new approaches to harness global interconnects
play

New Approaches to Harness Global Interconnects Jason Cong Computer - PowerPoint PPT Presentation

PART V New Approaches to Harness Global Interconnects Jason Cong Computer Science Department University of California at Los Angeles Email: cong@cs.ucla.edu Tel: 310-206-2775 http://cadlab.cs.ucla.edu/~cong ASPDAC'01 Tutorial Jason Cong 1


  1. PART V New Approaches to Harness Global Interconnects Jason Cong Computer Science Department University of California at Los Angeles Email: cong@cs.ucla.edu Tel: 310-206-2775 http://cadlab.cs.ucla.edu/~cong ASPDAC'01 Tutorial Jason Cong 1

  2. Part V Outline I Interconnect Interconnect- -Centric Design Flow Centric Design Flow I I Interconnect Performance Estimation Models Interconnect Performance Estimation Models I N IPEM for optimal IPEM for optimal wiresizing wiresizing N IPEM for IPEM for wiresizing wiresizing and buffer insertion and buffer insertion I Interconnect Planning Interconnect Planning I N Physical hierarchy generation Physical hierarchy generation N Floorplan Floorplan/coarse placement with interconnect planning /coarse placement with interconnect planning N Interconnect architecture planning Interconnect architecture planning I Concluding Remarks Concluding Remarks I ASPDAC'01 Tutorial Jason Cong 2

  3. Clock cycles required for traveling 2cm line under BIWS (buffer insertion and wire sizing) 5 4 Estimated by IPEM On NTRS’97 technology clock cycle(s) 3 Driver size: 100x min gate 2 Receiver size: 100x min gate Buffer size: 100x min gate 1 0 5 G Hz 0.25 um 0.18 ym 3 G Hz 0.13 um 0.10 um 0.07 um 1 G Hz ASPDAC'01 Tutorial Jason Cong 3

  4. How Far Can We Go in Each Clock Cycle 7 clock I NTRS’97 0.07um Tech I 5 G Hz across-chip clock 6 clock I 620 mm 2 (24.9mm x 24.9mm) I IPEM BIWS estimations 5 clock N Buffer size: 100x N Driver/receiver size: 100x I From corner to corner: N 7 clock cycles 4 clock 1 clock 2 clock 3 clock 15.04 22.56 24.9 (mm) 0 7.52 ASPDAC'01 Tutorial Jason Cong 4

  5. Two Important Implications I Interconnects determine the system Interconnects determine the system I performance performance Interconnect/communication-centric design methodology I Need multiple clock cycles to cross the global Need multiple clock cycles to cross the global I interconnects in giga interconnects in giga- -hertz designs hertz designs Pipelining/retiming on global interconnects ASPDAC'01 Tutorial Jason Cong 5

  6. Interconnect-Centric Design Methodology I Proposed transition Proposed transition I interconnect device device interconnect device/function centric interconnect/communication centric I Analogy Analogy I Data/Objects Programs Programs Data/Objects ASPDAC'01 Tutorial Jason Cong 6

  7. Interconnect-Centric IC Design Flow Under Development at UCLA Architecture/Conceptual-level Design Design Specification Interconnect Planning Interconnect Performance • Physical Hierarchy Generation Estimation Models (IPEM) HDM • Foorplan/Coarse Placement with Interconnect Planning • OWS, SDWS, BISWS • Interconnect Architecture Planning abstraction Synthesis and Placement under Physical Hierarchy Structure view Functional view Interconnect Optimization Interconnect Synthesis Physical view (TRIO) Performance-driven Global Routing Timing view • Topology Optimization with Buffer Insertion • Wire sizing and spacing Pseudo Pin Assignment under Noise Control • Simultaneous Buffer Insertion and Wire Sizing • Simultaneous Topology Construction with Buffer Insertion and Wire Sizing Interconnect Layout Route Planning Point-to-Point Gridless Routing Final Layout ASPDAC'01 Tutorial Jason Cong 7

  8. Interconnect-Centric IC Design Flow Under Development at UCLA Architecture/Conceptual-level Design Design Specification Interconnect Planning Interconnect Performance Interconnect Planning Estimation Models (IPEM) Interconnect Performance • Physical Hierarchy Generation • Physical Hierarchy Generation Estimation Models (IPEM) • OWS • Foorplan/Coarse Placement with HDM • Foorplan/Coarse Placement with Interconnect Planning • OWS, SDWS, BISWS • SDWS • Interconnect Architecture Planning Interconnect Planning • BISWS • Interconnect Architecture Planning abstraction Synthesis and Placement under Physical Hierarchy Structure view Interconnect Optimization (TRIO) Interconnect Synthesis Functional view Interconnect Optimization Interconnect Synthesis • Topology Optimization with Physical view Performance-driven Global Routing (TRIO) Performance-driven Global Routing Timing view Buffer Insertion • Topology Optimization with Buffer Insertion • Wire sizing and spacing • Wire sizing and spacing Pseudo Pin Assignment under Noise Control Pseudo Pin Assignment under Noise Control • Simultaneous Buffer Insertion and Wire Sizing • Simultaneous Topology Construction • Simultaneous Buffer Insertion with Buffer Insertion and Wire Sizing Interconnect Layout and Wire Sizing Interconnect Layout • Simultaneous Topology Construction Route Planning Route Planning with Buffer Insertion and Wire Sizing Point-to-Point Gridless Routing Point-to-Point Gridless Routing Final Layout ASPDAC'01 Tutorial Jason Cong 8

  9. Interconnect-Centric IC Design Flow Under Development at UCLA Architecture/Conceptual-level Design Design Specification Interconnect Planning Interconnect Performance • Physical Hierarchy Generation Estimation Models (IPEM) HDM • Foorplan/Coarse Placement with Interconnect Planning • OWS, SDWS, BISWS • Interconnect Architecture Planning abstraction Synthesis and Placement under Physical Hierarchy Structure view Functional view Interconnect Optimization Interconnect Synthesis Physical view (TRIO) Performance-driven Global Routing Timing view • Topology Optimization with Buffer Insertion • Wire sizing and spacing Pseudo Pin Assignment under Noise Control • Simultaneous Buffer Insertion and Wire Sizing • Simultaneous Topology Construction with Buffer Insertion and Wire Sizing Interconnect Layout Route Planning Point-to-Point Gridless Routing Final Layout ASPDAC'01 Tutorial Jason Cong 9

  10. Part V Outline I Interconnect Interconnect- -Centric Design Flow Centric Design Flow I I Interconnect Performance Estimation Models Interconnect Performance Estimation Models I N IPEM for optimal IPEM for optimal wiresizing wiresizing N N IPEM for IPEM for wiresizing wiresizing and buffer insertion and buffer insertion N I Interconnect Planning Interconnect Planning I N Physical hierarchy generation Physical hierarchy generation N N Floorplan Floorplan/coarse placement with interconnect /coarse placement with interconnect N planning planning N Interconnect architecture planning Interconnect architecture planning N I Concluding Remarks Concluding Remarks I ASPDAC'01 Tutorial Jason Cong 10

  11. Interconnect Performance Estimation I Introduction & Motivation Introduction & Motivation I I Problem Formulation Problem Formulation I I Interconnect Delay Estimation Models under Various Interconnect Delay Estimation Models under Various I Layout Optimizations Layout Optimizations I Application and Conclusion Application and Conclusion I ASPDAC'01 Tutorial Jason Cong 11

  12. Impact of Interconnect Optimization on Future Technology Generations 5 2cm DS 4.5 4 2cm BIS 3.5 Delay (ns) 2cm BISWS 3 2.5 G DS: Driver Sizing only 2 G BIS: Buffer Insertion 1.5 and Sizing 1 G BISWS: Simultaneous 0.5 Buffer Insertion/Sizing 0 and Wiresizing 0.25 0.18 0.15 0.13 0.1 0.07 Technology ( u m) ASPDAC'01 Tutorial Jason Cong 12

  13. Complexity of Existing Interconnect Opt. Algorithms I 2cm line, W=20, B=10, segment every 500um 2cm line, W=20, B=10, segment every 500um I I Use Use best available best available algorithms: algorithms: I N Local Refinement ( Local Refinement (LR LR) ) N Dynamic Programming ( Dynamic Programming (DP DP) ) N Hybrid of Hybrid of DP+LR DP+LR DP DP+LR LR Algorithm OWS BI+OWS BIWS BISWS Delay (ns) 4.5 1.6 1.02 0.81 CPU (s) 0.06 0.42 4.5 12.4 ( HSPICE needs additional 60 seconds! ) ( HSPICE needs additional 60 seconds! ) ASPDAC'01 Tutorial Jason Cong 13

  14. Needs for Efficient Interconnect Estimation Models I Efficiency Efficiency I I Abstraction Abstraction to hide detailed design information to hide detailed design information I N granularity of wire segmentation granularity of wire segmentation N number of wire widths, buffer sizes, ... number of wire widths, buffer sizes, ... I Explicit relation Explicit relation to enable optimal design decision at to enable optimal design decision at I high levels high levels I Ease of interaction Ease of interaction with logic/high level synthesis tools with logic/high level synthesis tools I ASPDAC'01 Tutorial Jason Cong 14

  15. Interconnect Performance Estimation Modeling [Cong-Pan, ASPDAC’99, TAU’99, DAC’99] I Develop a set of Develop a set of interconnect performance estimation interconnect performance estimation I models ( (IPEM IPEM), under different optimization alternatives: ), under different optimization alternatives: models N Optimal Wire Sizing Optimal Wire Sizing (OWS) (OWS) N Simultaneous Driver and Wire Sizing Simultaneous Driver and Wire Sizing (SDWS) (SDWS) N Simultaneous Buffer Insertion and Wire Sizing Simultaneous Buffer Insertion and Wire Sizing (BIWS) (BIWS) N Simultaneous Buffer Insertion/Sizing and Wire Sizing Simultaneous Buffer Insertion/Sizing and Wire Sizing (BISWS) (BISWS) I IPEM have IPEM have I N closed closed- -form formula or simple characteristic equations form formula or simple characteristic equations N constant running time in practice constant running time in practice N high accuracy (about 90% accuracy on average) high accuracy (about 90% accuracy on average) ASPDAC'01 Tutorial Jason Cong 15

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend