rc.conf > >>>> performance_cpu_freq=3D"HIGH" > >>>> enables Turbo Boost and adds extra 10-20% to the system > >>>> performance. > >>>> > >>>> Turbo Boost operation can be monitored in run-time via the PMC > >>>> with command that prints number or really executed cycles per > >>>> CPU core: pmcstat -s unhalted-core-cycles -w 1 > >>>> > >>> > >>> Thank you very much! > >>> performance_cpu_freq=3D"HIGH" > >>> and as this option must be combined with state of the processor C1 > >>> C2 C3? > >>> performance_cx_lowest=3D"XX" > >>> economy_cx_lowest=3D"XX" > >> > >> The more CPU cores on package are sleeping and the deeper they are > >> sleeping, the bigger will be boost for remaining active cores. > >> Without using deeper C-states boost is usually quite small (about > >> 100-200MHz for desktop chips). Enabling C-states increases it in > >> few times. > >> > > > > I have a Core i5 c Turbo Boost technology (enabled in BIOS) > > After the following: > > sysctl dev.cpu.0.freq_levels > > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > > 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > > 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > > 200/2489 100/1244 > > > > performance_cpu_freq=3D"HIGH">> /etc/rc.conf > > > > /etc/rc.d/powerd restart > > > > sysctl dev.cpu.0.freq_levels > > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > > 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > > 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > > 200/2489 100/1244 > > > > CPU frequency does not rise above 2300 Mhz > > > > What am I doing wrong? >=20 > performance_cpu_freq variable handled not by /etc/rc.d/powerd, but=20 > /etc/rc.d/power_profile. >=20 ok I remove and insert power supply unit connector - nothing has changed... sysctl dev.cpu.0.freq_levels dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/222= 65 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/995= 6 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:25:43 2012 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 61F46106567F; Mon, 12 Mar 2012 20:25:43 +0000 (UTC) (envelope-from fidaj@ukr.net) Received: from fsm2.ukr.net (fsm2.ukr.net [195.214.192.121]) by mx1.freebsd.org (Postfix) with ESMTP id DE0CC8FC0A; Mon, 12 Mar 2012 20:25:42 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=fsm; h=Content-Transfer-Encoding:Content-Type:Mime-Version:References:In-Reply-To:Message-ID:Subject:Cc:To:From:Date; bh=OpdjAu/lOaWcWtewy6VjcO0v7sr+hk2GONhYjYTIB8o=; b=fsYM0/BR4tNmiUNy5ehFBcUhUVocxbw7u6ERJDI0sfIF2K+rqsXiPvqjRV7bQWEtBabVfa0tLWY1w4+03RY4K0HwYTxZ5Mb8Ki5z8BWVR/ApmRW4bNgeouxaMBwnq3V7XjIONvq+DAFi2Zovzqj2CdFXreawzBa1fK5Xnnk4PVI=; Received: from [178.137.138.140] (helo=nonamehost.) by fsm2.ukr.net with esmtpsa ID 1S7BoM-000DpP-1P ; Mon, 12 Mar 2012 22:25:42 +0200 Date: Mon, 12 Mar 2012 22:25:40 +0200 From: Ivan Klymenko To: Alexander Motin Message-ID: <20120312222540.7171df10@nonamehost.> In-Reply-To: <4F5E5870.8000600@FreeBSD.org> References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> <4F5E5870.8000600@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:25:43 -0000 =D0=92 Mon, 12 Mar 2012 22:11:28 +0200 Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > On 03/12/12 22:05, Ivan Klymenko wrote: > > =D0=92 Mon, 12 Mar 2012 21:55:21 +0200 > > Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > > > >> On 03/12/12 21:33, Ivan Klymenko wrote: > >>> =D0=92 Mon, 12 Mar 2012 21:15:35 +0200 > >>> Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > >>>> I'd like to note that recent r232793 change to cpufreq(4) in HEAD > >>>> opened simple access to the Intel Turbo Boost status/control. > >>>> I've found that at least two of my desktop systems (based > >>>> Nehalem and SandyBridge Core i7s) with enabled Intel Turbo Boost > >>>> in BIOS it is not use it by default, unless powerd is enabled. > >>>> And before this change it was difficult to detect/fix. > >>>> > >>>> ACPI reports extra performance level with frequency 1MHz above > >>>> the nominal to control Intel Turbo Boost operation. It is not a > >>>> bug, but feature: > >>>> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... > >>>> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. > >>>> > >>>> After boot with default settings I see: > >>>> dev.cpu.0.freq: 2933 > >>>> , that means Turbo Boost is disabled. > >>>> > >>>> Enabling powerd or just adding to rc.conf > >>>> performance_cpu_freq=3D"HIGH" > >>>> enables Turbo Boost and adds extra 10-20% to the system > >>>> performance. > >>>> > >>>> Turbo Boost operation can be monitored in run-time via the PMC > >>>> with command that prints number or really executed cycles per > >>>> CPU core: pmcstat -s unhalted-core-cycles -w 1 > >>>> > >>> > >>> Thank you very much! > >>> performance_cpu_freq=3D"HIGH" > >>> and as this option must be combined with state of the processor C1 > >>> C2 C3? > >>> performance_cx_lowest=3D"XX" > >>> economy_cx_lowest=3D"XX" > >> > >> The more CPU cores on package are sleeping and the deeper they are > >> sleeping, the bigger will be boost for remaining active cores. > >> Without using deeper C-states boost is usually quite small (about > >> 100-200MHz for desktop chips). Enabling C-states increases it in > >> few times. > >> > > > > I have a Core i5 c Turbo Boost technology (enabled in BIOS) > > After the following: > > sysctl dev.cpu.0.freq_levels > > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > > 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > > 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > > 200/2489 100/1244 > > > > performance_cpu_freq=3D"HIGH">> /etc/rc.conf > > > > /etc/rc.d/powerd restart > > > > sysctl dev.cpu.0.freq_levels > > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > > 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > > 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > > 200/2489 100/1244 > > > > CPU frequency does not rise above 2300 Mhz > > > > What am I doing wrong? >=20 > performance_cpu_freq variable handled not by /etc/rc.d/powerd, but=20 > /etc/rc.d/power_profile. >=20 hm :( hw.acpi.acline: 1 no change status :( apparently something is broken with ACPI From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:51:38 2012 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id A6457106566C; Mon, 12 Mar 2012 20:51:38 +0000 (UTC) (envelope-from fidaj@ukr.net) Received: from fsm2.ukr.net (fsm2.ukr.net [195.214.192.121]) by mx1.freebsd.org (Postfix) with ESMTP id 3A7E18FC1B; Mon, 12 Mar 2012 20:51:38 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=fsm; h=Content-Transfer-Encoding:Content-Type:Mime-Version:References:In-Reply-To:Message-ID:Subject:Cc:From:Date; bh=J2iVR+Le9ZihntSnjOf5xoMK8G2i2WPwMRKVj7NaPns=; b=Qxp4IH4Yd/Kgk6NcDKu0Rc/OOizvB0sCD3+oP6jx9PdMURL3/4bExT0Qx8hJurNU3a1GQcQSU9OYC8n69I2sCm2XRCVSQiAGS6yia7ceRF2iYrdu53tCth2a6dpup3o3kd+2TLZ+tBon0Ip2dSFdeMtefXQgOeoypGHHkQBbbOI=; Received: from [178.137.138.140] (helo=nonamehost.) by fsm2.ukr.net with esmtpsa ID 1S7CDR-000IE5-61 ; Mon, 12 Mar 2012 22:51:37 +0200 Date: Mon, 12 Mar 2012 22:51:35 +0200 From: Ivan Klymenko Message-ID: <20120312225135.7d7b6780@nonamehost.> In-Reply-To: <4F5E5EB8.5080506@FreeBSD.org> References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> <4F5E5870.8000600@FreeBSD.org> <4f5e5b28.894a440a.1955.ffff81e8SMTPIN_ADDED@mx.google.com> <4F5E5EB8.5080506@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:51:38 -0000 =D0=92 Mon, 12 Mar 2012 22:38:16 +0200 Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > On 03/12/12 22:22, Ivan Klymenko wrote: > > =D0=92 Mon, 12 Mar 2012 22:11:28 +0200 > > Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > > > >> On 03/12/12 22:05, Ivan Klymenko wrote: > >>> =D0=92 Mon, 12 Mar 2012 21:55:21 +0200 > >>> Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > >>> > >>>> On 03/12/12 21:33, Ivan Klymenko wrote: > >>>>> =D0=92 Mon, 12 Mar 2012 21:15:35 +0200 > >>>>> Alexander Motin =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > >>>>>> I'd like to note that recent r232793 change to cpufreq(4) in > >>>>>> HEAD opened simple access to the Intel Turbo Boost > >>>>>> status/control. I've found that at least two of my desktop > >>>>>> systems (based Nehalem and SandyBridge Core i7s) with enabled > >>>>>> Intel Turbo Boost in BIOS it is not use it by default, unless > >>>>>> powerd is enabled. And before this change it was difficult to > >>>>>> detect/fix. > >>>>>> > >>>>>> ACPI reports extra performance level with frequency 1MHz above > >>>>>> the nominal to control Intel Turbo Boost operation. It is not a > >>>>>> bug, but feature: > >>>>>> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... > >>>>>> In this case value 2933 means 2.93GHz, but 2934 means > >>>>>> 3.2-3.6GHz. > >>>>>> > >>>>>> After boot with default settings I see: > >>>>>> dev.cpu.0.freq: 2933 > >>>>>> , that means Turbo Boost is disabled. > >>>>>> > >>>>>> Enabling powerd or just adding to rc.conf > >>>>>> performance_cpu_freq=3D"HIGH" > >>>>>> enables Turbo Boost and adds extra 10-20% to the system > >>>>>> performance. > >>>>>> > >>>>>> Turbo Boost operation can be monitored in run-time via the PMC > >>>>>> with command that prints number or really executed cycles per > >>>>>> CPU core: pmcstat -s unhalted-core-cycles -w 1 > >>>>>> > >>>>> > >>>>> Thank you very much! > >>>>> performance_cpu_freq=3D"HIGH" > >>>>> and as this option must be combined with state of the processor > >>>>> C1 C2 C3? > >>>>> performance_cx_lowest=3D"XX" > >>>>> economy_cx_lowest=3D"XX" > >>>> > >>>> The more CPU cores on package are sleeping and the deeper they > >>>> are sleeping, the bigger will be boost for remaining active > >>>> cores. Without using deeper C-states boost is usually quite > >>>> small (about 100-200MHz for desktop chips). Enabling C-states > >>>> increases it in few times. > >>>> > >>> > >>> I have a Core i5 c Turbo Boost technology (enabled in BIOS) > >>> After the following: > >>> sysctl dev.cpu.0.freq_levels > >>> dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > >>> 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > >>> 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > >>> 200/2489 100/1244 > >>> > >>> performance_cpu_freq=3D"HIGH">> /etc/rc.conf > >>> > >>> /etc/rc.d/powerd restart > >>> > >>> sysctl dev.cpu.0.freq_levels > >>> dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > >>> 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > >>> 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > >>> 200/2489 100/1244 > >>> > >>> CPU frequency does not rise above 2300 Mhz > >>> > >>> What am I doing wrong? > >> > >> performance_cpu_freq variable handled not by /etc/rc.d/powerd, but > >> /etc/rc.d/power_profile. > >> > > > > ok > > > > I remove and insert power supply unit connector - nothing has > > changed... > > > > sysctl dev.cpu.0.freq_levels > > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 > > 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 > > 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 > > 200/2489 100/1244 >=20 > What changes do you expect to see in dev.cpu.0.freq_levels? This list > is static. It is dev.cpu.0.freq that may change and that is where=20 > difference between 2301 and 2300 should now have effect. >=20 I expected that I should be a value greater than 35000 when 2301... it is the same as the next 2300... From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 21:50:26 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id ECF691065670 for ; Mon, 12 Mar 2012 21:50:26 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id A1F358FC08 for ; Mon, 12 Mar 2012 21:50:26 +0000 (UTC) Received: from outgoing.leidinger.net (p4FC423CD.dip.t-dialin.net [79.196.35.205]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id A45FD84445C; Mon, 12 Mar 2012 22:50:11 +0100 (CET) Received: from unknown (IO.Leidinger.net [192.168.1.12]) by outgoing.leidinger.net (Postfix) with ESMTPS id F0835221A; Mon, 12 Mar 2012 22:50:08 +0100 (CET) Date: Mon, 12 Mar 2012 22:50:07 +0100 From: Alexander Leidinger To: "O. Hartmann" Message-ID: <20120312225007.000038ba@unknown> In-Reply-To: <4F5E16E2.5020001@mail.zedat.fu-berlin.de> References: <4F59EB20.3060500@mail.zedat.fu-berlin.de> <4F5A3E54.2080909@mail.zedat.fu-berlin.de> <4EFDA3B50106FD24@> <4F5E16E2.5020001@mail.zedat.fu-berlin.de> X-Mailer: Claws Mail 3.7.10cvs42 (GTK+ 2.16.6; i586-pc-mingw32msvc) Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: A45FD84445C.A0E97 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=-0.955, required 6, autolearn=disabled, ALL_TRUSTED -1.00, AWL 0.06, T_RP_MATCHES_RCVD -0.01) X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1332193813.31796@hHjU4OzMxDOZPCFRT6rYnw X-EBL-Spam-Status: No Cc: freebsd-performance@freebsd.org, Eduardo Morras Subject: Re: OpenCL backend for LLVM X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 21:50:27 -0000 On Mon, 12 Mar 2012 16:31:46 +0100 "O. Hartmann" wrote: > So far, FreeBSD does have the support of a native driver by nVidia. > But there are no compatible FreeBSD VUDA libraries, there is no > working "compiler" (nvcc does only run on Linux and expects still in > conjunction with the CUDA SDK 4.1 a gcc < 4.6) and LLVM is far away > from having a suitable PTX backend - a "sine conditio qua non" as I > was said once. I (with the help of some others after I had already something to show) once "convinced" the Linux version of the Intel C/C++ compiler to generate FreeBSD native binaries. I did this because I thought it could be possible and had interest to give it a try. No business behind, no market to satisfy. I don't know the specifics of this nvcc, but with a little bit of interest and motivation, maybe something similar could be done. > Some guy from Universit=E4t Saarbr=FCcken proposed in his final thesis > soem stuff, but it hasn't been picked up by BSD people. Linux folks I don't understand what you talk about here, but links to his final thesis may be much more interesting for some people than to not even know the title of this final thesis. Bye, Alexander. --=20 http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID =3D B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID =3D 72077137 From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 19:15:41 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 41F99106564A; Mon, 12 Mar 2012 19:15:41 +0000 (UTC) (envelope-from mavbsd@gmail.com) Received: from mail-bk0-f54.google.com (mail-bk0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id 94C7E8FC0C; Mon, 12 Mar 2012 19:15:40 +0000 (UTC) Received: by bkcjc3 with SMTP id jc3so4029250bkc.13 for ; Mon, 12 Mar 2012 12:15:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:message-id:date:from:user-agent:mime-version:to:subject :content-type:content-transfer-encoding; bh=DPnVeo72CVNO9h/ofo6oWjVDM69/REysPmBSqzAA/uI=; b=y2H+TmTekSKmA+9c3BGu5cvsQ83Yl2DSja/Ls7WFh78UUC0faantVWdKsD0Bg49qOV CXTdUcsKLu91qms7ITQbx/NHegWuI6YKe5gKn0FtibKGnuTgMWd45COK+ieQCV0ilZ0I HdaKoai2//9YTKYDn2RPY7pM+HKvOKL/dXbT8o5bhms6xtFcRMl+Kn3nwMNSJGdyGQeC bomxAemQ5JuH7yMIC3ltMOlUr7fggzNV6Z3NGFm44gOSCLVgDoo+vH+40LyKriuBMznP ym1WUEOf5f7mDJzXuqUvSUMUCC7ndeoUglb1RGcs9tlonawiKFT+zQHn4QvcDbH07jxq fB/A== Received: by 10.204.9.205 with SMTP id m13mr5148300bkm.68.1331579739574; Mon, 12 Mar 2012 12:15:39 -0700 (PDT) Received: from mavbook2.mavhome.dp.ua (pc.mavhome.dp.ua. [212.86.226.226]) by mx.google.com with ESMTPS id h16sm27293854bkk.12.2012.03.12.12.15.36 (version=SSLv3 cipher=OTHER); Mon, 12 Mar 2012 12:15:37 -0700 (PDT) Sender: Alexander Motin Message-ID: <4F5E4B57.1050605@FreeBSD.org> Date: Mon, 12 Mar 2012 21:15:35 +0200 From: Alexander Motin User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120226 Thunderbird/10.0.2 MIME-Version: 1.0 To: FreeBSD current , freebsd-performance@FreeBSD.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Mon, 12 Mar 2012 23:19:41 +0000 Cc: Subject: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 19:15:41 -0000 Hi. I'd like to note that recent r232793 change to cpufreq(4) in HEAD opened simple access to the Intel Turbo Boost status/control. I've found that at least two of my desktop systems (based Nehalem and SandyBridge Core i7s) with enabled Intel Turbo Boost in BIOS it is not use it by default, unless powerd is enabled. And before this change it was difficult to detect/fix. ACPI reports extra performance level with frequency 1MHz above the nominal to control Intel Turbo Boost operation. It is not a bug, but feature: dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. After boot with default settings I see: dev.cpu.0.freq: 2933 , that means Turbo Boost is disabled. Enabling powerd or just adding to rc.conf performance_cpu_freq="HIGH" enables Turbo Boost and adds extra 10-20% to the system performance. Turbo Boost operation can be monitored in run-time via the PMC with command that prints number or really executed cycles per CPU core: pmcstat -s unhalted-core-cycles -w 1 -- Alexander Motin From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 19:55:31 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 72081106564A; Mon, 12 Mar 2012 19:55:31 +0000 (UTC) (envelope-from mavbsd@gmail.com) Received: from mail-wi0-f178.google.com (mail-wi0-f178.google.com [209.85.212.178]) by mx1.freebsd.org (Postfix) with ESMTP id CAD1F8FC15; Mon, 12 Mar 2012 19:55:30 +0000 (UTC) Received: by wibhq7 with SMTP id hq7so3495242wib.13 for ; Mon, 12 Mar 2012 12:55:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=WMF10BYiXm85ixEabMkAJoxc/0s3cccjzBtwhKOxd+I=; b=vN9z0HuX6bWcz54oCAkW3vI9+t4NjPmqh71gWZZpppGQ8nsEopzPoh9Vdiuy1O+nPl pLMov6zTRsNb7gzLUcbe0BDT7ZNPXI0OQl1b2YPtIrWOC/uEcyc3IgLeEioEo+imsKwd VnOjy40FIFJaxDu1r7M7/77zyiDE8z6o7tvdK6Q3em8LqMAM7mQ9mayqewosv4oBqFBp edhZqxUcO9VTddPV0E8Qaguu8PGNwwLLqFxdqB2fQ2jfWni/4WXTHvDVPpTtnrxeuiVs wBVTqnvmrGG25WnoNXWzktiVpscC+AopiBoq3GksW42NE2Yqm8XCcYrQdYLWJ2hJcuuW axDQ== Received: by 10.180.102.231 with SMTP id fr7mr818723wib.10.1331582124362; Mon, 12 Mar 2012 12:55:24 -0700 (PDT) Received: from mavbook2.mavhome.dp.ua (pc.mavhome.dp.ua. [212.86.226.226]) by mx.google.com with ESMTPS id t20sm62310278wiv.0.2012.03.12.12.55.22 (version=SSLv3 cipher=OTHER); Mon, 12 Mar 2012 12:55:23 -0700 (PDT) Sender: Alexander Motin Message-ID: <4F5E54A9.5050301@FreeBSD.org> Date: Mon, 12 Mar 2012 21:55:21 +0200 From: Alexander Motin User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120226 Thunderbird/10.0.2 MIME-Version: 1.0 To: Ivan Klymenko References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> In-Reply-To: <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Mon, 12 Mar 2012 23:19:52 +0000 Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 19:55:31 -0000 On 03/12/12 21:33, Ivan Klymenko wrote: > В Mon, 12 Mar 2012 21:15:35 +0200 > Alexander Motin пишет: >> I'd like to note that recent r232793 change to cpufreq(4) in HEAD >> opened simple access to the Intel Turbo Boost status/control. I've >> found that at least two of my desktop systems (based Nehalem and >> SandyBridge Core i7s) with enabled Intel Turbo Boost in BIOS it is >> not use it by default, unless powerd is enabled. And before this >> change it was difficult to detect/fix. >> >> ACPI reports extra performance level with frequency 1MHz above the >> nominal to control Intel Turbo Boost operation. It is not a bug, but >> feature: >> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... >> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. >> >> After boot with default settings I see: >> dev.cpu.0.freq: 2933 >> , that means Turbo Boost is disabled. >> >> Enabling powerd or just adding to rc.conf >> performance_cpu_freq="HIGH" >> enables Turbo Boost and adds extra 10-20% to the system performance. >> >> Turbo Boost operation can be monitored in run-time via the PMC with >> command that prints number or really executed cycles per CPU core: >> pmcstat -s unhalted-core-cycles -w 1 >> > > Thank you very much! > performance_cpu_freq="HIGH" > and as this option must be combined with state of the processor C1 C2 > C3? > performance_cx_lowest="XX" > economy_cx_lowest="XX" The more CPU cores on package are sleeping and the deeper they are sleeping, the bigger will be boost for remaining active cores. Without using deeper C-states boost is usually quite small (about 100-200MHz for desktop chips). Enabling C-states increases it in few times. -- Alexander Motin From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:11:33 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D7A1B106566C; Mon, 12 Mar 2012 20:11:33 +0000 (UTC) (envelope-from mavbsd@gmail.com) Received: from mail-bk0-f54.google.com (mail-bk0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id 2B6038FC1A; Mon, 12 Mar 2012 20:11:32 +0000 (UTC) Received: by bkcjc3 with SMTP id jc3so4079403bkc.13 for ; Mon, 12 Mar 2012 13:11:32 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=5CAcEUGayDR9Ol9hHBoJZHM+wSjPH0FZynInB2I92j0=; b=dFOgbxjRF+0/SrnokGF56jPROJ35Wn7m9KEzqvCSyOpMdxSDFYVbEvpPmS+f1DwBPg HyKiYK1ChPqlVkqSvtlmY2XsEnn5HjpfRBdeyCcEYL1dmDkIig9CWPHekM+r12EQTplI r/dkWS4JbM0/ZnrBLbuxBZKJeZU1WNDuIMCO2FKvMz+K4Ow8SC2w8FvU2D9L7ybpRhgl Us3AXln2mpIhTmDgH0r1JYY5jUwPV6Zcp9LLx+ZGRYajx9wAIERbcTn6SCpvkCVlT6DN WBH1MLnN7mTNuMlq9IgyLjnOVCajQl7AIEpYinsckUolGINwGCLZHbtOARWGgBlDsF8q 7tYA== Received: by 10.204.173.11 with SMTP id n11mr5333724bkz.120.1331583092001; Mon, 12 Mar 2012 13:11:32 -0700 (PDT) Received: from mavbook2.mavhome.dp.ua (pc.mavhome.dp.ua. [212.86.226.226]) by mx.google.com with ESMTPS id o7sm27518056bkw.16.2012.03.12.13.11.30 (version=SSLv3 cipher=OTHER); Mon, 12 Mar 2012 13:11:31 -0700 (PDT) Sender: Alexander Motin Message-ID: <4F5E5870.8000600@FreeBSD.org> Date: Mon, 12 Mar 2012 22:11:28 +0200 From: Alexander Motin User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120226 Thunderbird/10.0.2 MIME-Version: 1.0 To: Ivan Klymenko References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> In-Reply-To: <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Tue, 13 Mar 2012 01:01:00 +0000 Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:11:34 -0000 On 03/12/12 22:05, Ivan Klymenko wrote: > В Mon, 12 Mar 2012 21:55:21 +0200 > Alexander Motin пишет: > >> On 03/12/12 21:33, Ivan Klymenko wrote: >>> В Mon, 12 Mar 2012 21:15:35 +0200 >>> Alexander Motin пишет: >>>> I'd like to note that recent r232793 change to cpufreq(4) in HEAD >>>> opened simple access to the Intel Turbo Boost status/control. I've >>>> found that at least two of my desktop systems (based Nehalem and >>>> SandyBridge Core i7s) with enabled Intel Turbo Boost in BIOS it is >>>> not use it by default, unless powerd is enabled. And before this >>>> change it was difficult to detect/fix. >>>> >>>> ACPI reports extra performance level with frequency 1MHz above the >>>> nominal to control Intel Turbo Boost operation. It is not a bug, >>>> but feature: >>>> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... >>>> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. >>>> >>>> After boot with default settings I see: >>>> dev.cpu.0.freq: 2933 >>>> , that means Turbo Boost is disabled. >>>> >>>> Enabling powerd or just adding to rc.conf >>>> performance_cpu_freq="HIGH" >>>> enables Turbo Boost and adds extra 10-20% to the system >>>> performance. >>>> >>>> Turbo Boost operation can be monitored in run-time via the PMC with >>>> command that prints number or really executed cycles per CPU core: >>>> pmcstat -s unhalted-core-cycles -w 1 >>>> >>> >>> Thank you very much! >>> performance_cpu_freq="HIGH" >>> and as this option must be combined with state of the processor C1 >>> C2 C3? >>> performance_cx_lowest="XX" >>> economy_cx_lowest="XX" >> >> The more CPU cores on package are sleeping and the deeper they are >> sleeping, the bigger will be boost for remaining active cores. >> Without using deeper C-states boost is usually quite small (about >> 100-200MHz for desktop chips). Enabling C-states increases it in few >> times. >> > > I have a Core i5 c Turbo Boost technology (enabled in BIOS) > After the following: > sysctl dev.cpu.0.freq_levels > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 > > performance_cpu_freq="HIGH">> /etc/rc.conf > > /etc/rc.d/powerd restart > > sysctl dev.cpu.0.freq_levels > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 > > CPU frequency does not rise above 2300 Mhz > > What am I doing wrong? performance_cpu_freq variable handled not by /etc/rc.d/powerd, but /etc/rc.d/power_profile. -- Alexander Motin From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:38:21 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 8C9061065672; Mon, 12 Mar 2012 20:38:21 +0000 (UTC) (envelope-from mavbsd@gmail.com) Received: from mail-bk0-f54.google.com (mail-bk0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id DDCBE8FC19; Mon, 12 Mar 2012 20:38:20 +0000 (UTC) Received: by bkcjc3 with SMTP id jc3so4102579bkc.13 for ; Mon, 12 Mar 2012 13:38:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=xdkM8V/ND5uAEBDI3stoEwo6/f64rYWJsZ98Q0qYnhs=; b=uIuM8IbhylE+fYY3ND/AIZ7s/zqCGtp0G6IQMCLbwiXaUi/xRTd/pjp6y6xGXUda4R uLUlDFvVViXTuo1RO3b5t4hSf87TMkc9qSlc35XFUbL5wOvJciz1Lg82Dm/H06VzAOz4 EwQQ/TcTfb6n6d7031yI4GH7G56stVaiCrXJ1b9DaSqsf7P7VqaN5SkSjfJy9Hznxg2c obP/pqTyuJSryGc7lchJAqjFgTn5NhypUVCk5JML+IlHdnbEkrCWDTbuR7ZHDq6RK4vl evEpvBA5qDZh0W7WGNDkqLp/IsRrXAloGGPBcpuZyCR05IRXSdo7ICjS1lffNw4dqlHK Lotg== Received: by 10.204.130.150 with SMTP id t22mr5196163bks.1.1331584699654; Mon, 12 Mar 2012 13:38:19 -0700 (PDT) Received: from mavbook2.mavhome.dp.ua (pc.mavhome.dp.ua. [212.86.226.226]) by mx.google.com with ESMTPS id jd17sm27678416bkb.4.2012.03.12.13.38.17 (version=SSLv3 cipher=OTHER); Mon, 12 Mar 2012 13:38:18 -0700 (PDT) Sender: Alexander Motin Message-ID: <4F5E5EB8.5080506@FreeBSD.org> Date: Mon, 12 Mar 2012 22:38:16 +0200 From: Alexander Motin User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120226 Thunderbird/10.0.2 MIME-Version: 1.0 To: Ivan Klymenko References: <4F5E4B57.1050605@FreeBSD.org> <4f5e4f82.41972a0a.0e49.2cfdSMTPIN_ADDED@mx.google.com> <4F5E54A9.5050301@FreeBSD.org> <4f5e5730.aa4a440a.4367.ffffa591SMTPIN_ADDED@mx.google.com> <4F5E5870.8000600@FreeBSD.org> <4f5e5b28.894a440a.1955.ffff81e8SMTPIN_ADDED@mx.google.com> In-Reply-To: <4f5e5b28.894a440a.1955.ffff81e8SMTPIN_ADDED@mx.google.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Tue, 13 Mar 2012 01:02:13 +0000 Cc: freebsd-performance@FreeBSD.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:38:21 -0000 On 03/12/12 22:22, Ivan Klymenko wrote: > В Mon, 12 Mar 2012 22:11:28 +0200 > Alexander Motin пишет: > >> On 03/12/12 22:05, Ivan Klymenko wrote: >>> В Mon, 12 Mar 2012 21:55:21 +0200 >>> Alexander Motin пишет: >>> >>>> On 03/12/12 21:33, Ivan Klymenko wrote: >>>>> В Mon, 12 Mar 2012 21:15:35 +0200 >>>>> Alexander Motin пишет: >>>>>> I'd like to note that recent r232793 change to cpufreq(4) in HEAD >>>>>> opened simple access to the Intel Turbo Boost status/control. >>>>>> I've found that at least two of my desktop systems (based >>>>>> Nehalem and SandyBridge Core i7s) with enabled Intel Turbo Boost >>>>>> in BIOS it is not use it by default, unless powerd is enabled. >>>>>> And before this change it was difficult to detect/fix. >>>>>> >>>>>> ACPI reports extra performance level with frequency 1MHz above >>>>>> the nominal to control Intel Turbo Boost operation. It is not a >>>>>> bug, but feature: >>>>>> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... >>>>>> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. >>>>>> >>>>>> After boot with default settings I see: >>>>>> dev.cpu.0.freq: 2933 >>>>>> , that means Turbo Boost is disabled. >>>>>> >>>>>> Enabling powerd or just adding to rc.conf >>>>>> performance_cpu_freq="HIGH" >>>>>> enables Turbo Boost and adds extra 10-20% to the system >>>>>> performance. >>>>>> >>>>>> Turbo Boost operation can be monitored in run-time via the PMC >>>>>> with command that prints number or really executed cycles per >>>>>> CPU core: pmcstat -s unhalted-core-cycles -w 1 >>>>>> >>>>> >>>>> Thank you very much! >>>>> performance_cpu_freq="HIGH" >>>>> and as this option must be combined with state of the processor C1 >>>>> C2 C3? >>>>> performance_cx_lowest="XX" >>>>> economy_cx_lowest="XX" >>>> >>>> The more CPU cores on package are sleeping and the deeper they are >>>> sleeping, the bigger will be boost for remaining active cores. >>>> Without using deeper C-states boost is usually quite small (about >>>> 100-200MHz for desktop chips). Enabling C-states increases it in >>>> few times. >>>> >>> >>> I have a Core i5 c Turbo Boost technology (enabled in BIOS) >>> After the following: >>> sysctl dev.cpu.0.freq_levels >>> dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 >>> 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 >>> 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 >>> 200/2489 100/1244 >>> >>> performance_cpu_freq="HIGH">> /etc/rc.conf >>> >>> /etc/rc.d/powerd restart >>> >>> sysctl dev.cpu.0.freq_levels >>> dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 >>> 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 >>> 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 >>> 200/2489 100/1244 >>> >>> CPU frequency does not rise above 2300 Mhz >>> >>> What am I doing wrong? >> >> performance_cpu_freq variable handled not by /etc/rc.d/powerd, but >> /etc/rc.d/power_profile. >> > > ok > > I remove and insert power supply unit connector - nothing has changed... > > sysctl dev.cpu.0.freq_levels > dev.cpu.0.freq_levels: 2301/35000 2300/35000 2000/29079 1800/25766 1600/22265 1400/18904 1225/16541 1200/15996 1050/13996 1000/12907 875/11293 800/9956 700/8711 600/7467 500/6222 400/4978 300/3733 200/2489 100/1244 What changes do you expect to see in dev.cpu.0.freq_levels? This list is static. It is dev.cpu.0.freq that may change and that is where difference between 2301 and 2300 should now have effect. -- Alexander Motin From owner-freebsd-performance@FreeBSD.ORG Mon Mar 12 20:52:15 2012 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6D78B106564A; Mon, 12 Mar 2012 20:52:15 +0000 (UTC) (envelope-from mavbsd@gmail.com) Received: from mail-bk0-f54.google.com (mail-bk0-f54.google.com [209.85.214.54]) by mx1.freebsd.org (Postfix) with ESMTP id BE01F8FC20; Mon, 12 Mar 2012 20:52:14 +0000 (UTC) Received: by bkcjc3 with SMTP id jc3so4114176bkc.13 for ; Mon, 12 Mar 2012 13:52:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=G8uMeOWQPUyE1yCOmjIaBCA4CSqW14hWDV4ZHlI6aHs=; b=XBG+Qmf8W04pHe5MUXOqO8+LS62dJV28rVYelUB9bd6H/c7lhCAweQ1VVcecLmi68R z/ircW1NrAVh8naRNStxlq3NkE+yQgZpp2L4gDFSB4njgj8/viSCu5V55PdEHpPG0wdB bBizCFJ+SWn8aV6yL7VxsKps96KYJ2q4FddeaWUhbT4yg1NpKKrGDQH8aQ82PhImfnLU f3wMJre2lbY5s3nS24ACs83bGP4eUFCKc13QBZ9pYrDaLAKoGJeEsVMRCtKuXe080sY8 k+Rjo5DroHIGnFh6/ABP9D6hgAXnnLzizYx7Ypns8bGHksoU/Wbp40NQOSw+kVbD+hQK nJ9w== Received: by 10.204.152.88 with SMTP id f24mr1095559bkw.121.1331585533685; Mon, 12 Mar 2012 13:52:13 -0700 (PDT) Received: from mavbook2.mavhome.dp.ua (pc.mavhome.dp.ua. [212.86.226.226]) by mx.google.com with ESMTPS id f5sm27713986bke.9.2012.03.12.13.52.11 (version=SSLv3 cipher=OTHER); Mon, 12 Mar 2012 13:52:12 -0700 (PDT) Sender: Alexander Motin Message-ID: <4F5E61FA.5080306@FreeBSD.org> Date: Mon, 12 Mar 2012 22:52:10 +0200 From: Alexander Motin User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:10.0.2) Gecko/20120226 Thunderbird/10.0.2 MIME-Version: 1.0 To: Ian Lepore References: <4F5E4B57.1050605@FreeBSD.org> <1331585159.1084.3.camel@revolution.hippie.lan> In-Reply-To: <1331585159.1084.3.camel@revolution.hippie.lan> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Tue, 13 Mar 2012 01:02:31 +0000 Cc: freebsd-performance@freebsd.org, FreeBSD current Subject: Re: Improved Intel Turbo Boost status/control X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Mar 2012 20:52:15 -0000 On 03/12/12 22:45, Ian Lepore wrote: > On Mon, 2012-03-12 at 21:15 +0200, Alexander Motin wrote: >> I'd like to note that recent r232793 change to cpufreq(4) in HEAD opened >> simple access to the Intel Turbo Boost status/control. I've found that >> at least two of my desktop systems (based Nehalem and SandyBridge Core >> i7s) with enabled Intel Turbo Boost in BIOS it is not use it by default, >> unless powerd is enabled. And before this change it was difficult to >> detect/fix. >> >> ACPI reports extra performance level with frequency 1MHz above the >> nominal to control Intel Turbo Boost operation. It is not a bug, but >> feature: >> dev.cpu.0.freq_levels: 2934/106000 2933/95000 2800/82000 ... >> In this case value 2933 means 2.93GHz, but 2934 means 3.2-3.6GHz. >> >> After boot with default settings I see: >> dev.cpu.0.freq: 2933 >> , that means Turbo Boost is disabled. >> >> Enabling powerd or just adding to rc.conf >> performance_cpu_freq="HIGH" >> enables Turbo Boost and adds extra 10-20% to the system performance. >> >> Turbo Boost operation can be monitored in run-time via the PMC with >> command that prints number or really executed cycles per CPU core: >> pmcstat -s unhalted-core-cycles -w 1 >> > > The r232793 patch applies cleanly to 8-stable and builds just fine, but > after install/reboot I don't see a change in the freq_levels > > revolution> sysctl dev.cpu.0 > dev.cpu.0.%desc: ACPI CPU > dev.cpu.0.%driver: cpu > dev.cpu.0.%location: handle=\_PR_.P001 > dev.cpu.0.%pnpinfo: _HID=none _UID=0 > dev.cpu.0.%parent: acpi0 > dev.cpu.0.coretemp.delta: 70 > dev.cpu.0.coretemp.resolution: 1 > dev.cpu.0.coretemp.tjmax: 101.0C > dev.cpu.0.coretemp.throttle_log: 0 > dev.cpu.0.temperature: 31.0C > dev.cpu.0.freq: 3333 > dev.cpu.0.freq_levels: 3333/130000 3200/117000 3067/105000 > 2933/94000 2800/85000 2667/76000 2533/68000 2400/61000 > 2267/54000 2133/48000 2000/43000 1867/39000 1733/35000 > 1600/32000 1400/28000 1200/24000 1000/20000 800/16000 600/12000 > 400/8000 200/4000 > dev.cpu.0.cx_supported: C1/32 C2/96 C3/128 > dev.cpu.0.cx_lowest: C1 > dev.cpu.0.cx_usage: 100.00% 0.00% 0.00% last 657us > revolution> > > > I would have expected a 3334 entry to appear after the reboot. Is this > expected (like are there other required changes missing in 8-stable), or > do I have something misconfigured? (I can post more info, but don't > want to spam the list if the answer is going to be "this shouldn't work > in 8.x). I don't know any reason why it should not work on 8.x. It is ACPI BIOS duty to report set of frequencies. This patch just makes system to follow it more close. Make sure your CPU supports Turbo Boost and it is enabled in BIOS. On my system disabling Turbo Boost in BIOS removes the frequency from the list. -- Alexander Motin