dynamic optimization for interactive computing systems

9
Dynamic Optimization for Interactive Computing Systems Parallel Computing Laboratory Sarah Bird February 23, 2012

Upload: john

Post on 23-Feb-2016

34 views

Category:

Documents


0 download

DESCRIPTION

Dynamic Optimization for Interactive Computing Systems . Parallel Computing Laboratory Sarah Bird February 23 , 2012. Multicore Revolution. Parallel Computing is becoming ubiquitous Only way forward for computing industry (unless you don’t care if your apps never run faster than in 2008) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Dynamic Optimization for  Interactive Computing Systems

Dynamic Optimization for Interactive Computing Systems

Parallel Computing LaboratorySarah Bird

February 23, 2012

Page 2: Dynamic Optimization for  Interactive Computing Systems

Multicore Revolution• Parallel Computing is becoming ubiquitous

– Only way forward for computing industry (unless you don’t care if your apps never run faster than in 2008)

– Unfortunately, parallel programming is (still) harder than sequential programming

Harness the power of parallelism for client applications

Page 3: Dynamic Optimization for  Interactive Computing Systems

Bridging the GapParallel

ApplicationsParallel Hardware

Parallel Software

IT industry Users

Krste Asanovic, Ras Bodik, Jim Demmel, Armando Fox,Tony Keaveny, Kurt Keutzer, John Kubiatowicz, Nelson Morgan,

Dave Patterson, Koushik Sen, John Wawrzynek, David Wessel, and Kathy Yelick

Page 4: Dynamic Optimization for  Interactive Computing Systems

Pediatric MRITypical exam ~ 1 hourMotion blurs the imagesScanner is a small loud tunnel

Difficult for children to stay still!

Traditional Solution: Anesthesia

Compressed Sensing reduces each scan to

15 secondsTakes too long to

reconstruct image~ Hours

Page 5: Dynamic Optimization for  Interactive Computing Systems

Compressed Sensing for Pediatric MRIImage reconstruction from 1-2 hours down to < 1 min

Page 6: Dynamic Optimization for  Interactive Computing Systems

PACORA

Runti

me

Cores Cache

Flawless user experience while maximizing battery life!

Speech Decoder

RuntimeService

Requirement

s = slope

d

Pena

lty

OS Resource Allocation Framework Apps don’t miss deadlines Turn off unnecessary resources Developers don’t need to understand

hardware

How do I guarantee interactivity on my multicore device when it’s running a bunch of apps?

Page 7: Dynamic Optimization for  Interactive Computing Systems

More Great ParLab ResearchCommunication-Avoiding Linear Algebra• Order of magnitude speedups over optimized code • 8.8x faster than Intel’s MKL

ParLab SEJITS project:Selected Embedded Just-in-Time Specialization Asp: “Asp is SEJITS in Python” general specializer

framework Performance of highly optimized C with the

productivity of Python!

Music Application Research• New user interfaces with

pressure-sensitive multi-touch gestural interfacesMulticore GPU

App

Dense Sparse

Page 8: Dynamic Optimization for  Interactive Computing Systems

Parallel Computing Laboratory• User-centric research agenda• Better user-interface programming across

diversity of devices• Data capsules for secure data access• Heterogeneity to improve performance and

reduce energy• Dynamic client+cloud partitioning to improve

efficiency

Future of Personal Computing

Page 9: Dynamic Optimization for  Interactive Computing Systems

Join us at ParLab for Lunch!5th Floor Soda Hall

A Real Time, Parallel GUI Service in Tessellation Many Core OSSynthesizing a Parallel Web Browser Layout Engine An Automatic Parallelizing and Vectorizing Compiler for Python Loop-NestsEnabling Specialization via MapReduce Accelerating Graph Algorithms by Software Optimization & Hardware Modification

Characterizing Memory Hierarchies of Multicore Processors Using Microbenchmarks Garbage Collection on GPUsDebugging SEJITSHardware Communication Channels for Quality-of-Service Enforcement OLOV: OpenCL for OpenCVMegh: A Cloud Backed File SystemParallelizing Machine Translation Training Pipeline with HadoopCDT: An interactive compiler translation debugger for SEJITS specializers PACORA: Performance-Aware Convex Optimization for Resource AllocationpOSKI Project UpdatesSEJITS in the CloudCommunication Costs of LU Decomposition Algorithms for Banded Matrices