SlideShare ist ein Scribd-Unternehmen logo
1 von 11
Downloaden Sie, um offline zu lesen
Cell Verification Metrics
Cell Verification Metrics



                         Sanjay Gupta
                 Cell Verification Lead
                    STI Design Center
                             6/27/2006
Outline
    Background
    Cell Architecture Overview
    Verification Process
    Hierarchical Verification
    Verification Metrics




2
Background
    Sony, Toshiba and IBM started the design process for a new
    high performance microprocessor in 2001


    IBM’s custom server verification methodology was used as a
    base
       New Vendor Tool was introduced
       IBM Cycle sim was used as the simulator of choice
       Most of the other verification tools used were IBM internal tools


    Cell processor met it goals and delivered excellent levels of
    performance and power efficiency
       256 GFlops (SP) @4GHz
       ~234M transistors
       ~235mm2 - 90nm SOI process

3
Overview
    Multi-core and non-homogeneous architecture
      One control optimized core - PPE
         Management and Allocation of tasks for SPEs
      Eight compute optimized cores – SPEs
         High computational tasks


    XDR Memory Interface
    Custom IO Interface
    Three completely different asynchronous clocks
    Non-critical logic run with 2x clock




4
Architecture

                                  SPU                                       SPU


                                                    …
                             LS     MFC                              LS       MFC

      PPE                    SPE0                                    SPE7

                                        Bus (EIB)


         Bus Interface Controller                       Memory Interface
                  (BIC)                                  Controller (MIC)




    To Southbridge Chip or                          To Main Memory
    to another Cell Chip


5
Verification
Process




6
Verification Planning
    Planning Theory : Top Down Specification/ Bottom up
    Implementation
      Plan out all environments needed to create a quality
      chip
      Break design into partition, island, unit, and block
      levels
      Define clear goals for each level
      Implement environments from block level up




7
Verification Phases

SYSTEM                                              PH1     PH2      PH3 PH4 PH5


                                   Phase1
CHIP                                    PH1         PH2    PH3      PH4 PH5


                                 Phase3       Phase4      Phase5
PARTITION                  PH1        PH2         PH3     PH4 PH5


               Phase1   Phase2      Phase3       Phase4
ISLAND          PH1      PH2         PH3          PH4     PH5



UNIT     PH1   PH2       PH3         PH4      PH5



                                      Time
  8
Statistics

                                                    Multi-processor
             Cell, 4 SPE Cell                      correctness
                 SPE, PPE                           Connectedness
                                                    Interface assumption
      SPU                                          validation
                        BIC

     MFC
                 MIC              PU
                                                     Processor element
                                                   functionality validation
                       EIB

             Unit/Island Environments               Thorough coverage
               Found 95% of Bugs
                                                    Functionality testing
            Partitions: 0.2% of Bugs
                                                    30 Simulation
             Full Chip: 3.5% of Bugs                Environments

            Verification Environment Hierarchies

9
Metrics
     The major metrics are
        Effective Passing Rate
           Includes testcase written as per plan, testcase running and
           testcase passing
        Effective Coverage
           Includes coverage implemented as per plan, coverage on line
           and coverage hit
        Checkers
           Includes % of checkers implemented and on line as per plan
        Reviews
           Includes % of the reviews conducted as per plan
        Bug Rate
           Includes logic as well as environment

        Sim Cycles


10
Metrics – cont…
     These metrics are assigned weights which are
     different for different environments.
     Different Environments are also assigned weights as
     per the complexity, newness etc.
     Based on all these information, verification progress
     can be calculated which is mostly upward curve ( as
     apposed to something which keeps on going up and
     down all the time)




11

Weitere ähnliche Inhalte

Andere mochten auch (7)

Dayal rtp q2_07
Dayal rtp q2_07Dayal rtp q2_07
Dayal rtp q2_07
 
Kitt clp
Kitt clpKitt clp
Kitt clp
 
20101203 desktop emulation
20101203 desktop emulation20101203 desktop emulation
20101203 desktop emulation
 
Latest Project
Latest ProjectLatest Project
Latest Project
 
Oeding
OedingOeding
Oeding
 
Meyers clp
Meyers clpMeyers clp
Meyers clp
 
Correale q4 2008_rtp
Correale q4 2008_rtpCorreale q4 2008_rtp
Correale q4 2008_rtp
 

Ähnlich wie Cell Verification Metrics and Process Overview

Coverage Solutions on Emulators
Coverage Solutions on EmulatorsCoverage Solutions on Emulators
Coverage Solutions on EmulatorsDVClub
 
A Unique Test Bench for Various System-on-a-Chip
A Unique Test Bench for Various System-on-a-Chip A Unique Test Bench for Various System-on-a-Chip
A Unique Test Bench for Various System-on-a-Chip IJECEIAES
 
Soft Error Study of ARM SoC at 28 Nanometers
Soft Error Study of ARM SoC at 28 NanometersSoft Error Study of ARM SoC at 28 Nanometers
Soft Error Study of ARM SoC at 28 NanometersWojciech Koszek
 
Radio Frequency Test Stands for Remote Controllers
Radio Frequency Test Stands for Remote ControllersRadio Frequency Test Stands for Remote Controllers
Radio Frequency Test Stands for Remote ControllersUjjal Dutt, PMP
 
Os Madsen Block
Os Madsen BlockOs Madsen Block
Os Madsen Blockoscon2007
 
An integrated approach for designing and testing specific processors
An integrated approach for designing and testing specific processorsAn integrated approach for designing and testing specific processors
An integrated approach for designing and testing specific processorsVLSICS Design
 
Approaches for Power Management Verification of SOC
Approaches for Power Management Verification of SOC Approaches for Power Management Verification of SOC
Approaches for Power Management Verification of SOC DVClub
 
Best Practices and Performance Studies for High-Performance Computing Clusters
Best Practices and Performance Studies for High-Performance Computing ClustersBest Practices and Performance Studies for High-Performance Computing Clusters
Best Practices and Performance Studies for High-Performance Computing ClustersIntel® Software
 
Modeling System Behaviors: A Better Paradigm on Prototyping
Modeling System Behaviors: A Better Paradigm on PrototypingModeling System Behaviors: A Better Paradigm on Prototyping
Modeling System Behaviors: A Better Paradigm on PrototypingDVClub
 
System Development for Verification of General Purpose Input Output
System Development for Verification of General Purpose Input OutputSystem Development for Verification of General Purpose Input Output
System Development for Verification of General Purpose Input OutputRSIS International
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREVLSICS Design
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREVLSICS Design
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREVLSICS Design
 
Performance Characterization of the Pentium Pro Processor
Performance Characterization of the Pentium Pro ProcessorPerformance Characterization of the Pentium Pro Processor
Performance Characterization of the Pentium Pro ProcessorDileep Bhandarkar
 
智慧檢測技術與工業自動化
智慧檢測技術與工業自動化智慧檢測技術與工業自動化
智慧檢測技術與工業自動化CHENHuiMei
 
Introduction to NBL
Introduction to NBLIntroduction to NBL
Introduction to NBLFei Ji Siao
 

Ähnlich wie Cell Verification Metrics and Process Overview (20)

Cell verification dv club
Cell verification dv clubCell verification dv club
Cell verification dv club
 
Coverage Solutions on Emulators
Coverage Solutions on EmulatorsCoverage Solutions on Emulators
Coverage Solutions on Emulators
 
Sharam salamian
Sharam salamianSharam salamian
Sharam salamian
 
A Unique Test Bench for Various System-on-a-Chip
A Unique Test Bench for Various System-on-a-Chip A Unique Test Bench for Various System-on-a-Chip
A Unique Test Bench for Various System-on-a-Chip
 
Soft Error Study of ARM SoC at 28 Nanometers
Soft Error Study of ARM SoC at 28 NanometersSoft Error Study of ARM SoC at 28 Nanometers
Soft Error Study of ARM SoC at 28 Nanometers
 
Radio Frequency Test Stands for Remote Controllers
Radio Frequency Test Stands for Remote ControllersRadio Frequency Test Stands for Remote Controllers
Radio Frequency Test Stands for Remote Controllers
 
Os Madsen Block
Os Madsen BlockOs Madsen Block
Os Madsen Block
 
Synopsys jul1411
Synopsys jul1411Synopsys jul1411
Synopsys jul1411
 
An integrated approach for designing and testing specific processors
An integrated approach for designing and testing specific processorsAn integrated approach for designing and testing specific processors
An integrated approach for designing and testing specific processors
 
Approaches for Power Management Verification of SOC
Approaches for Power Management Verification of SOC Approaches for Power Management Verification of SOC
Approaches for Power Management Verification of SOC
 
Best Practices and Performance Studies for High-Performance Computing Clusters
Best Practices and Performance Studies for High-Performance Computing ClustersBest Practices and Performance Studies for High-Performance Computing Clusters
Best Practices and Performance Studies for High-Performance Computing Clusters
 
Modeling System Behaviors: A Better Paradigm on Prototyping
Modeling System Behaviors: A Better Paradigm on PrototypingModeling System Behaviors: A Better Paradigm on Prototyping
Modeling System Behaviors: A Better Paradigm on Prototyping
 
System Development for Verification of General Purpose Input Output
System Development for Verification of General Purpose Input OutputSystem Development for Verification of General Purpose Input Output
System Development for Verification of General Purpose Input Output
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
 
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER COREUVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
UVM BASED REUSABLE VERIFICATION IP FOR WISHBONE COMPLIANT SPI MASTER CORE
 
Tos tutorial
Tos tutorialTos tutorial
Tos tutorial
 
Performance Characterization of the Pentium Pro Processor
Performance Characterization of the Pentium Pro ProcessorPerformance Characterization of the Pentium Pro Processor
Performance Characterization of the Pentium Pro Processor
 
智慧檢測技術與工業自動化
智慧檢測技術與工業自動化智慧檢測技術與工業自動化
智慧檢測技術與工業自動化
 
Introduction to NBL
Introduction to NBLIntroduction to NBL
Introduction to NBL
 

Mehr von Obsidian Software (20)

Zhang rtp q307
Zhang rtp q307Zhang rtp q307
Zhang rtp q307
 
Zehr dv club_12052006
Zehr dv club_12052006Zehr dv club_12052006
Zehr dv club_12052006
 
Yang greenstein part_2
Yang greenstein part_2Yang greenstein part_2
Yang greenstein part_2
 
Yang greenstein part_1
Yang greenstein part_1Yang greenstein part_1
Yang greenstein part_1
 
Williamson arm validation metrics
Williamson arm validation metricsWilliamson arm validation metrics
Williamson arm validation metrics
 
Whipp q3 2008_sv
Whipp q3 2008_svWhipp q3 2008_sv
Whipp q3 2008_sv
 
Vishakantaiah validating
Vishakantaiah validatingVishakantaiah validating
Vishakantaiah validating
 
Validation and-design-in-a-small-team-environment
Validation and-design-in-a-small-team-environmentValidation and-design-in-a-small-team-environment
Validation and-design-in-a-small-team-environment
 
Tobin verification isglobal
Tobin verification isglobalTobin verification isglobal
Tobin verification isglobal
 
Tierney bq207
Tierney bq207Tierney bq207
Tierney bq207
 
The validation attitude
The validation attitudeThe validation attitude
The validation attitude
 
Thaker q3 2008
Thaker q3 2008Thaker q3 2008
Thaker q3 2008
 
Thaker q3 2008
Thaker q3 2008Thaker q3 2008
Thaker q3 2008
 
Strickland dvclub
Strickland dvclubStrickland dvclub
Strickland dvclub
 
Stinson post si and verification
Stinson post si and verificationStinson post si and verification
Stinson post si and verification
 
Shultz dallas q108
Shultz dallas q108Shultz dallas q108
Shultz dallas q108
 
Shreeve dv club_ams
Shreeve dv club_amsShreeve dv club_ams
Shreeve dv club_ams
 
Schulz sv q2_2009
Schulz sv q2_2009Schulz sv q2_2009
Schulz sv q2_2009
 
Schulz dallas q1_2008
Schulz dallas q1_2008Schulz dallas q1_2008
Schulz dallas q1_2008
 
Salamian dv club_foils_intel_austin
Salamian dv club_foils_intel_austinSalamian dv club_foils_intel_austin
Salamian dv club_foils_intel_austin
 

Cell Verification Metrics and Process Overview

  • 1. Cell Verification Metrics Cell Verification Metrics Sanjay Gupta Cell Verification Lead STI Design Center 6/27/2006
  • 2. Outline Background Cell Architecture Overview Verification Process Hierarchical Verification Verification Metrics 2
  • 3. Background Sony, Toshiba and IBM started the design process for a new high performance microprocessor in 2001 IBM’s custom server verification methodology was used as a base New Vendor Tool was introduced IBM Cycle sim was used as the simulator of choice Most of the other verification tools used were IBM internal tools Cell processor met it goals and delivered excellent levels of performance and power efficiency 256 GFlops (SP) @4GHz ~234M transistors ~235mm2 - 90nm SOI process 3
  • 4. Overview Multi-core and non-homogeneous architecture One control optimized core - PPE Management and Allocation of tasks for SPEs Eight compute optimized cores – SPEs High computational tasks XDR Memory Interface Custom IO Interface Three completely different asynchronous clocks Non-critical logic run with 2x clock 4
  • 5. Architecture SPU SPU … LS MFC LS MFC PPE SPE0 SPE7 Bus (EIB) Bus Interface Controller Memory Interface (BIC) Controller (MIC) To Southbridge Chip or To Main Memory to another Cell Chip 5
  • 7. Verification Planning Planning Theory : Top Down Specification/ Bottom up Implementation Plan out all environments needed to create a quality chip Break design into partition, island, unit, and block levels Define clear goals for each level Implement environments from block level up 7
  • 8. Verification Phases SYSTEM PH1 PH2 PH3 PH4 PH5 Phase1 CHIP PH1 PH2 PH3 PH4 PH5 Phase3 Phase4 Phase5 PARTITION PH1 PH2 PH3 PH4 PH5 Phase1 Phase2 Phase3 Phase4 ISLAND PH1 PH2 PH3 PH4 PH5 UNIT PH1 PH2 PH3 PH4 PH5 Time 8
  • 9. Statistics Multi-processor Cell, 4 SPE Cell correctness SPE, PPE Connectedness Interface assumption SPU validation BIC MFC MIC PU Processor element functionality validation EIB Unit/Island Environments Thorough coverage Found 95% of Bugs Functionality testing Partitions: 0.2% of Bugs 30 Simulation Full Chip: 3.5% of Bugs Environments Verification Environment Hierarchies 9
  • 10. Metrics The major metrics are Effective Passing Rate Includes testcase written as per plan, testcase running and testcase passing Effective Coverage Includes coverage implemented as per plan, coverage on line and coverage hit Checkers Includes % of checkers implemented and on line as per plan Reviews Includes % of the reviews conducted as per plan Bug Rate Includes logic as well as environment Sim Cycles 10
  • 11. Metrics – cont… These metrics are assigned weights which are different for different environments. Different Environments are also assigned weights as per the complexity, newness etc. Based on all these information, verification progress can be calculated which is mostly upward curve ( as apposed to something which keeps on going up and down all the time) 11