phidian Introduction Related work Machine learning methodology - PowerPoint PPT Presentation

How deep learning can drive physical synthesis towards more predictable legalization Renan Netto , Sheiny Fabre, Tiago Augusto Fontana, Vinicius Livramento, La´ ercio Pilla, Jos´ e Lu´ ıs G¨ untzel Embedded Computing Lab (ECL) — Dept. of Computer Science and Statistics Federal University of Santa Catarina (UFSC) ISPD - April 14-17 - San Francisco, CA phidian

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Outline Introduction 1 Related work 2 Machine learning methodology 3 Physical design integration 4 Experimental results 5 Conclusions 6

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in physical design CTS Clock data Result Signo ff Layout data Timing ML models Routing data Routing j Violations i j i Timing data Renan Netto ISPD - April 14-17 - San Francisco, CA 3

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in physical design CTS Clock data Result Signo ff Layout data Timing ML models Routing data Routing j Violations i j i Timing data It has not been used to predict legalization yet! Renan Netto ISPD - April 14-17 - San Francisco, CA 3

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in legalization 1) Choosing among different legalization algorithms illegal placement legalization legalization algorithm A algorithm B solution B solution A Renan Netto ISPD - April 14-17 - San Francisco, CA 4

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in legalization 2) Guiding an incremental placement technique Renan Netto ISPD - April 14-17 - San Francisco, CA 5

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in legalization 3) Guiding an circuit partitioning strategy Renan Netto ISPD - April 14-17 - San Francisco, CA 6

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Machine learning applications in legalization 3) Guiding an circuit partitioning strategy This work explores mainly option (3), but also partially explores option (2) Renan Netto ISPD - April 14-17 - San Francisco, CA 6

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Contributions Feature extraction strategy for training machine learning models. Evaluation of different ML models in order to select the best one for this problem. We employed the best ML model as a pruning mechanism for a circuit partitioning strategy. Renan Netto ISPD - April 14-17 - San Francisco, CA 7

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Table of related works Work Prediction Features ML model Kahng et al. CTS outcome clock data non-convolutional Han et al. signoff timing timing data non-convolutional Zhou et al. # of DRCs layout data, routing data non-convolutional Chan et al. locations of DRCs layout data, routing data non-convolutional Fabrizi et al. short violations layout data, routing data non-convolutional Xie et al. # and location of DRCs circuit snapshot convolutional non-convolutional, This work legalization quality layout data, circuit snapshot convolutional Renan Netto ISPD - April 14-17 - San Francisco, CA 8

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Methodology overview Disp > threshold Layout data ML model Renan Netto ISPD - April 14-17 - San Francisco, CA 12

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Training data generation Circuit partitioning using k-d tree ( height = 2 in the example) Renan Netto ISPD - April 14-17 - San Francisco, CA 13

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Training data generation Sample 1 Sample 2 Sample 3 Sample 4 Circuit partitioning using k-d tree ( height = 2 in the example) Renan Netto ISPD - April 14-17 - San Francisco, CA 13

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Training data generation Displacement 1 Displacement 2 Displacement 3 Displacement 4 Circuit partitioning using k-d tree ( height = 2 in the example) Renan Netto ISPD - April 14-17 - San Francisco, CA 13

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Handling partitions of different sizes Sample 1 Sample 2 Renan Netto ISPD - April 14-17 - San Francisco, CA 14

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Handling partitions of different sizes Sample 1 Sample 2 Sample 3 Sample 4 Renan Netto ISPD - April 14-17 - San Francisco, CA 14

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Handling partitions of different sizes Sample 1 Sample 2 Sample 3 Sample 4 Actual values: 1 ≤ height ≤ 9 and 1024 samples for each height. Renan Netto ISPD - April 14-17 - San Francisco, CA 15

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Feature selection: non-convolutional ML models D = 0 . 49 Density of the partition area A = [64 , 48] Area occupied by cells of each height Renan Netto ISPD - April 14-17 - San Francisco, CA 16

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Feature selection: non-convolutional ML models Renan Netto ISPD - April 14-17 - San Francisco, CA 17

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Feature selection: non-convolutional ML models 5 4 3 2 1 0 0 0.2 0.4 0.6 0.8 1 Renan Netto ISPD - April 14-17 - San Francisco, CA 17

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Feature selection: non-convolutional ML models 0.5 0.4 0.3 0.2 0.1 0 0 0.2 0.4 0.6 0.8 1 Renan Netto ISPD - April 14-17 - San Francisco, CA 17

Introduction Related work Machine learning methodology Physical design integration Experimental results Conclusions Feature selection: non-convolutional ML models 8 6 4 2 0 0 0.2 0.4 0.6 0.8 1 Renan Netto ISPD - April 14-17 - San Francisco, CA 18

phidian Introduction Related work Machine learning methodology - PowerPoint PPT Presentation

How deep learning can drive physical synthesis towards more predictable legalization Renan Netto , Sheiny Fabre, Tiago Augusto Fontana, Vinicius Livramento, La ercio Pilla, Jos e Lu s G untzel Embedded Computing Lab (ECL) Dept.

phidian Introduction Memory Hierarchy Modularity The Entity-Component System Design Pattern

MACAW : A Media Access Based on MACA, a Multiple Access Collision Protocol for Wireless

Self ish Rout ing and t he P rice of Anarchy Tim Roughgarden Cornell Universit y Includes

constraining designs or designers? Krishna Panda Texas Instrument kpanda@ti.com 1

USenate Meeting CCF Report (attachment) November 1, 2018 Staff Senate Report Student

Data Services Integration Team WP1 Federated Identity Paul Millar, Patrick Fuhrmann, Bernd

Results from GERDA Phase I and status of the

Selected Groundwater Activities at the U.S. Geological Survey With focus on opportunities for

This meeting is being recorded. If you do not wish to be recorded, please disconnect now. USDA is

Plotting directl y u sing pandas P YTH ON FOR R U SE R S Daniel Chen Instr u ctor Plotting in

PROPOSAL For a Modular, Pluggable 802.11 MAC Model To Facilitate Experimentation and

TOS Arno Puder 1 Device Drivers Code that manages the details of interacting with a

Nouveau The overdue Status update Karol Herbst Karol Herbst Nouveau 1 / 15 Goal Reliable

Congruence Closure with Integer Offsets Robert Nieuwenhuis and Albert Oliveras UPC, Barcelona

Projections in Eberlein compactifications Nico Spronk (U. Waterloo) Fields Institute, COSy 2014

Diagnostic Capabilities of the Red Storm Compliance Test Suite Mike Davis Cray Inc.

Indecor Slides (india) Private Limited https://www.indiamart.com/indecor-slides/ We are occupied

Available Bandwidth Available Bandwidth Estimation in IEEE 802.11- - Estimation in IEEE 802.11

MEDICAL D E M O S L I D E Title text demo Lorem Ipsum is simply dummy text of the printing and

Transvaginal Ultrasound None Guided Pelvic Procedures Tara Morgan, MD Assistant Professor of

Rhode Island Stormwater Design and Installations Standards Manual Public Workshop LID S ite

Committee Meeting Thursday, October 1, 2020 Welcome! Online Meeting Protocols and Tips 1. Be

FALL 2018 NEIGHBORHOOD LEADERS MEETING OCTOBER 17, 2018 JOSH POLAND PUBLIC INFORMATION OFFICER

ROAD MAP TO HAPPINESS LEADS TO SUCCESS SLOW AND STEADY CLIMB Gradually upgraded each part of