Integration of Retiming with Architectural Floorplanning: A New Design Methodology for DSM Abdallah and Bassam Tabbara Profs: R.K.Brayton, A.R.Newton,

Slides:



Advertisements
Similar presentations
SoC Challenges & Transaction Level Modeling (TLM) Dr. Eng. Amr T. Abdel-Hamid ELECT 1002 Spring 2008 System-On-a-Chip Design.
Advertisements

THERMAL-AWARE BUS-DRIVEN FLOORPLANNING PO-HSUN WU & TSUNG-YI HO Department of Computer Science and Information Engineering, National Cheng Kung University.
TOPIC : SYNTHESIS DESIGN FLOW Module 4.3 Verilog Synthesis.
Dan Lander Haru Yamamoto Shane Erickson (EE 201A Spring 2004)
ECOE 560 Design Methodologies and Tools for Software/Hardware Systems Spring 2004 Serdar Taşıran.
Courtesy RK Brayton (UCB) and A Kuehlmann (Cadence) 1 Logic Synthesis Sequential Synthesis.
1 Physical Hierarchy Generation with Routing Congestion Control Chin-Chih Chang *, Jason Cong *, Zhigang (David) Pan +, and Xin Yuan * * UCLA Computer.
The Design Process Outline Goal Reading Design Domain Design Flow
1 HW/SW Partitioning Embedded Systems Design. 2 Hardware/Software Codesign “Exploration of the system design space formed by combinations of hardware.
CS244-Introduction to Embedded Systems and Ubiquitous Computing Instructor: Eli Bozorgzadeh Computer Science Department UC Irvine Winter 2010.
A Timing-Driven Soft-Macro Resynthesis Method in Interaction with Chip Floorplanning Hsiao-Pin Su 1 2 Allen C.-H. Wu 1 Youn-Long Lin 1 1 Department of.
abk C.A.D. Agenda u Roadmapping: “Living Roadmaps” for systems u SiP physical implementation platforms (CLC, SOS) s Tools needs u Interfaces and.
Fixed-outline Floorplanner (Parquet) A constraint satisfaction problem “Parquet” based on “floorplan slack” Use better local search to satisfy constraints.
Architecture and Routing for NoC-based FPGA Israel Cidon* *joint work with Roman Gindin and Idit Keidar.
Merging Synthesis With Layout For Soc Design -- Research Status Jinian Bian and Hongxi Xue Dept. Of Computer Science and Technology, Tsinghua University,
Processing Rate Optimization by Sequential System Floorplanning Jia Wang 1, Ping-Chih Wu 2, and Hai Zhou 1 1 Electrical Engineering & Computer Science.
The Memory/Logic Interface in FPGA’s with Large Embedded Memory Arrays The Memory/Logic Interface in FPGA’s with Large Embedded Memory Arrays Steven J.
User Programmable Logic Device: Architecture and CAD Tools TingTing Hwang and C. L. Liu.
Threshold Voltage Assignment to Supply Voltage Islands in Core- based System-on-a-Chip Designs Project Proposal: Gall Gotfried Steven Beigelmacher 02/09/05.
From Concept to Silicon How an idea becomes a part of a new chip at ATI Richard Huddy ATI Research.
Placement-Centered Research Directions and New Problems Xiaojian Yang Amir Farrahi Synplicity Inc.
Combining High Level Synthesis and Floorplan Together EDA Lab, Tsinghua University Jinian Bian.
ECE 506 Reconfigurable Computing Lecture 8 FPGA Placement.
Hierarchical Physical Design Methodology for Multi-Million Gate Chips Session 11 Wei-Jin Dai.
Design methodology.
1 Chapter 2. The System-on-a-Chip Design Process Canonical SoC Design System design flow The Specification Problem System design.
EZ-COURSEWARE State-of-the-Art Teaching Tools From AMS Teaching Tomorrow’s Technology Today.
ISE. Tatjana Petrovic 249/982/22 ISE software tools ISE is Xilinx software design tools that concentrate on delivering you the most productivity available.
CSE 242A Integrated Circuit Layout Automation Lecture: Partitioning Winter 2009 Chung-Kuan Cheng.
CAD Techniques for IP-Based and System-On-Chip Designs Allen C.-H. Wu Department of Computer Science Tsing Hua University Hsinchu, Taiwan, R.O.C {
ECO Methodology for Very High Frequency Microprocessor Sumit Goswami, Srivatsa Srinath, Anoop V, Ravi Sekhar Intel Technology, Bangalore, India Introduction.
CAD for Physical Design of VLSI Circuits
Lecture 17 Lecture 17: Platform-Based Design and IP ECE 412: Microcomputer Laboratory.
10/7/ VLSI Physical Design Automation Prof. David Pan Office: ACES Lecture 6. Floorplanning (1)
ASIC Design Flow – An Overview Ing. Pullini Antonio
Lessons Learned The Hard Way: FPGA  PCB Integration Challenges Dave Brady & Bruce Riggins.
Modern VLSI Design 3e: Chapters 1-3 week12-1 Lecture 30 Scale and Yield Mar. 24, 2003.
Computer-Aided Design of Digital VLSI Circuits & Systems Priyank Kalla Dept. of Elec. & Comp. Engineering University of Utah,SLC Perspectives on Next-Generation.
CMOS Design Methods.
New Modeling Techniques for the Global Routing Problem Anthony Vannelli Department of Electrical and Computer Engineering University of Waterloo Waterloo,
HDL-Based Layout Synthesis Methodologies Allen C.-H. Wu Department of Computer Science Tsing Hua University Hsinchu, Taiwan, R.O.C {
FPGA-Based System Design: Chapter 6 Copyright  2004 Prentice Hall PTR Topics n Design methodologies.
Thermal-aware Steiner Routing for 3D Stacked ICs M. Pathak and S.K. Lim Georgia Institute of Technology ICCAD 07.
CSE 494: Electronic Design Automation Lecture 2 VLSI Design, Physical Design Automation, Design Styles.
Massachusetts Institute of Technology 1 L14 – Physical Design Spring 2007 Ajay Joshi.
Chonnam national university VLSI Lab 8.4 Block Integration for Hard Macros The process of integrating the subblocks into the macro.
L11: Lower Power High Level Synthesis(2) 성균관대학교 조 준 동 교수
Placement. Physical Design Cycle Partitioning Placement/ Floorplanning Placement/ Floorplanning Routing Break the circuit up into smaller segments Place.
VLSI Physical Design: From Graph Partitioning to Timing Closure Chapter 6: Detailed Routing © KLMH Lienig 1 What Makes a Design Difficult to Route Charles.
CS244-Introduction to Embedded Systems and Ubiquitous Computing Instructor: Eli Bozorgzadeh Computer Science Department UC Irvine Winter 2010.
TOPIC : SYNTHESIS INTRODUCTION Module 4.3 : Synthesis.
EE 466/586 VLSI Design Partha Pande School of EECS Washington State University
ECE 260B – CSE 241A /UCB EECS Kahng/Keutzer/Newton Physical Design Flow Read Netlist Initial Placement Placement Improvement Cost Estimation Routing.
CHAPTER 8 Developing Hard Macros The topics are: Overview Hard macro design issues Hard macro design process Physical design for hard macros Block integration.
System-level power analysis and estimation September 20, 2006 Chong-Min Kyung.
1 Copyright  2001 Pao-Ann Hsiung SW HW Module Outline l Introduction l Unified HW/SW Representations l HW/SW Partitioning Techniques l Integrated HW/SW.
FPGA CAD 10-MAR-2003.
A New Design Methodology for DSM Abdallah Tabbara Bassam Tabbara Robert K. Brayton, A. Richard Newton, Kurt Keutzer GSRC NexSIS Group University of California.
A Design Flow for Optimal Circuit Design Using Resource and Timing Estimation Farnaz Gharibian and Kenneth B. Kent {f.gharibian, unb.ca Faculty.
Architecture and algorithm for synthesizable embedded programmable logic core Noha Kafafi, Kimberly Bozman, Steven J. E. Wilton 2003 Field programmable.
CAD for VLSI Ramakrishna Lecture#2.
1 Floorplanning of Pipelined Array (FoPA) Modules using Sequence Pairs Matt Moe Herman Schmit.
Interconnect Characteristics of 2.5-D System Integration Scheme Yangdong (Steven) Deng & Wojciech P. Maly
1/29 UTDSP: A VLIW Programmable DSP Processor Sean Hsien-en Peng Department of Electrical and Computer Engineering University of Toronto October 26 th,
RTL Design Flow RTL Synthesis HDL netlist logic optimization netlist Library/ module generators physical design layout manual design a b s q 0 1 d clk.
VLSI Design Flow The Y-chart consists of three major domains:
EMT 351/4 DIGITAL IC DESIGN Week # 1 EDA & HDL.
Partial Reconfigurable Designs
Incremental Placement Algorithm for Field Programmable Gate Arrays
EDA Lab., Tsinghua University
Presentation transcript:

Integration of Retiming with Architectural Floorplanning: A New Design Methodology for DSM Abdallah and Bassam Tabbara Profs: R.K.Brayton, A.R.Newton, and K.Keutzer The NexSIS Project

2 Issues in DSM timing at the module level not an issue timing at the chip level is an issue bigger raw capacity that can be used by: àreplication àreuse NTRS Projections: à1997:.25u4M tr/cm pins6 layers 3cm 2 à2006:.1u40M tr/cm pins8 layers 10cm 2

3 Problem Description one-level hierarchy of design àminimum number of levels to support reuse àmid way between flat and two level placement and wireplanning of: à modules, average size: 50k gates àdynamic range of modules sizes: 1-500k gates àtypes of modules: hard, firm, soft hard: layout firm: gates + aspect ratio soft: RTL àlarge number of nets: 40k-100k àpins per module:

4 Problem Statement We address chip level assembly of predesigned IP blocks, each under 100k gates in size, either as hard or soft macros, optimizing for performance, power and area (emphasis in that order).

5 Goals develop a tool that has an impact in DSM by supporting IP reuse handle IP blocks that have constraints and should be combined to result in a certain functionality. User design constraints include: àdelay àpower dissipation àarea generate a final layout within hours (overnight) àcomplexity of algorithms within O(m 2 ) -O(m 3 ) m = design complexity final result should: àbe within 5-10% of human design (may not be able to compare) àmeet the user constraints if possible or make design suggestions

6 Challenges size issues: àbigger block sizes, aspect ratios and relative sizes ànumber of pins, nets much bigger than blocks placement issues: àspecial design for memories? àpartitioning hard, clustering easy routing issues: àno channels, point to point àbusses àmany metal layers to be assigned àtiming at the chip level

7 Conventional Flows integration of various steps and tools: àLogic Synthesis - Physical Design àGlobal - Detailed separation of concerns: àfront end - back end àno contract separation entails hundreds of iterations: ànumber of iterations can be proportional to complexity of design

8 Conventional Flow Architecture

9 New Design Flow minimize design iteration: àplanning at the early stages of the flow àsupport incremental changes àneed for a proof of convergence introduce retiming into the architectural floorplanning stage àbetter handle on timing issues àpath-based vs. net-based

10 Design Flow Architecture

11 Functional Decomposition provides an entry point for reused IPs àRTL may already be well characterized àarea-delay trade-off as an important performance characteristic result is: àa set of blocks àsome area-delay trade-off estimates

12 Retiming takes in lower bound constraints creates upper bound constraints reduces area of modules whenever possible can be made refinable and incremental àdepends on granularity of the representation path-based

13 Placement / Routing initial placement/routing step àcan be a min-cut or any constructive approach àhas to be fast àgives lower bounds on delays between modules placement/routing: àtakes in upper bounds from retiming as flexibility on placement àreplaces modules resulting in better lower bound constraints àobjective is to reduce total chip area àdelay is reduced indirectly

14 Logic Synthesis assumption: àproblems can be solved at the module level àpredictable for given size modules can be run in parallel for the different modules provides better estimates of area-delay trade-offs for subsequent iterations

15 Iterations loop between placement and retiming àuntil no further improvements are possible àmay iterate many times àvery similar to: initial min-cut partitioning low temperature simulated annealing àhave to prove some convergence criteria loop between floorplanning/wireplanning and layout àonly a few iterations àeach iteration information is retained through area-delay trade-offs àalso proof of convergence