dynamic optimization for interactive computing systems
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 PresentationTRANSCRIPT
Dynamic Optimization for Interactive Computing Systems
Parallel Computing LaboratorySarah 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)
– Unfortunately, parallel programming is (still) harder than sequential programming
Harness the power of parallelism for client applications
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
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
Compressed Sensing for Pediatric MRIImage reconstruction from 1-2 hours down to < 1 min
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?
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
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
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