From wh6p at cms.mail.virginia.edu  Thu Aug 13 15:15:46 2009
From: wh6p at cms.mail.virginia.edu (Wei Huang)
Date: Thu, 13 Aug 2009 18:15:46 -0400
Subject: [Hotspot] Convection capacitance
In-Reply-To: <7281f8250908131459s4f211cdat9b19ef43df52ea2b@mail.gmail.com>
References: <7281f8250907301207j220fa757kf8b7866904981545@mail.gmail.com>
	<E67A47C9960BFAEF21A9D7DA@10.41.1.239>
	<7281f8250908131459s4f211cdat9b19ef43df52ea2b@mail.gmail.com>
Message-ID: <web-6986040@neon.mail.virginia.edu>

Hi Saranya,

If you are interested in the package warmup phase, all you need to do is 
just to set the initial temperatures to ambient temperature, and provide the 
power trace. But you might need a LONG simulation to catch the details. 
However, if you are only interested in a relatively coarser time granularity 
(for example, every second), you may want to set the sampling rate in 
hotspot.config to a larger value (say 0.1 second or something like that). As 
for the thermal cap for Virtex FPGA, I guess I can't help with more details. 
You'll have to find the dimensions and packaging material properties. 
Ballpark numbers should work reasonably well as long as you are not actually 
the designer for the Virtex package :)

Let me know if you have further questions. Good luck.

-Wei

On Thu, 13 Aug 2009 15:59:16 -0600
  saranya chandrasekaran <saran86in at gmail.com> wrote:
> Hi Wei,
> 
> Thanks for your reply!
> 
> I am interested in knowing the warm-up phase thermal response. Is there a
> general function to obtain the temperature increase during the initial
> warm-up phase that I can use for my simulation?
> 
> If not, how do I use HotSpot to obtain the thermal response from the time 
>I
> switch on the chip till it attains the steady state temperature? ( I would
> need to know the thermal cap of the package, is there a rough estimation 
>for
> Virtex device?).
> 
> Thanks
> Saranya
> 
> On Thu, Jul 30, 2009 at 1:21 PM, Wei Huang 
><wh6p at cms.mail.virginia.edu>wrote:
> 
>> Hi Saranya,
>>
>> It is probably difficult to find thermal capacitance value in the package
>> datasheet. But you can estimate it by knowing the dimensions of the 
>>package,
>> and the material of the package (specific heat and density). Usually, the
>> thermal cap of package is quite big compared to silicon thermal cap, and
>> hence of less interest unless you want to know the long-term transient
>> thermal response during the warmup phase (tens of seconds to minutes).
>>
>> Hope this is helpful.
>>
>> Wei
>>
>>
>> --On Thursday, July 30, 2009 1:07 PM -0600 saranya chandrasekaran <
>> saran86in at gmail.com> wrote:
>>
>>  Hi,
>>>
>>> I'm trying to obtain the temperature values of Xilinx's
>>> Virtex 4 FPGA using HotSpot, quite similar to the lines
>>> of this paper
>>> http://www.cs.virginia.edu/~skadron/Papers/iccd05_siva.pd<http://www.cs.virginia.edu/%7Eskadron/Papers/iccd05_siva.pd>
>>> f which uses Virtex 2 Pro. I'm not quite sure what the
>>> convection capacitance is (I searched the datasheet and
>>> couldnt get the information) or how it is to be
>>> calculated for this FPGA device. Can you please help me
>>> with this query.
>>>
>>> Thanks
>>> Saranya
>>>
>>
>>
>>
>>
>>

Wei Huang, PhD
Postdoctoral Researcher
Dept. of Computer Science
University of Virginia
Charlottesville, VA 22904

From zhwang at cise.ufl.edu  Fri Aug 14 19:43:45 2009
From: zhwang at cise.ufl.edu (Zhe Wang)
Date: Fri, 14 Aug 2009 22:43:45 -0400
Subject: [Hotspot] What is gcc.ptrace file?
Message-ID: <4A8620E1.2040905@cise.ufl.edu>

Hello,
    I am new to Hotspot. Can anyone tell me what gcc.ptrace file( power 
trace) means? Is there any documents talking about the content of this file?

    Thanks very much.

Neil

From skadron at cs.virginia.edu  Mon Aug 17 06:32:54 2009
From: skadron at cs.virginia.edu (Kevin Skadron)
Date: Mon, 17 Aug 2009 09:32:54 -0400
Subject: [Hotspot] What is gcc.ptrace file?
In-Reply-To: <4A8620E1.2040905@cise.ufl.edu>
References: <4A8620E1.2040905@cise.ufl.edu>
Message-ID: <4A895C06.9050505@cs.virginia.edu>

This is a trace of average power dissipated in each unit over each 
timestep.  Each line is a new timestep (corresponding to whatever 
timestep you specify when running HotSpot--of course this means the 
power trace should be collected at the same sampling rate).

Please see the "How-To" section of the HotSpot website for more info.

/K

Zhe Wang wrote:
> Hello,
>     I am new to Hotspot. Can anyone tell me what gcc.ptrace file( power 
> trace) means? Is there any documents talking about the content of this file?
> 
>     Thanks very much.
> 
> Neil
> _______________________________________________
> HotSpot mailing list
> HotSpot at mail.cs.virginia.edu
> http://www.cs.virginia.edu/mailman/listinfo/hotspot

From zhwang at cise.ufl.edu  Tue Aug 18 15:52:48 2009
From: zhwang at cise.ufl.edu (Zhe Wang)
Date: Tue, 18 Aug 2009 18:52:48 -0400
Subject: [Hotspot] What is gcc.ptrace file?
In-Reply-To: <4A895C06.9050505@cs.virginia.edu>
References: <4A8620E1.2040905@cise.ufl.edu> <4A895C06.9050505@cs.virginia.edu>
Message-ID: <4A8B30C0.3060003@cise.ufl.edu>

Hey, thank you guys for the replies. Really help a lot.

Neil
Kevin Skadron wrote:
> This is a trace of average power dissipated in each unit over each 
> timestep.  Each line is a new timestep (corresponding to whatever 
> timestep you specify when running HotSpot--of course this means the 
> power trace should be collected at the same sampling rate).
>
> Please see the "How-To" section of the HotSpot website for more info.
>
> /K
>
> Zhe Wang wrote:
>> Hello,
>>     I am new to Hotspot. Can anyone tell me what gcc.ptrace file( 
>> power trace) means? Is there any documents talking about the content 
>> of this file?
>>
>>     Thanks very much.
>>
>> Neil
>> _______________________________________________
>> HotSpot mailing list
>> HotSpot at mail.cs.virginia.edu
>> http://www.cs.virginia.edu/mailman/listinfo/hotspot
>