FPGAs for Temperature-Aware Microarchitecture Research Siva Velusamy, Wei Huang, John Lach, Mircea Stan and Kevin Skadron University of Virginia.

Slides:



Advertisements
Similar presentations
Forschungszentrum Informatik, Karlsruhe Power Estimation Approach for SRAM- based FPGAs FZI Embedded System Design Group (ESDG) Karlheinz Weiss, Thorsten.
Advertisements

FPGA (Field Programmable Gate Array)
Performance, Energy and Thermal Considerations of SMT and CMP architectures Yingmin Li, David Brooks, Zhigang Hu, Kevin Skadron Dept. of Computer Science,
Survey of Reconfigurable Logic Technologies
Application-Specific Customization of FPGA Soft- core Processors Journal Paper Presentation Presented by: Ahmad Sghaier Course Instructor: Dr. Shawki Areibi.
DARPA Assessing Parameter and Model Sensitivities of Cycle-Time Predictions Using GTX u Abstract The GTX (GSRC Technology Extrapolation) system serves.
1 Closed-Loop Modeling of Power and Temperature Profiles of FPGAs Kanupriya Gulati Sunil P. Khatri Peng Li Department of ECE, Texas A&M University, College.
Extensible Processors. 2 ASIP Gain performance by:  Specialized hardware for the whole application (ASIC). −  Almost no flexibility. −High cost.  Use.
11/04/06 1 Multicore Processor On FPGA Project name : Spring Semester 2005 / 2006 Characterization Presentation Presenting : Oren Sela & Tom Yahalom Supervisor.
Yefu Wang and Kai Ma. Project Goals and Assumptions Control power consumption of multi-core CPU by CPU frequency scaling Assumptions: Each core can be.
1 Variability Characterization in FPGAs Brendan Hargreaves 10/05/2006.
1 Fast Communication for Multi – Core SOPC Technion – Israel Institute of Technology Department of Electrical Engineering High Speed Digital Systems Lab.
February 4, 2002 John Wawrzynek
1 Chapter 14 Embedded Processing Cores. 2 Overview RISC: Reduced Instruction Set Computer RISC-based processor: PowerPC, ARM and MIPS The embedded processor.
UCB November 8, 2001 Krishna V Palem Proceler Inc. Customization Using Variable Instruction Sets Krishna V Palem CTO Proceler Inc.
Temperature-Aware Design Presented by Mehul Shah 4/29/04.
Implementation of DSP Algorithm on SoC. Mid-Semester Presentation Student : Einat Tevel Supervisor : Isaschar Walter Accompaning engineer : Emilia Burlak.
Lecture 7 Lecture 7: Hardware/Software Systems on the XUP Board ECE 412: Microcomputer Laboratory.
Using FPGAs with Embedded Processors for Complete Hardware and Software Systems Jonah Weber May 2, 2006.
Requirements: General, simple, and fast, and must model heating at the granularity of architectural objects  Must be able to dynamically calculate temperatures.
© 2011 Xilinx, Inc. All Rights Reserved This material exempt per Department of Commerce license exception TSU Xilinx Tool Flow.
Slide 1 U.Va. Department of Computer Science LAVA Architecture-Level Power Modeling N. Kim, T. Austin, T. Mudge, and D. Grunwald. “Challenges for Architectural.
Determining the Optimal Process Technology for Performance- Constrained Circuits Michael Boyer & Sudeep Ghosh ECE 563: Introduction to VLSI December 5.
Power Reduction for FPGA using Multiple Vdd/Vth
1 3-General Purpose Processors: Altera Nios II 2 Altera Nios II processor A 32-bit soft core processor from Altera Comes in three cores: Fast, Standard,
Design and Characterization of TMD-MPI Ethernet Bridge Kevin Lam Professor Paul Chow.
1 Rapid Estimation of Power Consumption for Hybrid FPGAs Chun Hok Ho 1, Philip Leong 2, Wayne Luk 1, Steve Wilton 3 1 Department of Computing, Imperial.
Lessons Learned The Hard Way: FPGA  PCB Integration Challenges Dave Brady & Bruce Riggins.
1 UCR Hardware Security Primitives with focus on PUFs Slide credit: Srini Devedas and others.
집적회로 Spring 2007 Prof. Sang Sik AHN Signal Processing LAB.
Project Presentation: Physical Unclonable Functions
Advanced Computer Architecture, CSE 520 Generating FPGA-Accelerated DFT Libraries Chi-Li Yu Nov. 13, 2007.
Using Cycle Efficiency as a System Designer Metric to Characterize an Embedded DSP and Compare Hard Core vs. Soft Core Advisor Dr. Vishwani D. Agrawal.
J. Christiansen, CERN - EP/MIC
A Crash Course in HARDWARE SIGMil. “Real world” hardware (analog) “Virtual world” hardware (digital)
1 Some Limits of Power Delivery in the Multicore Era Runjie Zhang, Brett H. Meyer, Wei Huang, Kevin Skadron and Mircea R. Stan University of Virginia,
Reminder Lab 0 Xilinx ISE tutorial Research Send me an if interested Looking for those interested in RC with skills in compilers/languages/synthesis,
Somervill RSC 1 125/MAPLD'05 Reconfigurable Processing Module (RPM) Kevin Somervill 1 Dr. Robert Hodson 1
Introduction to FPGA Created & Presented By Ali Masoudi For Advanced Digital Communication Lab (ADC-Lab) At Isfahan University Of technology (IUT) Department.
1 An Improved Block-Based Thermal Model in HotSpot 4.0 with Granularity Considerations Wei Huang 1, Karthik Sankaranarayanan 1, Robert Ribando 3, Mircea.
An FPGA Implementation of the Ewald Direct Space and Lennard-Jones Compute Engines By: David Chui Supervisor: Professor P. Chow.
Supervisor: Fearghal Morgan Analog Devices: Ray Carter Dept. Electronic Engineering NUIG 23 April 2008 Software Driver for ADV7800 Video Decoder Nóirín.
Rinoy Pazhekattu. Introduction  Most IPs today are designed using component-based design  Each component is its own IP that can be switched out for.
EKT303/4 PRINCIPLES OF PRINCIPLES OF COMPUTER ARCHITECTURE (PoCA)
1 RapidIO Testbed Update Chris Conger Honeywell Project 1/25/2004.
A Monte Carlo Simulation Accelerator using FPGA Devices Final Year project : LHW0304 Ng Kin Fung && Ng Kwok Tung Supervisor : Professor LEONG, Heng Wai.
1 Leakage Power Analysis of a 90nm FPGA Authors: Tim Tuan (Xilinx), Bocheng Lai (UCLA) Presenter: Sang-Kyo Han (ECE, University of Maryland) Published.
Improving Energy Efficiency of Configurable Caches via Temperature-Aware Configuration Selection Hamid Noori †, Maziar Goudarzi ‡, Koji Inoue ‡, and Kazuaki.
ESS | FPGA for Dummies | | Maurizio Donna FPGA for Dummies Basic FPGA architecture.
Somervill RSC 1 125/MAPLD'05 Reconfigurable Processing Module (RPM) Kevin Somervill 1 Dr. Robert Hodson 1
Fail-Safe Module for Unmanned Autonomous Vehicle
Peter JansweijerATLAS week: February 24, 2004Slide 1 Preparatory Design Studies MROD-X Use Xilinx Virtex II Pro –RocketIO –PowerPC –Port the current MROD-In.
JouleTrack - A Web Based Tool for Software Energy Profiling Amit Sinha and Anantha Chandrakasan Massachusetts Institute of Technology June 19, 2001.
Students: Avi Urman Kobi Maltinsky Supervisor: Rivkin Ina Semester: Spring 2012.
A Brief Introduction to FPGAs
Back-end Electronics Upgrade TileCal Meeting 23/10/2009.
Maj Jeffrey Falkinburg Room 2E46E
Presenter: Darshika G. Perera Assistant Professor
Summary Remaining Challenges The Future Messages to Take Home.
Raghuraman Balasubramanian Karthikeyan Sankaralingam
Introduction to Programmable Logic
Head-to-Head Xilinx Virtex-II Pro Altera Stratix 1.5v 130nm copper
The Complete Solution for Cost-Effective PCI & CompactPCI Implementations 1.
Instructor: Dr. Phillip Jones
Xilinx ChipScope Pro Overview
Lecture 41: Introduction to Reconfigurable Computing
What-If Testing Framework
ChipScope Pro Software
ChipScope Pro Software
Application-Specific Customization of Soft Processor Microarchitecture
Presentation transcript:

FPGAs for Temperature-Aware Microarchitecture Research Siva Velusamy, Wei Huang, John Lach, Mircea Stan and Kevin Skadron University of Virginia

Motivation Temperature fast becoming a constraint to increasing performance HotSpot [ISCA 03] – tool that can be integrated with power performance simulators to predict temperature Use FPGAs to analyze micro-architecture/temperature interactions validate HotSpot

Methodology Implement temperature sensors on the FPGA fabric Instantiate sensors at various locations on the FPGA along with a soft- microprocessor under test A simple controller can read the temperature from the sensors and control the activity of the system.

Experimental Setup Ring oscillator based temperature sensor Xilinx EDK/ISE software Xilinx XC2VP7 device on an Insight Memec board Embedded PowerPC used as the controller MicroBlaze used as the processor under test FPGA core powered using constant DC supply that allows measurement of current

Temperature Sensor Schematic Sergio Lopez-Buedo and Eduardo Boemo, Making Visible the Thermal Behavior of Embedded Microprocessors on FPGAs, FPGA 2004.

Sensor Implementation Each NOT can be implemented in a single LUT. Each of the LUTs have to be manually placed (RLOC constraints) To achieve similar frequencies, the LUTs need to be manually routed as well.

Sensor Calibration

Application 1: Granularity of Temperature Variations Attempt to determine how big an area is needed to create a local HotSpot Method: Create a “ heater ” unit Sorround it by sensors Vary the size of the heater unit and vary the distance between different heater units.

Application 1: Granularity of Temperature Variations Heater size Distance bet. Heater units Close Medium Distant 2 slices slices slices

Application 2: Clock gating

Application 3: Comparison with HotSpot UnitPower (mW) SensorHotSpot blank left_ppc bot_ppc ppc mb blank

Challenges Dependence on Vdd Vdd bounce/load Especially when coupled with clock gating “ Simple ” soft-processors Core implementation differs from custom microprocessors Area frequency Power models

Conclusion Testbed for temperature-aware micro- architecture experiments. Easy to implement, fine grained granularity Validated HotSpot steady state temperatures to within 10%.