From krishnaks at iitkgp.ac.in Tue Mar 2 07:18:53 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Tue, 2 Mar 2010 17:48:53 +0530 (IST) Subject: [Hotspot] Hotspot - reg. Message-ID: <57111.203.110.243.22.1267532333.squirrel@webmail.iitkgp.ac.in> Dear Professor, when I tried the following command, hotspot -c ../hotspot.config -f ../floorplan/abc.flp -p abc.pptrace -o abc.ttrace -steady_file abc.steady it gave the following error error: inordinate floorplan size! What could be wrong?. Pl help. -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 From skadron at cs.virginia.edu Tue Mar 2 09:20:54 2010 From: skadron at cs.virginia.edu (Kevin Skadron) Date: Tue, 02 Mar 2010 09:20:54 -0500 Subject: [Hotspot] Hotspot - reg. In-Reply-To: <57111.203.110.243.22.1267532333.squirrel@webmail.iitkgp.ac.in> References: <57111.203.110.243.22.1267532333.squirrel@webmail.iitkgp.ac.in> Message-ID: <4B8D1EC6.10705@cs.virginia.edu> "Inordinate floorplan size" typically means that the spreader and/or the heatsink size have been configured to be smaller than the area of the floorplan. --Kevin Krishna Kumar S wrote: > Dear Professor, > > when I tried the following command, > > hotspot -c ../hotspot.config -f ../floorplan/abc.flp -p abc.pptrace -o > abc.ttrace -steady_file abc.steady > > it gave the following error > > error: inordinate floorplan size! > > > What could be wrong?. Pl help. > From krishnaks at iitkgp.ac.in Tue Mar 9 00:09:26 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Tue, 9 Mar 2010 10:39:26 +0530 (IST) Subject: [Hotspot] Hotspot - Reg. Message-ID: <54109.203.110.246.230.1268111366.squirrel@webmail.iitkgp.ac.in> Dear Prof., Can I tune Hotspot to accept a power trace in nano watts? If possible, how? -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 Mob: 09476105406 09933636208 From wh6p at virginia.edu Tue Mar 9 09:51:57 2010 From: wh6p at virginia.edu (Wei Huang) Date: Tue, 9 Mar 2010 08:51:57 -0600 Subject: [Hotspot] Hotspot - Reg. In-Reply-To: <54109.203.110.246.230.1268111366.squirrel@webmail.iitkgp.ac.in> References: <54109.203.110.246.230.1268111366.squirrel@webmail.iitkgp.ac.in> Message-ID: Hi, You can hack inside HotSpot code (probably hotspot.c, but there may be other places you need to change as well) by dividing the power numbers read from the input power trace by 10^9. The easier way would be just to convert to watts in your power trace file using a script . -Wei On Mon, Mar 8, 2010 at 11:09 PM, Krishna Kumar S wrote: > Dear Prof., > Can I tune Hotspot to accept a power trace in nano watts? If > possible, how? > > -- > Research Scholar > Dept of E & ECE > Indian Institute of Technology, Kharagpur > Kharagpur, West Bengal. 721302 > > Mob: 09476105406 > 09933636208 > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100309/73fba5fd/attachment.html From krishnaks at iitkgp.ac.in Sun Mar 14 08:34:39 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Sun, 14 Mar 2010 19:04:39 +0530 (IST) Subject: [Hotspot] Limitation on number of bocks? Message-ID: <36438.10.3.100.148.1268573679.squirrel@webmail.iitkgp.ac.in> Dear Prof., when i tried hotspot -c hotspot.config -f abc.flp -p abc.pptrace -steady_file abc.steady i got message hotspot: util.c:165: dmatrix:Assertion `m[0] != ((void *)0)` failed. Aborted Is it because the dynamic memory allocation (util.c) has a limit on the number of blocks the tool can accept? If so, is there a way that I can increase the number of blocks the tool can accept? -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 Mob: 09476105406 09933636208 From wh6p at virginia.edu Sun Mar 14 09:27:24 2010 From: wh6p at virginia.edu (Wei Huang) Date: Sun, 14 Mar 2010 09:27:24 -0500 Subject: [Hotspot] Limitation on number of bocks? In-Reply-To: <36438.10.3.100.148.1268573679.squirrel@webmail.iitkgp.ac.in> References: <36438.10.3.100.148.1268573679.squirrel@webmail.iitkgp.ac.in> Message-ID: How many blocks do you have in your floorplan? -Wei On Sun, Mar 14, 2010 at 8:34 AM, Krishna Kumar S wrote: > Dear Prof., > > when i tried hotspot -c hotspot.config -f abc.flp -p abc.pptrace > -steady_file abc.steady i got message > > hotspot: util.c:165: dmatrix:Assertion `m[0] != ((void *)0)` failed. > Aborted > > > Is it because the dynamic memory allocation (util.c) has a limit on the > number of blocks the tool can accept? If so, is there a way that I can > increase the number of blocks the tool can accept? > > > -- > Research Scholar > Dept of E & ECE > Indian Institute of Technology, Kharagpur > Kharagpur, West Bengal. 721302 > > Mob: 09476105406 > 09933636208 > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100314/debffad7/attachment.html From wh6p at virginia.edu Mon Mar 15 12:48:25 2010 From: wh6p at virginia.edu (Wei Huang) Date: Mon, 15 Mar 2010 12:48:25 -0500 Subject: [Hotspot] [Fwd: Re: Floorplan format] In-Reply-To: <4B9E44C1.4050607@cs.virginia.edu> References: <4B9E44C1.4050607@cs.virginia.edu> Message-ID: Hi Krishna, I guess it meant to be "rotatable" so that the direction of the block can be changed. If you have further questions regarding this, please let us know. As for the aspect ratio, you can try to make it to 5.0, although I wouldn't recommend to do so, because unless you are modeling something like a cache line or register file entry, AR > 5.0 is uncommon. If you are sure the structure you model has that aspect ratio, then you can use it. HotSpot should be able to internally divide it into subblocks with AR close to 1.0 to improve the accuracy of the results. (By the way, if you don't mind, please also cc the mailing list ( hotspot at cs.virginia.edu) in the future, so that it also helps people who have similar questions and your questions may get faster and better responses from other HotSpot users.) Hope this helps. -Wei > -------- Original Message -------- > Subject: Re: Floorplan format > Date: Sat, 13 Mar 2010 16:57:23 +0530 > From: Krishna M.Viswanath > To: skadron at cs.virginia.edu > > > ... > I would also like to know that in the configuration file\description > file(.desc), what does the 'rotable' column stand for? Also can the > maximum values of the aspect ratio been entered in the description file > be more than 5 ? I was not able to get the details regarding these > information in the manual of Hotspot 5.0. > As of now I'vve been using the max aspect ratios of 3 and rotable values > as 1. > > Regards, > Krishna M.V. > > > > > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100315/6643e901/attachment.html From krishnaks at iitkgp.ac.in Tue Mar 16 08:22:57 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Tue, 16 Mar 2010 18:52:57 +0530 (IST) Subject: [Hotspot] .svg file Message-ID: <45506.10.3.100.148.1268745777.squirrel@webmail.iitkgp.ac.in> Dear Prof., If the .svg file created using grid_thermal_map.pl is dark black, what does it mean? -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 Mob: 09476105406 09933636208 From wh6p at virginia.edu Tue Mar 16 09:30:53 2010 From: wh6p at virginia.edu (Wei Huang) Date: Tue, 16 Mar 2010 09:30:53 -0500 Subject: [Hotspot] .svg file In-Reply-To: <45506.10.3.100.148.1268745777.squirrel@webmail.iitkgp.ac.in> References: <45506.10.3.100.148.1268745777.squirrel@webmail.iitkgp.ac.in> Message-ID: Maybe your browser doens't have plugins for SVG? Have you tried to view other SVG files that are not generated form HotSpot release? -Wei On Tue, Mar 16, 2010 at 8:22 AM, Krishna Kumar S wrote: > Dear Prof., > If the .svg file created using grid_thermal_map.pl is dark black, > what does it mean? > > -- > Research Scholar > Dept of E & ECE > Indian Institute of Technology, Kharagpur > Kharagpur, West Bengal. 721302 > > Mob: 09476105406 > 09933636208 > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100316/e4063f7a/attachment.html From krishnaks at iitkgp.ac.in Mon Mar 22 01:20:36 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Mon, 22 Mar 2010 11:50:36 +0530 (IST) Subject: [Hotspot] Negative temperature Message-ID: <18120.10.3.100.148.1269238836.squirrel@webmail.iitkgp.ac.in> Dear Prof., I used the tool with ambient temperature 273.15 Kelvin. But I see some negative temperatures like -50 degree Celsius in temperature trace file. The maximum temperature generated is about 6 degree Celsius. These are the temperatures generated by combinational gates. Why do I get negative temperatures, below ambient temperature? -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 Mob: 09476105406 09933636208 From wh6p at virginia.edu Mon Mar 22 12:17:29 2010 From: wh6p at virginia.edu (Wei Huang) Date: Mon, 22 Mar 2010 12:17:29 -0500 Subject: [Hotspot] Negative temperature In-Reply-To: <18120.10.3.100.148.1269238836.squirrel@webmail.iitkgp.ac.in> References: <18120.10.3.100.148.1269238836.squirrel@webmail.iitkgp.ac.in> Message-ID: Hi, What was your initial temperature? It should also be set in Kelvin. Regards, -Wei On Mon, Mar 22, 2010 at 1:20 AM, Krishna Kumar S wrote: > Dear Prof., > I used the tool with ambient temperature 273.15 Kelvin. But I see > some negative temperatures like -50 degree Celsius in temperature > trace file. The maximum temperature generated is about 6 degree > Celsius. These are the temperatures generated by combinational gates. > Why do I get negative temperatures, below ambient temperature? > > -- > Research Scholar > Dept of E & ECE > Indian Institute of Technology, Kharagpur > Kharagpur, West Bengal. 721302 > > Mob: 09476105406 > 09933636208 > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot > -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100322/5fbbc6b4/attachment.html From bochen.wu at gmail.com Tue Mar 30 20:49:28 2010 From: bochen.wu at gmail.com (Bo Chen Wu) Date: Tue, 30 Mar 2010 21:49:28 -0400 Subject: [Hotspot] Question about Compiling the HotSpot 5.0 Message-ID: Hey guys, I just download the HotSpot 5.0 recently and I am new to Linux.I tried to compile the HotSpot 5.0 in my school's Linux Machine but keep geting the following errors: "make: Fatal error in reader: Makefile, line 51: Unexpected end of line seen." I also tried wtih HotSpot 4.2 in addtion to re-configure the GNU make, and I still got these errors. Does anyone compile the HotSpot 4.2 or 5.0 recently? or does anyone know why I got these error messages? -- Thank You For Your Time. Bo Chen Wu (646)-861-9905 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100330/fc4d8adc/attachment.html From bernauer at informatik.uni-tuebingen.de Wed Mar 31 01:52:57 2010 From: bernauer at informatik.uni-tuebingen.de (Andreas Bernauer) Date: Wed, 31 Mar 2010 08:52:57 +0200 (CEST) Subject: [Hotspot] Question about Compiling the HotSpot 5.0 In-Reply-To: Message-ID: <24457283.781270018373850.JavaMail.bernauer@lava> Hi Bo, line 51 lies within a Makefile conditional. It could be that your make does not understand the conditional directive. As far as I can see, you need GNU make to compile Hotspot (called gmake on some systems). I compiled Hotspot 4.2 and 5.0 successfully with the following version of make: >>>>>>>>>>>>>>>> $ make --version GNU Make 3.81 Copyright (C) 2006 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. This program built for i486-pc-linux-gnu <<<<<<<<<<<<<<<<< If you provide a log of your terminal session, we may be able to help you more. Also, the output of `uname -a` may be helpful, so we know which system you are using. Cheers, Andreas. -- Andreas Bernauer WSI/TI, Sand 13, B202, 72076 T?bingen, +49 70 71 29 75 940 http://www.ti.uni-tuebingen.de/Andreas_Bernauer.227.0.html ----- "Bo Chen Wu" wrote: > Hey guys, > > I just download the HotSpot 5.0 recently and I am new to Linux.I tried > to > compile the HotSpot 5.0 in my school's Linux Machine but keep geting > the > following errors: "make: Fatal error in reader: Makefile, line 51: > Unexpected end of line seen." I also tried wtih HotSpot 4.2 in addtion > to > re-configure the GNU make, and I still got these errors. > > Does anyone compile the HotSpot 4.2 or 5.0 recently? or does anyone > know why > I got these error messages? > > -- > Thank You For Your Time. > Bo Chen Wu > (646)-861-9905 > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot From fazal256 at yahoo.com Wed Mar 31 15:00:20 2010 From: fazal256 at yahoo.com (fazal hameed) Date: Wed, 31 Mar 2010 13:00:20 -0700 (PDT) Subject: [Hotspot] Power values from cacti Message-ID: <517638.48542.qm@web54205.mail.re2.yahoo.com> Hi, I am using cacti 6.0 for the dynamic power, lkg power and area estimation of register file, Issue queue, ROB etc with the technology files from ITRS. The power values are very small for the cacti and the average power density of most of the components is in the range of 0.7 W/mm2. I have generated a floorplan using cacti area model. By running cycle accurate simulation for the single core, I get very less temp values. I do not know how to address this problem. I want to address the thermal issue in my experiment by using some microarchitectural techniques. But the avg temp is the range of 45.7 close to ambient temperature. There is significant reduction in power but not equally reduction in temperature. Is the problem due to very small area of the core and the heat sink model is large or should I change the package properties. Is there any method to cope with this issue. Should I multiply the power values of each component with a constant value of 10 so that power density is 7 W/mm2. regards, Fazal Hameed