PC configuration for fastest compiles (synthesis, place and route,etc)

Discussion in 'VHDL' started by wallge, Feb 15, 2008.

  1. wallge

    wallge Guest

    I am looking at getting a new PC for doing FPGA development.
    I mostly use the altera tools and aldec active HDL.

    I was wondering if anyone had any thoughts or comments on
    optimal PC configurations for this.

    What affects synthesis time, place and route time -

    Cache size? SDRAM speed/bandwidth ,
    amount of total SDRAM (2 vs 4 vs 8 GB main memory).
    Do 32 vs 64 bit architectures make any difference at all?
    What about CPU clock speed -
    Is the price delta from a 2.0 GHz machine to a 3.2 GHz machine
    really worth it in terms of reducing compile times?

    What about multicore? Is it possible to have too many cores?
    is there an optimal number in terms of bang for the buck?

    Are there any advantages between the various Intel or AMD
    chip architectures?

    I know similar questions have been posed before,
    but I thought it would be good to revisit this, now that we are
    seeing the PC market flooded with new multicore processors,
    and EDA tool vendors starting to parallelize their algorithms to take
    advantage of the new CPUs.
     
    wallge, Feb 15, 2008
    #1
    1. Advertising

  2. wallge

    CM Guest

    Re: PC configuration for fastest compiles (synthesis, place androute, etc)

    On Feb 16, 12:40 am, wallge <> wrote:
    > I am looking at getting a new PC for doing FPGA development.
    > I mostly use the altera tools and aldec active HDL.
    >
    > I was wondering if anyone had any thoughts or comments on
    > optimal PC configurations for this.
    >
    > What affects synthesis time, place and route time -
    >
    > Cache size? SDRAM speed/bandwidth ,
    > amount of total SDRAM (2 vs 4 vs 8 GB main memory).
    > Do 32 vs 64 bit architectures make any difference at all?
    > What about CPU clock speed -
    > Is the price delta from a 2.0 GHz machine to a 3.2 GHz machine
    > really worth it in terms of reducing compile times?
    >
    > What about multicore? Is it possible to have too many cores?
    > is there an optimal number in terms of bang for the buck?
    >
    > Are there any advantages between the various Intel or AMD
    > chip architectures?
    >
    > I know similar questions have been posed before,
    > but I thought it would be good to revisit this, now that we are
    > seeing the PC market flooded with new multicore processors,
    > and EDA tool vendors starting to parallelize their algorithms to take
    > advantage of the new CPUs.


    CPU Intel Core2 Duo E8200 / E8400
    MB ASUS P5K PRO 『http://0rz.tw/
    773vW』
    or Gigabyte EP35-DS3
    RAM 2G DDR2-800 x 2

    C2Q can do 4 QuartusII process for different versions in a project $_$
     
    CM, Feb 17, 2008
    #2
    1. Advertising

Want to reply to this thread or ask your own question?

It takes just 2 minutes to sign up (and it's free!). Just click the sign up button to choose a username and then you can ask your own questions on the forum.
Similar Threads
  1. Sridhar Hegde
    Replies:
    2
    Views:
    2,533
    Ajeetha Kumari
    Sep 13, 2004
  2. wallge
    Replies:
    2
    Views:
    1,498
    wallge
    Nov 8, 2006
  3. ec

    After Place and Route

    ec, Jan 2, 2007, in forum: VHDL
    Replies:
    3
    Views:
    482
  4. Replies:
    2
    Views:
    528
    renergy
    Nov 14, 2007
  5. Replies:
    1
    Views:
    431
    scottcarl
    Feb 18, 2008
Loading...

Share This Page