From ks4kk at virginia.edu Sun May 2 10:14:11 2010 From: ks4kk at virginia.edu (Karthik Sankaranarayanan) Date: Sun, 2 May 2010 10:14:11 -0700 Subject: [Hotspot] Debug the source code In-Reply-To: References: Message-ID: Hi, > Also, another one of your paper mention about using flp-basic and flp-advance options when perform floor plan optimization using HotSpotFloorPlan, do you > have any documented simulation steps that i can borrow? Please see http://www.jilp.org/vol7/v7paper15.pdf for the simulation parameters (especially Figure 2 ) Thanks, -karthik On Fri, Apr 30, 2010 at 6:21 AM, Wei Huang wrote: > Hi Bo, please see below... > > >> I read two of the research papers you have upload on the HoSpot website. >> In the papers, you mentioned about use Oil-Silicon and Air-Sink for >> simulation. I would like to perform the same simulations, do you have any >> documented simulation steps for these two scenarios? >> > > I believe there is a configuration file for the oil-based cooling case, in > HotSpot v5.0. > >> >> Also, another one of your paper mention about using flp-basic and >> flp-advance options when perform floor plan optimization using >> HotSpotFloorPlan, do you have any documented simulation steps that i can >> borrow? >> > > I am not very familiar with details of HotFloorplanner, it is developed my > another colleague. Once he sees this post, he should be able to help you > with this question. > >> >> As i mentioned before, I was trying to integrate the micrchannel into 3D >> thermal simulation. based on the work that is done by David Atienza, he >> indicated that at each grid cell's total resistance can be calculated using >> following equation: >> Rtot = Rcond + Rconv + Rheat = 1 / (Gsi/t + 1/Rb) + A / (h*At) + A / >> (V*P*cp) where each of the variable are constant. >> > > I am not aware of this work, sounds interesting. Will check it out. > >> >> Currently I am looking at using this equation to calculate the steady >> state temperature. I debugged the HoSpot source code and found out that >> steady_state_temp(model, overall_power, steady_temp) is used to calculate >> the steady state temperature. I found the follow function call flows: >> steady_state_temp -> steady_state_temp_grid -> recursive_multigrid -> >> set_heuristic_temp -> scaleadd_dvector >> >> which it use model->layers.rz as the delta resistance. this is a single >> value that is used through out the grid cells in the single layer, i was >> wondering if i change this rz to equal to the total resistance value mention >> above, will it work? Plus, why the HotSpot uses rz in this calculation? Will >> it be necessary to create a matrix for each layer to calculate the grid >> cell's resistance individual? >> > > Correct me if I didn't understand your idea. Basically you want to get rid > of the layered RC network and replace it with an equivalent single layer? I > doubt this would work well in terms of accuracy, but if you want some > first-order exploration or quick and dirty results, this might be worth > tring. As for "rz" in the grid model, I don't quite understand your > question... Because we assume regular grid cells, so as long as the material > within each layer is homogeneous, it is convenient to use one rz value for > that layer. Solving matrix for large grid size is very expensive (imagine > 1000x1000 with 10 layers), so instead we use an iterative method to solve > the network. I am sure there are much better algorithms out there for this > problem. > > -Wei > >> >> Thank you >> BoChen Wu >> >> On Tue, Apr 6, 2010 at 2:47 PM, Bo Chen Wu wrote: >> >>> Hi Wei Huang, >>> >>> Thank you very much for your response, I appreciated, Please see my >>> comments below and please let me know if you have any questions: >>> >>> Penn State University >>> M.S. of Computer Science and Engineering >>> BoChen Wu >>> bochen.wu at gmail.com >>> >>> On Tue, Apr 6, 2010 at 10:54 AM, Wei Huang wrote: >>> >>>> HI Please see below... >>>> >>>> On Mon, Apr 5, 2010 at 7:17 PM, Bo Chen Wu wrote: >>>> >>>>> Hey guys, >>>>> >>>>> I have several questions would like to ask you guys: >>>>> >>>>> 1) I just finished running the Hotspot tutorial? I would like to debug >>>>> to see what is the hotspot actually doing while running it? Can I use visual >>>>> studio 2008 to debug it? Or do you have a better program to suggest for me >>>>> to debug the source code? >>>>> >>>> >>>> Our online HOW-TO provides step-by-step instructions on how to compile >>>> HotSpot in Windows and how to use HotSpot in VC++. >>>> >>> [BCW 04/06/2010]: I only saw the HOW-TO provides step-by-step >>> instruction of how to build the HotSpot, but it did not said how to >>> using VC++ to step into code to debug and see what each line of code doing. >>> I guess I should create a project initially in the visual studio 2008 and >>> debug the HotSpot? Or do you guess another way of stepping through the >>> source code? >>> >>>> >>>>> 2) I notice that hotspot support partial 3-D stacking thermal which >>>>> only apply for grid model, What is the model which thermal model is the >>>>> current 3-D stacking thermal model that Hotspot is using, or What kind >>>>> equation is the Hotspot use to compute the each grid cell's temperature at >>>>> run time? >>>>> >>>> >>>> I am not sure I understand your question. The grid model is a >>>> finite-difference model, which updates temperature of one grid cell based >>>> its neighbors and iterate. >>>> >>> [BCW 04/06/2010]: I think you answered partial of my question. based on >>> what you said above, the finite-different model is basically updated each >>> cell's temperature based on its neighbors' temperature? My question was what >>> kind equation or logic was used in this finite-difference model? For >>> example, does the cell subtract its temperature from the average temperature >>> of all its neighbor cells? >>> >>>> >>>>> 3) I am currently trying to integrate a 3-D liquid cooling thermal >>>>> model to the Hotspot, I think the best place of the source for me to change >>>>> is in the RCutil.c function AK4? is this correct? >>>>> >>>> >>>> This seems a non-trivial hack to HotSpot. I don't have a ready answer >>>> for you now. But it should be more complicated than just modify the >>>> algorithm. If you are talking about microchannel cooling, you need to add >>>> layers that model the microchannels, and also have a good way to model the >>>> silicon-to-channel convection, and the thermal model for the liquid flow. >>>> There are some recent papers on how to model 3D u-channel cooling in the >>>> literature, for example, you can search recent ICCAD papers. >>>> >>> [BCW 04/06/2010]: You are right, i plan to use the microchannel cooling >>> that recently scholars have studied. Also, from the reading the research >>> papers, i have obtained the model of calculating the total thermal >>> resistance at each cell level for 3-D stacking using microchannel cooling. >>> Since HotSpot supports calculating the grid-cell level temperatures, I would >>> like the integrated the model i found into HotSpot. i think to model the >>> microchannel, I can just use an extra layer with microchannel floor plan. I >>> am doing this for my class project. >>> >>>> >>>> Hope this helps. >>>> >>>> -Wei >>>> >>>>> >>>>> -- >>>>> 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 >>>>> >>>>> >>>> >>> >>> >>> -- >>> Thank You For Your Time. >>> Bo Chen Wu >>> (646)-861-9905 >>> >> >> >> >> -- >> Thank You For Your Time. >> >> Bo Chen Wu >> The Pennsylvania State University - University Park >> >> M.S. of Computer Science and Engineering >> (646)-861-9905 >> > > > _______________________________________________ > 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/20100502/a22dd4c3/attachment.html From ks4kk at virginia.edu Sun May 2 10:05:25 2010 From: ks4kk at virginia.edu (Karthik Sankaranarayanan) Date: Sun, 2 May 2010 10:05:25 -0700 Subject: [Hotspot] Question about hotfloorplan In-Reply-To: References: Message-ID: Hi Juan, As Wei has explained, "connectivity" denotes that the units talk to each other. If you would like certain units that talk to each other to also be placed close to each other, a possibility is to increase the corresponding weight in the connectivity table (instead of 1, to say 10). HotFloorplan optimizes for a multi-variable objective function (a linear combination of area, wire length and temperature). Hence, if you would like for the overall wire-length (weighted sum of the connectivities) to be weighted higher, you could increase the lambdaW parameter. See the flp_evaluate_metric function in flp.c for more details. Hope this helps. Thanks, -karthik 2010/4/30 Wei Huang > Hi Juan, > > sorry for the late response. I personally am not very familiar with > HotFloorplanner, but I am sure my colleagues are able to help you with this > once they see this post. > > My guess is that the "connectivity" means the two units are logically > adjacent in the microarchitecture. But they are not necessarily physically > adjacent in the floorplan. The floorplanner will try its best by not put the > two blocks too far apart, which might cause timing violations due to > interconnect delays and such. There may be some assumptions/configs > regarding the relationship between delay and distance for each type of units > in the tool. Basically, the floorplanner's job is to find an optimal > floorplan that minimizes the hot spot temperature without violating timing > constraint (or it also optimizes the timing at the same time for a given hot > spot temperature constraint). I might not be entirely accurate about the > tool, but you get the basic idea. > > Hope this helps. > > -Wei > > 2010/4/29 Juan Manuel Cebri?n Gonz?lez > >> Hello. >> >> I've been working on some description files for a set of processors, >> scaling technologies etc for 2 cores, 4 cores... When i tried to build the >> floorplans using this tool i get some weird results. While the area is been >> optimized, the connectivity specified in the .desc file seems to be >> completely ignored. I get an isolated ICache in the middle of the chip and >> other similar results. Then i looked at the ev6.flp.orig you provided and it >> also completely ignores the connectivity info from the .desc file (i.e. DTB >> LdStQ 1) both structures should be adjacent, but they are not. >> >> Here are the connectivity and the generated floorplan. >> >> # Connectivity information >> # Line format \t\t >> >> # Core 0 >> IntExec_c0_ ROB_c0_ 1 >> Bpred_c0_ TLB_c0_ 1 >> Bpred_c0_ Icache_c0_ 1 >> Dcache_c0_ LdStQ_c0_ 1 >> ROB_c0_ IntReg_c0_ 1 >> TLB_c0_ LdStQ_c0_ 1 >> AluMap_c0_ LdStQ_c0_ 1 >> FPAlu_c0_ ROB_c0_ 1 >> Dcache_c0_ L2_c0_ 1 >> Icache_c0_ L2_c0_ 1 >> AluMap_c0_ ROB_c0_ 1 >> ROB_c0_ FPReg_c0_ 1 >> >> # Core 1 >> IntExec_c1_ ROB_c1_ 1 >> Bpred_c1_ TLB_c1_ 1 >> Bpred_c1_ Icache_c1_ 1 >> Dcache_c1_ LdStQ_c1_ 1 >> ROB_c1_ IntReg_c1_ 1 >> TLB_c1_ LdStQ_c1_ 1 >> AluMap_c1_ LdStQ_c1_ 1 >> FPAlu_c1_ ROB_c1_ 1 >> Dcache_c1_ L2_c1_ 1 >> Icache_c1_ L2_c1_ 1 >> AluMap_c1_ ROB_c1_ 1 >> ROB_c1_ FPReg_c1_ 1 >> >> #L2 is shared >> L2_c0_ L2_c1_ 1 >> >> And the output (picture) >> >> http://skywalker.inf.um.es/~jcebrian/mi_procesador_2p_8kbpred.pdf >> >> Is there something wrong with the tool or i am misunderstanding the >> "connectivity" meaning from the .desc file? (i understand that if two >> structures are "connected" they should be adjacent, or at least as close as >> possible (this does not happen in my 2-Core output). >> >> Thank you in advance. >> >> Best, Juan Manuel. >> >> -- >> --------------------------------------------- >> Juan Manuel Cebri?n Gonz?lez >> University of Murcia, Spain >> http://skywalker.inf.um.es/~jcebrian/ >> --------------------------------------------- >> >> >> _______________________________________________ >> HotSpot mailing list >> HotSpot at mail.cs.virginia.edu >> http://www.cs.virginia.edu/mailman/listinfo/hotspot >> >> > > _______________________________________________ > 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/20100502/601324b0/attachment.html From jcebrian at ditec.um.es Mon May 3 01:30:50 2010 From: jcebrian at ditec.um.es (=?ISO-8859-1?Q?Juan_Manuel_Cebri=E1n_Gonz=E1lez?=) Date: Mon, 3 May 2010 10:30:50 +0200 Subject: [Hotspot] Question about hotfloorplan In-Reply-To: References:

Message-ID: Thank you for your replies. I'll try increasing the weight in the connectivity table as you suggested and post the results. 2010/5/2 Karthik Sankaranarayanan > Hi Juan, > > As Wei has explained, "connectivity" denotes that the units talk to each > other. If you would like certain units that talk to each other to also be > placed close to each other, a possibility is to increase the corresponding > weight in the connectivity table (instead of 1, to say 10). HotFloorplan > optimizes for a multi-variable objective function (a linear combination of > area, wire length and temperature). Hence, if you would like for the overall > wire-length (weighted sum of the connectivities) to be weighted higher, you > could increase the lambdaW parameter. See the flp_evaluate_metric function > in flp.c for more details. > > Hope this helps. > Thanks, > -karthik > > 2010/4/30 Wei Huang > > Hi Juan, >> >> sorry for the late response. I personally am not very familiar with >> HotFloorplanner, but I am sure my colleagues are able to help you with this >> once they see this post. >> >> My guess is that the "connectivity" means the two units are logically >> adjacent in the microarchitecture. But they are not necessarily physically >> adjacent in the floorplan. The floorplanner will try its best by not put the >> two blocks too far apart, which might cause timing violations due to >> interconnect delays and such. There may be some assumptions/configs >> regarding the relationship between delay and distance for each type of units >> in the tool. Basically, the floorplanner's job is to find an optimal >> floorplan that minimizes the hot spot temperature without violating timing >> constraint (or it also optimizes the timing at the same time for a given hot >> spot temperature constraint). I might not be entirely accurate about the >> tool, but you get the basic idea. >> >> Hope this helps. >> >> -Wei >> >> 2010/4/29 Juan Manuel Cebri?n Gonz?lez >> >>> Hello. >>> >>> I've been working on some description files for a set of processors, >>> scaling technologies etc for 2 cores, 4 cores... When i tried to build the >>> floorplans using this tool i get some weird results. While the area is been >>> optimized, the connectivity specified in the .desc file seems to be >>> completely ignored. I get an isolated ICache in the middle of the chip and >>> other similar results. Then i looked at the ev6.flp.orig you provided and it >>> also completely ignores the connectivity info from the .desc file (i.e. DTB >>> LdStQ 1) both structures should be adjacent, but they are not. >>> >>> Here are the connectivity and the generated floorplan. >>> >>> # Connectivity information >>> # Line format \t\t >>> >>> # Core 0 >>> IntExec_c0_ ROB_c0_ 1 >>> Bpred_c0_ TLB_c0_ 1 >>> Bpred_c0_ Icache_c0_ 1 >>> Dcache_c0_ LdStQ_c0_ 1 >>> ROB_c0_ IntReg_c0_ 1 >>> TLB_c0_ LdStQ_c0_ 1 >>> AluMap_c0_ LdStQ_c0_ 1 >>> FPAlu_c0_ ROB_c0_ 1 >>> Dcache_c0_ L2_c0_ 1 >>> Icache_c0_ L2_c0_ 1 >>> AluMap_c0_ ROB_c0_ 1 >>> ROB_c0_ FPReg_c0_ 1 >>> >>> # Core 1 >>> IntExec_c1_ ROB_c1_ 1 >>> Bpred_c1_ TLB_c1_ 1 >>> Bpred_c1_ Icache_c1_ 1 >>> Dcache_c1_ LdStQ_c1_ 1 >>> ROB_c1_ IntReg_c1_ 1 >>> TLB_c1_ LdStQ_c1_ 1 >>> AluMap_c1_ LdStQ_c1_ 1 >>> FPAlu_c1_ ROB_c1_ 1 >>> Dcache_c1_ L2_c1_ 1 >>> Icache_c1_ L2_c1_ 1 >>> AluMap_c1_ ROB_c1_ 1 >>> ROB_c1_ FPReg_c1_ 1 >>> >>> #L2 is shared >>> L2_c0_ L2_c1_ 1 >>> >>> And the output (picture) >>> >>> http://skywalker.inf.um.es/~jcebrian/mi_procesador_2p_8kbpred.pdf >>> >>> Is there something wrong with the tool or i am misunderstanding the >>> "connectivity" meaning from the .desc file? (i understand that if two >>> structures are "connected" they should be adjacent, or at least as close as >>> possible (this does not happen in my 2-Core output). >>> >>> Thank you in advance. >>> >>> Best, Juan Manuel. >>> >>> -- >>> --------------------------------------------- >>> Juan Manuel Cebri?n Gonz?lez >>> University of Murcia, Spain >>> http://skywalker.inf.um.es/~jcebrian/ >>> --------------------------------------------- >>> >>> >>> _______________________________________________ >>> HotSpot mailing list >>> HotSpot at mail.cs.virginia.edu >>> http://www.cs.virginia.edu/mailman/listinfo/hotspot >>> >>> >> >> _______________________________________________ >> HotSpot mailing list >> HotSpot at mail.cs.virginia.edu >> http://www.cs.virginia.edu/mailman/listinfo/hotspot >> >> > -- --------------------------------------------- Juan Manuel Cebri?n Gonz?lez University of Murcia, Spain http://skywalker.inf.um.es/~jcebrian/ --------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100503/f7a4cd30/attachment.html From wowlyy at hotmail.com Tue May 4 12:43:09 2010 From: wowlyy at hotmail.com (=?gb2312?B?wO7R89Hz?=) Date: Wed, 5 May 2010 03:43:09 +0800 Subject: [Hotspot] The power trace file Message-ID: Hi, I'm a grad students working on thermal aware routing. Now I'm trying to use Hotspot to generate temperature map. I've read the guide, two files are needed for generating the temperature map. One is the .flp, and the other is .ptrace. Can you tell me how to get the power trace file? I've search a lot benchmarks, but I didn't find anyone having the power information. Sincerely, Yangyang _________________________________________________________________ MSN????????????????25???????????2010????????? http://kaba.msn.com.cn/?k=1 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/2ac24bc0/attachment.html From a9051224 at st2.fju.edu.tw Tue May 4 12:54:21 2010 From: a9051224 at st2.fju.edu.tw (Yuan-Ying Chang) Date: Wed, 5 May 2010 03:54:21 +0800 Subject: [Hotspot] floorplan setting Message-ID: Dear, Could I change the chip size in the floorplan? The original setting in hotspot is 0.016*0.016 m^2. I want to change the chip size in the floorplan, but I can't find the parameter to change it. (p.s. I use the MS Excel interface to draw floorplan.) -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/89634503/attachment.html From ks4kk at virginia.edu Tue May 4 13:12:52 2010 From: ks4kk at virginia.edu (Karthik Sankaranarayanan) Date: Tue, 4 May 2010 13:12:52 -0700 Subject: [Hotspot] floorplan setting In-Reply-To: References: Message-ID: Hi, The .flp files do not explicitly specify the total chip size. They only specify the sizes of the individual functional blocks and the total chip size is calculated from them. If you would like to change the chip size, please change the sizes of the individual functional blocks accordingly. Thanks, -karthik On Tue, May 4, 2010 at 12:54 PM, Yuan-Ying Chang wrote: > > Dear, > > Could I change the chip size in the floorplan? The original setting in > hotspot is 0.016*0.016 m^2. > I want to change the chip size in the floorplan, but I can't find the > parameter to change it. > (p.s. I use the MS Excel interface to draw floorplan.) > _______________________________________________ > 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/20100504/a1012be0/attachment.html From skadron at cs.virginia.edu Tue May 4 14:00:47 2010 From: skadron at cs.virginia.edu (Kevin Skadron) Date: Tue, 04 May 2010 17:00:47 -0400 Subject: [Hotspot] The power trace file In-Reply-To: References: Message-ID: <4BE08AFF.6080003@cs.virginia.edu> You will need to use a simulator that also models power to generate average power per time step. Wattch (usually integrated with Simplescalar) is a common choice for this, although it is starting to be supplanted by other models. McPat is a recent one that has been integrated with M5. --Kevin On 5/4/2010 3:43 PM, ??? wrote: > Hi, > I'm a grad students working on thermal aware routing. Now I'm trying to > use Hotspot to generate temperature map. I've read the guide, two files > are needed for generating the temperature map. One is the .flp, and the > other is .ptrace. Can you tell me how to get the power trace file? I've > search a lot benchmarks, but I didn't find anyone having the power > information. > > Sincerely, > Yangyang > ------------------------------------------------------------------------ > ????? Windows Live Messenger ???????? ????? > > > > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot From fsamie at gmail.com Thu May 6 01:32:21 2010 From: fsamie at gmail.com (farzad samie) Date: Thu, 6 May 2010 13:02:21 +0430 Subject: [Hotspot] The power trace file Message-ID: Hi Yangyang, you need a cycle accurate simulator which models the power dissipation. There are some simulators which report average power of functional units in each cycle. As Kevin said, Wattch is a common model which integrated with SimpleScalar. you should change the source code of Wattch as follows: for every 10000 cycle, average power consumption of each component and dump them in a power trace file. a better idea is to use PTscalar, a power-thermal simulator which calculates the average power of components in each 10000 cycle itself. hope it helps. Farzad. On Wed, May 5, 2010 at 11:30 PM, wrote: > Send HotSpot mailing list submissions to > hotspot at mail.cs.virginia.edu > > To subscribe or unsubscribe via the World Wide Web, visit > http://www.cs.virginia.edu/mailman/listinfo/hotspot > or, via email, send a message with subject or body 'help' to > hotspot-request at mail.cs.virginia.edu > > You can reach the person managing the list at > hotspot-owner at mail.cs.virginia.edu > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of HotSpot digest..." > > > Today's Topics: > > 1. The power trace file (???) > 2. floorplan setting (Yuan-Ying Chang) > 3. Re: floorplan setting (Karthik Sankaranarayanan) > 4. Re: The power trace file (Kevin Skadron) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Wed, 5 May 2010 03:43:09 +0800 > From: ??? > Subject: [Hotspot] The power trace file > To: Hotspot mail list > Message-ID: > Content-Type: text/plain; charset="gb2312" > > > > > > > > Hi, > I'm a grad students working on thermal aware routing. Now I'm > trying to use Hotspot to generate temperature map. I've read the guide, > two files are needed for generating the temperature map. One is the > .flp, and the other is .ptrace. Can you tell me how to get the power > trace file? I've search a lot benchmarks, but I didn't find anyone > having the power information. > > Sincerely, > Yangyang > _________________________________________________________________ > MSN????????????????25???????????2010????????? > http://kaba.msn.com.cn/?k=1 > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/2ac24bc0/attachment-0001.html > > ------------------------------ > > Message: 2 > Date: Wed, 5 May 2010 03:54:21 +0800 > From: Yuan-Ying Chang > Subject: [Hotspot] floorplan setting > To: hotspot at mail.cs.virginia.edu > Message-ID: > > Content-Type: text/plain; charset="iso-8859-1" > > Dear, > > Could I change the chip size in the floorplan? The original setting in > hotspot is 0.016*0.016 m^2. > I want to change the chip size in the floorplan, but I can't find the > parameter to change it. > (p.s. I use the MS Excel interface to draw floorplan.) > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/89634503/attachment-0001.html > > ------------------------------ > > Message: 3 > Date: Tue, 4 May 2010 13:12:52 -0700 > From: Karthik Sankaranarayanan > Subject: Re: [Hotspot] floorplan setting > To: a9051224 at st2.fju.edu.tw > Cc: hotspot at mail.cs.virginia.edu > Message-ID: > > Content-Type: text/plain; charset="iso-8859-1" > > Hi, > > The .flp files do not explicitly specify the total chip size. They only > specify the sizes of the individual functional blocks and the total chip > size is calculated from them. If you would like to change the chip size, > please change the sizes of the individual functional blocks accordingly. > > Thanks, > -karthik > > On Tue, May 4, 2010 at 12:54 PM, Yuan-Ying Chang >wrote: > > > > > Dear, > > > > Could I change the chip size in the floorplan? The original setting in > > hotspot is 0.016*0.016 m^2. > > I want to change the chip size in the floorplan, but I can't find the > > parameter to change it. > > (p.s. I use the MS Excel interface to draw floorplan.) > > _______________________________________________ > > 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/20100504/a1012be0/attachment-0001.html > > ------------------------------ > > Message: 4 > Date: Tue, 04 May 2010 17:00:47 -0400 > From: Kevin Skadron > Subject: Re: [Hotspot] The power trace file > To: hotspot at mail.cs.virginia.edu > Message-ID: <4BE08AFF.6080003 at cs.virginia.edu> > Content-Type: text/plain; charset=UTF-8; format=flowed > > You will need to use a simulator that also models power to generate > average power per time step. Wattch (usually integrated with > Simplescalar) is a common choice for this, although it is starting to be > supplanted by other models. McPat is a recent one that has been > integrated with M5. > > --Kevin > > On 5/4/2010 3:43 PM, ??? wrote: > > Hi, > > I'm a grad students working on thermal aware routing. Now I'm trying to > > use Hotspot to generate temperature map. I've read the guide, two files > > are needed for generating the temperature map. One is the .flp, and the > > other is .ptrace. Can you tell me how to get the power trace file? I've > > search a lot benchmarks, but I didn't find anyone having the power > > information. > > > > Sincerely, > > Yangyang > > ------------------------------------------------------------------------ > > ????? Windows Live Messenger ???????? ????? > > > > > > > > > > _______________________________________________ > > HotSpot mailing list > > HotSpot at mail.cs.virginia.edu > > http://www.cs.virginia.edu/mailman/listinfo/hotspot > > > > ------------------------------ > > _______________________________________________ > HotSpot mailing list > HotSpot at mail.cs.virginia.edu > http://www.cs.virginia.edu/mailman/listinfo/hotspot > > > End of HotSpot Digest, Vol 35, Issue 3 > ************************************** > -- Farzad Samie -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100506/2b4f6efe/attachment.html From sthannirmalai at hotmail.com Thu May 20 01:58:50 2010 From: sthannirmalai at hotmail.com (thannir malai) Date: Thu, 20 May 2010 05:58:50 +0000 Subject: [Hotspot] HotSpot integeration with sim-wattch Message-ID: Hi, I want some hints on how to integerate HotSpot with sim-wattch . I really appreciate it. Thanks _________________________________________________________________ The New Busy is not the too busy. Combine all your e-mail accounts with Hotmail. http://www.windowslive.com/campaign/thenewbusy?tile=multiaccount&ocid=PID28326::T:WLMTAGL:ON:WL:en-US:WM_HMP:042010_4 -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100520/5802f0e2/attachment.html From devendra.rai at tik.ee.ethz.ch Fri May 21 10:21:38 2010 From: devendra.rai at tik.ee.ethz.ch (Devendra Rai) Date: Fri, 21 May 2010 16:21:38 +0200 Subject: [Hotspot] Simulation: sensitivity Message-ID: Hello HotSpot, I am using hotspot for purposes other than what it was directly intended for, and I am now wondering about a few things. First, here is what I am trying to do: Simulate an isolated single component (like L2) and see how the temperature evolves. Then, I place a similar component (say, L3) of the same dimensions in L2's neighborhood, and then play with the power trace of L3 to see the effect on L2. I am playing with rather large power trace numbers like 20,40... with the units being the same as the defaults. I was hoping that with L3 "powered on" L2 would show a significantly different temperature trace than when it was isolated. But, I observe that hotspot outputs the same values no matter what is the temperature of L3. So, I believe that I am missing things like, telling hotspot that they are in the same silicon. My floorplan has this simple entry: L2 0.01000 0.01000 0.000000 0.000000 L3 0.01000 0.01000 0.010000 0.000000 Can you suggest what I am missing? Thanks Devendra Rai On Thu, May 6, 2010 at 10:32, farzad samie wrote: > Hi Yangyang, > you need a cycle accurate simulator which models the power dissipation. > There are some simulators which report average power of functional units in > each cycle. As Kevin said, Wattch is a common model which integrated with > SimpleScalar. you should change the source code of Wattch as follows: > for every 10000 cycle, average power consumption of each component and dump > them in a power trace file. > a better idea is to use PTscalar, a power-thermal simulator which > calculates the average power of components in each 10000 cycle itself. > hope it helps. > Farzad. > > On Wed, May 5, 2010 at 11:30 PM, wrote: > >> Send HotSpot mailing list submissions to >> hotspot at mail.cs.virginia.edu >> >> To subscribe or unsubscribe via the World Wide Web, visit >> http://www.cs.virginia.edu/mailman/listinfo/hotspot >> or, via email, send a message with subject or body 'help' to >> hotspot-request at mail.cs.virginia.edu >> >> You can reach the person managing the list at >> hotspot-owner at mail.cs.virginia.edu >> >> When replying, please edit your Subject line so it is more specific >> than "Re: Contents of HotSpot digest..." >> >> >> Today's Topics: >> >> 1. The power trace file (???) >> 2. floorplan setting (Yuan-Ying Chang) >> 3. Re: floorplan setting (Karthik Sankaranarayanan) >> 4. Re: The power trace file (Kevin Skadron) >> >> >> ---------------------------------------------------------------------- >> >> Message: 1 >> Date: Wed, 5 May 2010 03:43:09 +0800 >> From: ??? >> Subject: [Hotspot] The power trace file >> To: Hotspot mail list >> Message-ID: >> Content-Type: text/plain; charset="gb2312" >> >> >> >> >> >> >> >> Hi, >> I'm a grad students working on thermal aware routing. Now I'm >> trying to use Hotspot to generate temperature map. I've read the guide, >> two files are needed for generating the temperature map. One is the >> .flp, and the other is .ptrace. Can you tell me how to get the power >> trace file? I've search a lot benchmarks, but I didn't find anyone >> having the power information. >> >> Sincerely, >> Yangyang >> _________________________________________________________________ >> MSN????????????????25???????????2010????????? >> http://kaba.msn.com.cn/?k=1 >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/2ac24bc0/attachment-0001.html >> >> ------------------------------ >> >> Message: 2 >> Date: Wed, 5 May 2010 03:54:21 +0800 >> From: Yuan-Ying Chang >> Subject: [Hotspot] floorplan setting >> To: hotspot at mail.cs.virginia.edu >> Message-ID: >> >> Content-Type: text/plain; charset="iso-8859-1" >> >> Dear, >> >> Could I change the chip size in the floorplan? The original setting in >> hotspot is 0.016*0.016 m^2. >> I want to change the chip size in the floorplan, but I can't find the >> parameter to change it. >> (p.s. I use the MS Excel interface to draw floorplan.) >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100505/89634503/attachment-0001.html >> >> ------------------------------ >> >> Message: 3 >> Date: Tue, 4 May 2010 13:12:52 -0700 >> From: Karthik Sankaranarayanan >> Subject: Re: [Hotspot] floorplan setting >> To: a9051224 at st2.fju.edu.tw >> Cc: hotspot at mail.cs.virginia.edu >> Message-ID: >> >> Content-Type: text/plain; charset="iso-8859-1" >> >> Hi, >> >> The .flp files do not explicitly specify the total chip size. They only >> specify the sizes of the individual functional blocks and the total chip >> size is calculated from them. If you would like to change the chip size, >> please change the sizes of the individual functional blocks accordingly. >> >> Thanks, >> -karthik >> >> On Tue, May 4, 2010 at 12:54 PM, Yuan-Ying Chang > >wrote: >> >> > >> > Dear, >> > >> > Could I change the chip size in the floorplan? The original setting in >> > hotspot is 0.016*0.016 m^2. >> > I want to change the chip size in the floorplan, but I can't find the >> > parameter to change it. >> > (p.s. I use the MS Excel interface to draw floorplan.) >> > _______________________________________________ >> > 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/20100504/a1012be0/attachment-0001.html >> >> ------------------------------ >> >> Message: 4 >> Date: Tue, 04 May 2010 17:00:47 -0400 >> From: Kevin Skadron >> Subject: Re: [Hotspot] The power trace file >> To: hotspot at mail.cs.virginia.edu >> Message-ID: <4BE08AFF.6080003 at cs.virginia.edu> >> Content-Type: text/plain; charset=UTF-8; format=flowed >> >> You will need to use a simulator that also models power to generate >> average power per time step. Wattch (usually integrated with >> Simplescalar) is a common choice for this, although it is starting to be >> supplanted by other models. McPat is a recent one that has been >> integrated with M5. >> >> --Kevin >> >> On 5/4/2010 3:43 PM, ??? wrote: >> > Hi, >> > I'm a grad students working on thermal aware routing. Now I'm trying to >> > use Hotspot to generate temperature map. I've read the guide, two files >> > are needed for generating the temperature map. One is the .flp, and the >> > other is .ptrace. Can you tell me how to get the power trace file? I've >> > search a lot benchmarks, but I didn't find anyone having the power >> > information. >> > >> > Sincerely, >> > Yangyang >> > ------------------------------------------------------------------------ >> > ????? Windows Live Messenger ???????? ????? >> > >> > >> > >> > >> > _______________________________________________ >> > HotSpot mailing list >> > HotSpot at mail.cs.virginia.edu >> > http://www.cs.virginia.edu/mailman/listinfo/hotspot >> >> >> >> ------------------------------ >> >> _______________________________________________ >> HotSpot mailing list >> HotSpot at mail.cs.virginia.edu >> http://www.cs.virginia.edu/mailman/listinfo/hotspot >> >> >> End of HotSpot Digest, Vol 35, Issue 3 >> ************************************** >> > > > > -- > Farzad Samie > > _______________________________________________ > 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/20100521/c6ee838a/attachment.html From amin.ezhdehakosh at gmail.com Mon May 24 11:07:08 2010 From: amin.ezhdehakosh at gmail.com (Amin Ezhdehakosh) Date: Mon, 24 May 2010 19:37:08 +0430 Subject: [Hotspot] HotSpot for FPGA Message-ID: Hi, I want to use HotSpot for FPGA with grid model, grids in FPGA contain one CLB, one switch box and two connection blocks. With power, size, and location information of each tile I want to get temperature of each tile. How can I use HotSpot for this application? -- Best Regards, Amin Ezhdehakosh -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100524/2a821fb7/attachment.html From amin.ezhdehakosh at gmail.com Mon May 24 11:10:12 2010 From: amin.ezhdehakosh at gmail.com (Amin Ezhdehakosh) Date: Mon, 24 May 2010 19:40:12 +0430 Subject: [Hotspot] HotSpot for FPGA In-Reply-To: References: Message-ID: Hi, I want to use HotSpot for FPGA with grid model, grids in FPGA contain one CLB, one switch box and two connection blocks. With power, size, and location information of each tile I want to get temperature of each tile. How can I use HotSpot for this application? -- Best Regards, Amin Ezhdehakosh -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100524/b87c683a/attachment.html From wh6p at virginia.edu Mon May 24 11:59:11 2010 From: wh6p at virginia.edu (Wei Huang) Date: Mon, 24 May 2010 10:59:11 -0500 Subject: [Hotspot] HotSpot for FPGA In-Reply-To: References:

Message-ID: Hi, you would need a floorplan and some package information for your FPGA. On the HotSpot website, there is a HOW-TO section I recommend to read and try out the examples first. After that, you can use the example floorplan file, config file, and power trace file etc as templates and customize them for your own case. The email archive and FAQs on the website are also good sources for answers to common questions. -Wei On Mon, May 24, 2010 at 10:10 AM, Amin Ezhdehakosh < amin.ezhdehakosh at gmail.com> wrote: > Hi, > I want to use HotSpot for FPGA with grid model, grids in FPGA contain one > CLB, one switch box and two connection blocks. With power, size, and > location information of each tile I want to get temperature of each tile. > How can I use HotSpot for this application? > > -- > Best Regards, > Amin Ezhdehakosh > > _______________________________________________ > 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/20100524/2615df31/attachment-0001.html From krishnaks at iitkgp.ac.in Mon May 24 14:10:14 2010 From: krishnaks at iitkgp.ac.in (Krishna Kumar S) Date: Mon, 24 May 2010 23:40:14 +0530 (IST) Subject: [Hotspot] Simulation gets killed Message-ID: <50904.10.3.100.148.1274724614.squirrel@webmail.iitkgp.ac.in> Dear Prof., When I try the following command, simulation terminates with the message - Killed. hotspot -c hotspot.config -f xy.flp -p xy.ptrace -steady_file xy.steady -model_type grid What can be the reason? -- Research Scholar Dept of E & ECE Indian Institute of Technology, Kharagpur Kharagpur, West Bengal. 721302 Mob: 09476105406 09933636208 From skadron at cs.virginia.edu Mon May 24 15:09:00 2010 From: skadron at cs.virginia.edu (Kevin Skadron) Date: Mon, 24 May 2010 15:09:00 -0400 Subject: [Hotspot] Simulation gets killed In-Reply-To: <50904.10.3.100.148.1274724614.squirrel@webmail.iitkgp.ac.in> References: <50904.10.3.100.148.1274724614.squirrel@webmail.iitkgp.ac.in> Message-ID: <4BFACECC.2020601@cs.virginia.edu> There are too many possible reasons to hazard a guess. Many depend on your local setup, such as whether your environment limits are being exceeded. A good first step would be for you to run it in a debugger and see where it fails. /K On 5/24/2010 2:10 PM, Krishna Kumar S wrote: > Dear Prof., > > When I try the following command, simulation terminates with the message - > Killed. > > hotspot -c hotspot.config -f xy.flp -p xy.ptrace -steady_file xy.steady > -model_type grid > > > What can be the reason? > From bswu at yard.ee.nthu.edu.tw Mon May 24 23:34:19 2010 From: bswu at yard.ee.nthu.edu.tw (Bing-Shiou Wu) Date: Tue, 25 May 2010 11:34:19 +0800 Subject: [Hotspot] Simulation Problem Message-ID: <20100525033419.M61998@larc.ee.nthu.edu.tw> Hi, I had some problems when I did the 3D IC thermal simulation. The error message were "negative grid cell start index!\n", or "grid cell end index out of bounds!". I had succeeded in one layer lcf file simulation but failed with multi-layer lcf file. Thanks. From amin.ezhdehakosh at gmail.com Tue May 25 07:46:36 2010 From: amin.ezhdehakosh at gmail.com (Amin Ezhdehakosh) Date: Tue, 25 May 2010 16:16:36 +0430 Subject: [Hotspot] power trace file Message-ID: Hi, I want to extract FPGA thermal model. I have each tile size and power of each tile. How can I get thermal model? In power trace file for each block more than one power assigned. Could you please explain power trace file and let me know how can I extract thermal model of FPGA? -- Best Regards, Amin Ezhdehakosh -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20100525/214a64f2/attachment.html From wh6p at virginia.edu Tue May 25 10:32:23 2010 From: wh6p at virginia.edu (Wei Huang) Date: Tue, 25 May 2010 09:32:23 -0500 Subject: [Hotspot] Simulation Problem In-Reply-To: <20100525033419.M61998@larc.ee.nthu.edu.tw> References: <20100525033419.M61998@larc.ee.nthu.edu.tw> Message-ID: Hi, some common reasons: all layer must have exactly the same size; the floorplan for each must not have blank or overlapped area; layer numbers are specified... Please check if any of these are violated in your config. thanks, -Wei On Mon, May 24, 2010 at 10:34 PM, Bing-Shiou Wu wrote: > Hi, > I had some problems when I did the 3D IC thermal simulation. The error > message were "negative grid cell start index!\n", or "grid cell end index > out of bounds!". I had succeeded in one layer lcf file simulation but > failed > with multi-layer lcf file. > Thanks. > > _______________________________________________ > 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/20100525/21b49235/attachment.html From wh6p at virginia.edu Tue May 25 10:37:30 2010 From: wh6p at virginia.edu (Wei Huang) Date: Tue, 25 May 2010 09:37:30 -0500 Subject: [Hotspot] power trace file In-Reply-To: References: Message-ID: Hi, you need to have a floorplan file for your chip (see the example flp file). If you just want a steady-state temperature map, your power trace file only needs one line for block names and one line for power of each block in your floorplan. Of course you also need to set the cooling package parameters in the .config file. Hope this helps. -Wei On Tue, May 25, 2010 at 6:46 AM, Amin Ezhdehakosh < amin.ezhdehakosh at gmail.com> wrote: > Hi, > I want to extract FPGA thermal model. I have each tile size and power of > each tile. How can I get thermal model? In power trace file for each block > more than one power assigned. Could you please explain power trace file and > let me know how can I extract thermal model of FPGA? > > -- > Best Regards, > Amin Ezhdehakosh > > _______________________________________________ > 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/20100525/631b7579/attachment.html