( ESNUG 434 Item 2 ) -------------------------------------------- [11/18/04]

Subject: ( ESNUG 433 #5 ) Yet Another DC 2004.6 Nighthawk User Benchmark

> We were also able to fit our design on our 32-bit Linux boxes and got
> even faster turnaround time.
>
>                   DC 2003.06       DC 2004.06 beta Nighthawk
>                  ------------      -------------------------
>         Runtime     61 hrs                 20 hrs
>    Area (cells)    1.1 M                  1.1 M
>             WNS   -0.5 ns               -0.15 ns
>             TNS   1318 ns                -229 ns
>
> Of course nothing is for free.  We did have to make one change to our
> scripts; removed any explicit use of uniquify commands.
>
>     - Sam Bishai     
>       Cisco Systems                              Kanata, ON, Canada


From: Linming Jin <ljin=user domain=brocade spot calm>

Hi, John,

Here is our benchmark data of DC 2003.12-SP1 vs. DC 2004.06 Nighthawk:

                                                Nighthawk     Improvement
                             DC 2003.12-SP1    DC 2004.06    of Nighthawk
                             --------------    ----------   --------------
  Total Number of Nets           39072              33545        14.1%
  Leaf Cell Count                33515              28122        16.1%
  Reference Cell Count             251                267         6.4%
  Combinational Area            252759             242610         4.0%
  Noncombinational Area        2000381            1998169         0.1%
  Cell Area                    2253140            2240779         0.5%
  Runtime                         6798               9056       -33.2% (worse)

  Timing Path Group 'CLK1'
  Levels of Logic                   35                 30        14.3%
  Critical Path Length           2.551               2.33         8.7%
  Critical Path Slack           -0.423              -0.21        50.4%
  Total Negative Slack        -172.392              -57.5        66.6%
  No. of Violating Paths          1026                479        53.3%

  Timing Path Group 'CLK2'
  Levels of Logic                   16                 15         6.3%
  Critical Path Length           1.023               1.04        -1.7% (worse)
  Critical Path Slack           -0.417              -0.43        -3.1% (worse)
  Total Negative Slack         -17.947             -11.94        33.5%
  No. of Violating Paths           132                 80        39.4%

  Timing Path Group 'CLK3'
  Levels of Logic                   17                 14         17.6%
  Critical Path Length           2.754                2.7          2.0%
  Critical Path Slack           -0.625              -0.59          5.6%
  Total Negative Slack        -134.336            -148.73        -10.7% (worse)
  No. of Violating Paths           362                344          5.0%

  Timing Path Group 'CLK4'
  Levels of Logic                   22                 10          54.5%
  Critical Path Length           2.132               2.12           0.6%
  Critical Path Slack           -0.099              -0.02          79.8%
  Total Negative Slack          -7.756              -0.52          93.3%
  No. of Violating Paths           126                 26          79.4%


The runtime of 2004.06 Nighthawk was actually longer in our test, but it
has improved in most other areas.

    - Linming Jin
      Brocade Communications                     San Jose, CA


 Sign up for the DeepChip newsletter.
Email
 Read what EDA tool users really think.


Feedback About Wiretaps ESNUGs SIGN UP! Downloads Trip Reports Advertise

"Relax. This is a discussion. Anything said here is just one engineer's opinion. Email in your dissenting letter and it'll be published, too."
This Web Site Is Modified Every 2-3 Days
Copyright 1991-2024 John Cooley.  All Rights Reserved.
| Contact John Cooley | Webmaster | Legal | Feedback Form |

   !!!     "It's not a BUG,
  /o o\  /  it's a FEATURE!"
 (  >  )
  \ - / 
  _] [_     (jcooley 1991)