From ks4kk at cs.virginia.edu  Tue Feb  3 07:29:32 2009
From: ks4kk at cs.virginia.edu (Karthik Sankaranarayanan)
Date: Tue, 3 Feb 2009 10:29:32 -0500 (EST)
Subject: [Hotspot] Grid cell end index out of bounds
In-Reply-To: <959353.61627.qm@web53707.mail.re2.yahoo.com>
References: <959353.61627.qm@web53707.mail.re2.yahoo.com>
Message-ID: <Pine.SOC.4.64.0902031027210.18001@cobra.cs.Virginia.EDU>


Hi Mohamed,

Thanks a lot for sharing the tool with the community. It would definitely 
be helpful to those working with HotSpot and Matlab.

Sincerely,
-karthik

On Tue, 3 Feb 2009, Mohamed Elsawaf wrote:

> Hi Karthik
>
> I would like to share modified script that convert floor-plan into Matlab format. [attached]
> you can troubleshoot the block over lap using Matlab tools.
>
> Thank you
> M Elsawaf
> --- On Sat, 1/17/09, Karthik Sankaranarayanan <ks4kk at cs.virginia.edu> wrote:
> From: Karthik Sankaranarayanan <ks4kk at cs.virginia.edu>
> Subject: Re: [Hotspot] Grid cell end index out of bounds
> To: "Mohamed Elsawaf" <mohamed_elsawaf at yahoo.com>
> Cc: hotspot at mail.cs.virginia.edu
> Date: Saturday, January 17, 2009, 9:23 AM
>
> In the description about a correct floorplan, I forgot to mention the condition
> that the area of the individual rectangles should add up to the area of the
> envelop rectangle (the die). This basically means that there should not be any
> gaps or overlaps in your floorplan.
>
> Thanks,
> -karthik
>
>
> On Sat, 17 Jan 2009, Karthik Sankaranarayanan wrote:
>
>>
>> Hi Mohamed,
>>
>> No special floorplan is needed for the grid model - just the normal
> rectangular blocks would do. Just make sure there are no overlaps between the
> individual rectangles and that the envelop of all the rectangles is also a
> rectangle.
>>
>> The block model assumes that the floorplan is OK (in the sense described
> above) and proceeds with its calculations while the grid model checks the
> floorplan before proceeding (when mapping it onto a grid). So, if the floorplan
> was erroneous, the block model would not have caught it (actually, a
> non-overlapping floorplan is a precondition for HotSpot).
>>
>> Please read the HOWTO file
> (http://lava.cs.virginia.edu/HotSpot/HotSpot-HOWTO.htm) - it mentions the
> command line to explain the use of tofig.pl. The output of tofig.pl is in the
> .fig format which can be viewed using the XFig software. It can also be
> converted into other formats.
>>
>> Hope this helps
>> -karthik
>>
>> On Sat, 17 Jan 2009, Mohamed Elsawaf wrote:
>>
>>> Hi Karthik
>>>
>>> it is really strange that grid mode see that i have overlapping
> functional blocks while block mode working ok! How grid mode is expecting
> functional blocks shapes? As the current functional block are rectangular not
> squares or multiple of square Do i need to plot floor-plan as grid cells?  ?
>>>
>>> I used tofig.pl tool but i don't know how to use its output to
> plot my floor-plan, can you please send me more details? waiting for your
> feedback. Thank you M. Elsawaf
>>>
>>> --- On Fri, 1/16/09, Karthik Sankaranarayanan
> <ks4kk at cs.virginia.edu> wrote:
>>> From: Karthik Sankaranarayanan <ks4kk at cs.virginia.edu>
>>> Subject: Re: [Hotspot] Grid cell end index out of bounds
>>> To: "Mohamed Elsawaf" <mohamed_elsawaf at yahoo.com>
>>> Cc: hotspot at mail.cs.virginia.edu
>>> Date: Friday, January 16, 2009, 8:02 AM
>>>
>>> Hi Mohamed,
>>>
>>> It appears that your floorplan might have overlapping functional
> blocks.
>>> You can use tofig.pl tool to plot your floorplan and correct any
> errors
>>> that might be in the floorplan.
>>>
>>> -karthik
>>>
>>>
>>>
>>> On Fri, 16 Jan 2009, Mohamed Elsawaf wrote:
>>>
>>>> HiI have problem running grid mode, the simulation is working OK
> with
>>> block mode.
>>>>
>>>> I got below warning at grid mode:?
>>>>
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>> warning: overlap of functional blocks?
>>>>
>>>> then below error
>>>>
>>>>
>>>> error: grid cell end index out of bounds!
>>>>
>>>>
>>>> I managed to avoid warning message by decreasing cols to 16
> [-grid_cols
>>> 16] while keeping row 1024 [-grid_row 1024]
>>>> but still getting same error
>>>>
>>>> error: grid cell end index out of bounds!
>>>> Note: number of warning increase by increasing number of cols
>>>> please advise
>>>>
>>>> Thank you
>>>> M. Elsawaf
>>>>
>>>>
>>>>
>>

From mohamed_elsawaf at yahoo.com  Tue Feb  3 06:52:12 2009
From: mohamed_elsawaf at yahoo.com (Mohamed Elsawaf)
Date: Tue, 3 Feb 2009 06:52:12 -0800 (PST)
Subject: [Hotspot] Grid cell end index out of bounds
In-Reply-To: <Pine.SOC.4.64.0901171120450.5053@cobra.cs.Virginia.EDU>
Message-ID: <959353.61627.qm@web53707.mail.re2.yahoo.com>

Hi Karthik

I would like to share modified script that convert floor-plan into Matlab format. [attached]
you can troubleshoot the block over lap using Matlab tools.

Thank you
M Elsawaf
--- On Sat, 1/17/09, Karthik Sankaranarayanan <ks4kk at cs.virginia.edu> wrote:
From: Karthik Sankaranarayanan <ks4kk at cs.virginia.edu>
Subject: Re: [Hotspot] Grid cell end index out of bounds
To: "Mohamed Elsawaf" <mohamed_elsawaf at yahoo.com>
Cc: hotspot at mail.cs.virginia.edu
Date: Saturday, January 17, 2009, 9:23 AM

In the description about a correct floorplan, I forgot to mention the condition
that the area of the individual rectangles should add up to the area of the
envelop rectangle (the die). This basically means that there should not be any
gaps or overlaps in your floorplan.

Thanks,
-karthik


On Sat, 17 Jan 2009, Karthik Sankaranarayanan wrote:

> 
> Hi Mohamed,
> 
> No special floorplan is needed for the grid model - just the normal
rectangular blocks would do. Just make sure there are no overlaps between the
individual rectangles and that the envelop of all the rectangles is also a
rectangle.
> 
> The block model assumes that the floorplan is OK (in the sense described
above) and proceeds with its calculations while the grid model checks the
floorplan before proceeding (when mapping it onto a grid). So, if the floorplan
was erroneous, the block model would not have caught it (actually, a
non-overlapping floorplan is a precondition for HotSpot).
> 
> Please read the HOWTO file
(http://lava.cs.virginia.edu/HotSpot/HotSpot-HOWTO.htm) - it mentions the
command line to explain the use of tofig.pl. The output of tofig.pl is in the
.fig format which can be viewed using the XFig software. It can also be
converted into other formats.
> 
> Hope this helps
> -karthik
> 
> On Sat, 17 Jan 2009, Mohamed Elsawaf wrote:
> 
>> Hi Karthik
>> 
>> it is really strange that grid mode see that i have overlapping
functional blocks while block mode working ok! How grid mode is expecting
functional blocks shapes? As the current functional block are rectangular not
squares or multiple of square Do i need to plot floor-plan as grid cells?  ?
>> 
>> I used tofig.pl tool but i don't know how to use its output to
plot my floor-plan, can you please send me more details? waiting for your
feedback. Thank you M. Elsawaf
>> 
>> --- On Fri, 1/16/09, Karthik Sankaranarayanan
<ks4kk at cs.virginia.edu> wrote:
>> From: Karthik Sankaranarayanan <ks4kk at cs.virginia.edu>
>> Subject: Re: [Hotspot] Grid cell end index out of bounds
>> To: "Mohamed Elsawaf" <mohamed_elsawaf at yahoo.com>
>> Cc: hotspot at mail.cs.virginia.edu
>> Date: Friday, January 16, 2009, 8:02 AM
>> 
>> Hi Mohamed,
>> 
>> It appears that your floorplan might have overlapping functional
blocks.
>> You can use tofig.pl tool to plot your floorplan and correct any
errors
>> that might be in the floorplan.
>> 
>> -karthik
>> 
>> 
>> 
>> On Fri, 16 Jan 2009, Mohamed Elsawaf wrote:
>> 
>>> HiI have problem running grid mode, the simulation is working OK
with
>> block mode.
>>> 
>>> I got below warning at grid mode:?
>>> 
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> warning: overlap of functional blocks?
>>> 
>>> then below error
>>> 
>>> 
>>> error: grid cell end index out of bounds!
>>> 
>>> 
>>> I managed to avoid warning message by decreasing cols to 16
[-grid_cols
>> 16] while keeping row 1024 [-grid_row 1024]
>>> but still getting same error
>>> 
>>> error: grid cell end index out of bounds!
>>> Note: number of warning increase by increasing number of cols
>>> please advise
>>> 
>>> Thank you
>>> M. Elsawaf
>>> 
>>> 
>>> 
> 


      
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20090203/b293d797/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: to_matlab_drawing_R4.pl
Type: application/octet-stream
Size: 3220 bytes
Desc: not available
Url : http://www.cs.virginia.edu/pipermail/hotspot/attachments/20090203/b293d797/attachment-0001.obj 

From eb5237 at wayne.edu  Sat Feb  7 07:04:43 2009
From: eb5237 at wayne.edu (pradeep hettiarachchi)
Date: Sat, 7 Feb 2009 07:04:43 -0800
Subject: [Hotspot] Profiling
Message-ID: <8fe204b0902070704u5e36a257xb28a93a51314b229@mail.gmail.com>

Dear Sir,
I am a graduate student at Wayne State University, studying your wonderful
software package to gain more knowledge about architecture
aware thermal management techniques. The question I have is how do you
profile a given software piece to generate its thermal behavior? In other
words, if I want to analyze the thermal behavior of some application as you
have done in the "Table 2. Benchmark summary. "I" = integer, "F" = floating
point"  in your Paper for various applications, how do you decompose the
given application(say gzip) into instruction level, provided the source code
is not available? Do you assume that the machine instruction generated from
the binary will run in the same frequency as they listed in
the relevant profile file or your have different technique to generate the
profile file?
Assume that I want to find the thermal behavior of the processor when my
particular application ( say "tman' ) is running. what steps I should
follow, if I have source codes/ dont have source codes?
I appreciate your kind reply for my problem.


Thanking you,




Sincerely,

Pradeep M. Hettiarachchi
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20090207/ae0bbf20/attachment.html 

From fostertaz at access.ee.ntu.edu.tw  Thu Feb 19 05:41:53 2009
From: fostertaz at access.ee.ntu.edu.tw (=?Big5?B?pP2vRaZ0Zm9zdGVydGF6?=)
Date: Thu, 19 Feb 2009 21:41:53 +0800
Subject: [Hotspot] Integration with a cycle-based simulator
Message-ID: <a12acee80902190541l4390c570ya084372f13600ca5@mail.gmail.com>

Hi.

I wish to get every transient temperature of a fixed sampling period in my
cycle-based simulator.
My simulator generates an average power and inputs this power value to
HotSpot every 1000 cycles.
But how could I pass the current temperature to the next simulation of
HotSpot?

For now I've tried to use the original function in HotSpot, which is

*dump_temp(model, temp, "next.init");
*//the "model" and "temp" is the same variable in original code

Then "next.init" will be the initial transient temperature of next
simualtion.
Is my approach to get every transient temperature correct?

Thanks in advance.

Foster Wang
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20090219/10bd1542/attachment.html 

From wh6p at cms.mail.virginia.edu  Thu Feb 19 07:06:27 2009
From: wh6p at cms.mail.virginia.edu (Wei Huang)
Date: Thu, 19 Feb 2009 10:06:27 -0500
Subject: [Hotspot] Integration with a cycle-based simulator
In-Reply-To: <a12acee80902190541l4390c570ya084372f13600ca5@mail.gmail.com>
References: <a12acee80902190541l4390c570ya084372f13600ca5@ma
 il.gmail.com>
Message-ID: <8F16D1851DC9637F8CBBD56C@mstu1>

Hello Foster,

We have a simple example showing a template of how to use 
HotSpot. Please have a look at sim-template.c and related 
files. README files and archived emails from this mailing 
list also have some related information.

Hope this is helpful.
-Wei


--On Thursday, February 19, 2009 9:41 PM +0800 
"=?Big5?B?pP2vRaZ0Zm9zdGVydGF6?=" 
<fostertaz at access.ee.ntu.edu.tw> wrote:

> Hi.
>
> I wish to get every transient temperature of a fixed
> sampling period in my cycle-based simulator.
> My simulator generates an average power and inputs this
> power value to HotSpot every 1000 cycles.
> But how could I pass the current temperature to the next
> simulation of HotSpot?
>
> For now I've tried to use the original function in
> HotSpot, which is
>
> dump_temp(model, temp, "next.init");
> //the "model" and "temp" is the same variable in original
> code
>
> Then "next.init" will be the initial transient
> temperature of next simualtion.
> Is my approach to get every transient temperature correct?
>
> Thanks in advance.
>
> Foster Wang





From shervin at ucsd.edu  Wed Feb 25 12:58:24 2009
From: shervin at ucsd.edu (Shervin Sharifi)
Date: Wed, 25 Feb 2009 12:58:24 -0800
Subject: [Hotspot] HotSpot
Message-ID: <f73279680902251258m536b8a7csdd2443eb7f2abfe3@mail.gmail.com>

I would like to use HotSpot for embedded processors. Does anybody have any
sample config files for embedded processors so that I can get an idea of the
thermal characteristics of the heat spreader, interface material, etc. used
in embedded processors?

Thanks
  Shervin
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.cs.virginia.edu/pipermail/hotspot/attachments/20090225/52c00cfb/attachment.html 

From wh6p at cms.mail.virginia.edu  Wed Feb 25 13:18:32 2009
From: wh6p at cms.mail.virginia.edu (Wei Huang)
Date: Wed, 25 Feb 2009 16:18:32 -0500
Subject: [Hotspot] HotSpot
In-Reply-To: <f73279680902251258m536b8a7csdd2443eb7f2abfe3@mail.gmail.com>
References: <f73279680902251258m536b8a7csdd2443eb7f2abfe3@ma
 il.gmail.com>
Message-ID: <33A4BFC6FA27B634C3073CB0@mstu1>

Hi Shervin,

Embedded processors can have different applications and 
different power and thermal budgets. Their cooling methods 
are also all over the places. Does your embedded processor 
have a high-performance cooling package or just use natural 
convection?

If it has something like a heatpipe or heatsink, then it is 
relatively easy to configure HotSpot to model that. 
Basically you can "remove" the heatsink by making it very 
thin, and apply the proper convection thermal resistance.

If natural convection is used, then you need to consider 
the heat transfer path from silicon to PCB. We are working 
on a new release with that heat transfer path and natural 
convection, planning to release it in the near future.

Hope this is helpful.

-Wei

--On Wednesday, February 25, 2009 12:58 PM -0800 Shervin 
Sharifi <shervin at ucsd.edu> wrote:

> I would like to use HotSpot for embedded processors.?
> Does anybody have any sample config files for embedded
> processors so that I can get an idea of the thermal
> characteristics of the heat spreader, interface material,
> etc. used in embedded processors??
>
>
>
> Thanks
> ??Shervin