impromptu data extraction and analysis data mining and analytics framework for vlsi designs sandeep...

15
Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P ([email protected] ); +91 80 2507 5492 Anand Ananthanarayanan ([email protected] ); +91 80 2507 5774 Intel Corporation

Upload: baldwin-jordan

Post on 15-Jan-2016

220 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI DesignsSandeep P ([email protected]); +91 80 2507 5492Anand Ananthanarayanan ([email protected]); +91 80 2507 5774Intel Corporation

Page 2: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

2Intel Information Technology, FOR INTERNAL USE ONLY

Author AffiliationsAuthor Affiliation Phone Number Email Address

Sandeep P Intel Corporation +91 80 2507 5492 [email protected] Ananthanarayanan Intel Corporation +91 80 2507 5774 [email protected]

Page 3: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

3Intel Information Technology, FOR INTERNAL USE ONLY

AbstractDesign processes from Logic design, validation, backend implementation and verification require a plethora of CAD tools. These tools generate reports, debug information in its own form and content. Designers need to parse and review data from multiple sources and tools to make design calls. When implementing backend design, a designer or a methodology owner needs to understand the patterns seen in the design. Data like number of paths dominated by low leakage, Slope profile for cells with margin > x ps, Drive strength profile of cells in timing path, etc., are critical to make design decisions, optimize design collaterals and ensure design with robust electrical functionality. Many of the data can be obtained only through data mining of results and logs of multiple tools. Data mining is also a constant activity from technology readiness to execution and post silicon debug phases. Data mining problem gets compounded when data is needed from different PV domains. For example, a designer looking to optimize power would need dynamic power information, path margin and max cap information all generated by different tools in different formats in different locations. Data mining has been historically done by adhoc scripts to parse through different reports, and log files. Data generated is post processed and then visualized. Any requirement change in data mining would need changes in the scripts. There is no data mining model which supports multiple tools with different output formats. There is no methodology which supports cross domain analysis.We present IDEA (Impromptu Data Extraction and Analysis). IDEA is data mining and data analysis framework in a highly interactive web application platform. It supports assimilating data from different tools and formats into one data organization in the form of SQL tables. SQL enables compact organization and faster queries. IDEA framework is built using the Linux-Apache™-Mysql™-Perl (LAMP) packages and uses the R language for performing statistical analysis on the data. R language enables handling huge amount of data with support for different statistical plots like pie-charts, histograms, box plots, scatter plots, Linear regression etc. IDEA data mining completes in minutes compared to hours/days with conventional approaches like scripts. IDEA is highly interactive web application with all the data extraction and plotting functionalities abstracted using highly interactive widgets. IDEA has been used to data mine power savings post Optimization, Analysis of power distribution, Profile the speed paths, Review standard cells usage, Utilization of cell sizes across the design space, RC delays per path stage and has multiple other usages. Large precious unorganized data lies unexploited. Structured Data Mining essential for competitive VLSI design. Increasing complexity makes data analytics a must-have for quality design. No EDA tool exists today to do this critical data mining. IDEA fills this gap and provides valuable data mining capability. It is time to think of Data Mining as a EDA product

Page 4: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

4Intel Information Technology, FOR INTERNAL USE ONLY

Design Process

Functional Circuit Design

Verify

Implement

Logic

Timing Reports Extraction reports

Route utilization Cell utilization

DRC reports Layout Checks

Multiple ToolsMultiple Reports Multiple Formats

Design Reports

Large Data gets generated requiring interpretation and Analysis

Page 5: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

5Intel Information Technology, FOR INTERNAL USE ONLY

Data Conundrum

Count of min Z cells with < y ps margin

Count of back2back flops

in design

Is clock power in wires or in devices?

Increase design guardband?

Slope profile for cells with margin > x ps

Numbers of paths dominated by low leakage

Drive strength profile of cells in timing path

Design Quality Increasingly Dependent on Multiple Parameters

Page 6: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

6Intel Information Technology, FOR INTERNAL USE ONLY

Data Mining - A Constant Activity• Data mining is done to generate design heuristicsTech Readiness

• Data mining is done to determine delta changes on design limits

• Data mining needed for optimizationDesign execution

• Data mining is done to root cause and understand the PV-Silicon miscorrelationPost silicon

Formal Data Mining Tool or Model Not Currently Available In Industry

Page 7: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

7Intel Information Technology, FOR INTERNAL USE ONLY

To solve this Data Mining problem, we present

Page 8: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

8Intel Information Technology, FOR INTERNAL USE ONLY

IDEAImpromptu Data Extraction and Analysis (IDEA) is Web application for Data mining on an open architecture Linked Data Caching SQL databases Common Xml interface for data manipulation Statistical analysis capability with ‘R’ Language Practically unlimited capacity with ‘R’ Language Data visualization capability Histograms, pie charts, density/scatter plots, dot charts

Faster turn around time (no text parsing scripts) Intuitive, web based user interface

Highly Interactive Application for Data Mining

Page 9: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

9Intel Information Technology, FOR INTERNAL USE ONLY

IDEA

Web Based Data Mining Platform

Page 10: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

10Intel Information Technology, FOR INTERNAL USE ONLY

IDEA ArchitectureDataBasePresentation Tier

Application Tier

Storage TierThree Tiered Web Application

Page 11: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

11Intel Information Technology, FOR INTERNAL USE ONLY

Architecture – Idea Client

Simple Client with Powerful CapabilitiesIdea Server

AJAX CallsJSON for data transfer

Control CenterData Viewer

Report Viewer

ExperimentsAppsStatistical AnalysisSpreadsheet GenerationPDF Converter

Data ExtractionData Manipulation

Page 12: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

12Intel Information Technology, FOR INTERNAL USE ONLY

Basic Usage FlowOpen IDEA App Select ProjectSelect Blocks

Manipulate Data Run pre-selected Queries OR Query interactively

Page 13: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

13Intel Information Technology, FOR INTERNAL USE ONLY

IDEA Usage and BenefitsIDEA Usage

Datamine power savings post OptimAnalysis of power distribution

Profile the speed pathsReview standard cells usage

Utilization of cell sizes across the design space

RC delays per path stage

- Data Mining Simplified -

Page 14: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

14Intel Information Technology, FOR INTERNAL USE ONLY

Summary• Large precious unorganized data lies unexploited• Structured Data Mining essential for competitive VLSI design• Increasing complexity makes data analytics a must-have for quality design • No EDA tool exists today to do this critical data mining• IDEA fills this gap and provides valuable data mining capability

- It is time to think of Data Mining as a EDA product -

Page 15: Impromptu Data Extraction and Analysis Data Mining and Analytics Framework for VLSI Designs Sandeep P (sandeep.p@intel.com); +91 80 2507 5492sandeep.p@intel.com

15Intel Information Technology, FOR INTERNAL USE ONLY

Acknowledgements Everyone at Intel who contributed to this work