Capo: Robust and Scalable OpenSource Mincut Floorplacer

1
Capo Robust and Scalable Open-Source Min-cut
Floorplacer
http//vlsicad.eecs.umich.edu/BK/PDtools/tar.gz/LA
TEST/

• Jarrod A. Roy, David A. Papa,Saurabh N. Adya,
  Hayward H. Chan, James F. Lu, Aaron N. Ng,Igor
  L. Markov
• EECS DepartmentUniversity of Michigan, Ann Arbor

Credits for original Capo Caldwell, Kahng
Markov
2
Original Motivation (ca 2000)

• Co-developed at UCLA with Andy Caldwellunder the
  guidance of Andrew Kahng
• First fixed-die placer in the literature
• First academic placer usingmulti-level
  partitioning (MLPart)
• First academic placer in the US to compete
  heads-onwith commercial placers on large
  industrial netlists
• All code written from scratch
• Capo - an experiment in min-cut placement
• DAC 2000 Can Recursive Bisection AloneProduce
  Routable Placements ?
• Message minimizing HPWL is not enough

3
Min-cut Bisection
4
Basic Components Techniques

• Overall runtime O(P (log P)2)
• Three min-cut partitioners
• MLPart and FMPart (heur.) BBPart
  (optimal)ASPDAC 2000, JEA 2000, ISPD 98/TCAD
  01
• Capo makes several different callsto MLPart
  every time (some are Vcycling)
• Shifting cut-lines (not a grid) ASIC 98
• Optimal end-case placers (BB) ISPD 98
• Also used in detail placement RowIroning
• Uniform whitespace allocation TCAD 03
• Non-uniform whitespace allocation ICCAD 03
• Feedback / cycling (Kahng Reda, DAC 04)

5
Capos Distinctive Features(can be found in some
industry tools, but rarely in academic placers)

• Global placement with Capo often produces legal
  placements
• No cell-shifting / legalization is necessary
• Top-down estimates of cell locations and
  interconnect are very accurate
• This seems to improve generic routability
• Ensured robust handling of obstacles since 2000
• Can make any netlist routable by more generous
  floorplan (greater whitespace)
• Request uniform whitespace distribution!

Very low via counts
6
The Integration of Block-packing(using Parquet)
ICCAD 04
7
Advanced Details

• Weighted terminal propagation
• Described in a TR by Karypis Selvakkumaran
• More accurate capture of HPWL in min-cut
  partitioning
• Nets with terminals too close to cut-line have
  cost lt1
• Some orig. nets are modeled by two nets for
  min-cut
• To improve terminal propagation, usean SOR-based
  quadratic placerafter every round of
  partitioning
• Also tried ACG (Alpert, Nam Villarrubia
  ICCAD03)
• Look-ahead criteria for Parquet were sharpened

8
Recent Improvements

• Whitespace allocation rewritten entirely
• New params -minLocalWS and -safeWS
• Cutline positioning relative to obstacles
• Feature locations are corners of fixed macros
• Among those, we minimize cutlength
• Cutline direction is selected based on cutlength
• MLPart FMPart are 2x faster (loop unroling)
• Also, bugfix in Vcycling
• Also, variable-effort partitioning in Capo
• Stronger, much faster RowIroning
• Stronger macro legalizer, more scalable cell leg.
• Meta-options -faster and -tryHarder

9
Large-scale Visualization

• Example different whitespace allocation modes
• Plots of large designs with data compression
• Less than 1 bit per cell
• The plotter is in the GSRC bookshelf under
  PlaceUtils

10
Capo Memory Runtime Datawith faster (Opteron
_at_2.8GHz, Linux)
7h40m
17 mins
11
Example of Self-profiling in Capo
Adaptec 1 (250K) Big Blue 4 (2.1M)

• MLPart took 9360.9sec
  (39.25)
• FMPart took 661.4sec
  (2.77)
• BBPart took 255.3sec
  (1.07)
• SmPlace took 1727.6sec
  (7.24)
• ProblemSetup took 11365.5sec (47.66)
• SmPlProbSetup took 133.5sec (0.56)
• Level Stats took 151.2sec
  (0.63)
• Total runtime of measured components
  23657.1sec (99.2)

• MLPart took 396.06sec
  (51.58)
• FMPart took 38.29sec
  (4.99)
• BBPart took 20.13sec
  (2.62)
• SmPlace took 139.14sec
  (18.12)
• ProblemSetup took 151.01sec (19.67)
• SmPlProbSetup took 4.85sec (0.63)
• Level Stats took 10.79sec
  (1.41)
• Total runtime of measured components
  760.43sec (99.03)

RowIroning takes additional 10-15 by runtime
12
Infrastructure Availablein GSRC Bookshelf (April
2005)

• Source code binaries
• Converters Bookshelf to/from LEFDEF
• Gnuplotter with data compression
• Macro cell legalizer
• Improved stand-alone RowIroning
• Complete Capo 9.1 (with MLPart)for Linux
  (32/64), Solaris (32/64) and Windowshttp//vlsica
  d.eecs.umich.edu/BK/PDtools/
• Compatible with OpenAccess
• Ongoing work on further improvements

13
Example Whats Wrong Here?