Re: Dope-Vectors for low energy compliers

sumesh <>
17 Mar 2002 23:10:08 -0500

          From comp.compilers

Related articles
Dope-Vectors for low energy compliers (Manish Verma) (2002-03-11)
Re: Dope-Vectors for low energy compliers (sumesh) (2002-03-17)
Re: Dope-Vectors for low energy compliers (2002-03-19)
| List of all articles for this month |

From: sumesh <>
Newsgroups: comp.compilers
Date: 17 Mar 2002 23:10:08 -0500
Organization: The George Washington University
References: 02-03-055
Keywords: storage, optimize
Posted-Date: 17 Mar 2002 23:10:08 EST

There has been some reserach already on the data allocation problem at the
level of an array . I guess data /source transformations can be used to
achieve a finer granularity .

  A few papers you might want to look at vs On chip memory : the data partitioning problem in embedded
processor based systems
by preeti ranjan panda et al university of california , irvie

2.memory energy mangement using software and hardware directed power control
delaluz et al
pennsylvania state university


"Manish Verma" <> wrote in message
> I am Phd student working on Low Energy Compilers and I have the
> following ques tion. Why do we need to store the Array(Data) in
> consecutive memory areas. We co uld use something like Dope-Vectors
> (the way HPF/Fortran uses) and then divide the array on different
> memories( Scratch-pad or main memory). I need help as I am confused
> as how to do this allocation and when is it worthwhile to do divide
> the data or rather is it worthwhile to divide the data. And try to
> optimise energy.

Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.