Unformatted text preview:

GP2 General Purpose Computation using Graphics Processors Dinesh Manocha Avneesh Sud http gamma cs unc edu GPGP Spring 2007 Department of Computer Science UNC Chapel Hill The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Instructors Dinesh Manocha dm cs unc edu 962 Avneesh Sud sud cs unc edu 962 1749 1849 Class Schedule Current Time Slot 2 00 3 15pm Mon Wed SN011 Office hours TBD Class mailing list gpgp cs unc edu GPGP What kind of course is it Is it a graphics course GPGP What kind of course is it Is it a graphics course Is it a system course GPGP What kind of course is it Is it a graphics course Is it a system course Is it an application course GPGP What kind of course is it Is it a graphics course Is it a system course Is it an application course It is all of them Is this the right course for me No strict pre requisites Course would borrow concepts from Computer graphics Linear algebra Numerical computations Architectures CPU GPUs Parallel programming data parallel programming Applications Geometric computations Database computations Scientific computing and physical simulation Computer vision Modern Commodity Processors CPU 2 x 3GHz 2 x 4 MB Cache CPU 2 x 3GHz 2 x 4 MB Cache PCI E Bus 4 GB s GPU 1 3 GHz Video Memory 768 MB GPU 1 3 GHz Video Memory 768 MB System Memory 4 GB HyperTransport 20 GB s The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GPUs of Today The GPU on commodity video cards has evolved into an extremely flexible and powerful processor Programmability Precision Power The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GPGP The GPU on commodity video cards has evolved into an extremely flexible and powerful processor Programmability Precision Power This course will address how to harness that power for general purpose computation non rasterization Algorithmic issues Programming and systems Applications The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GeForce 7900 302M Transistors 2005 The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GeForce 7900 302M Transistors OUT OF DATE The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GeForce 8800 600M Transistors 2006 The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Graphics Processing Units GPUs Commodity processor for graphics applications Massively parallel vector processors High memory bandwidth Low memory latency pipeline Programmable High growth rate Power efficient The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GPU Commodity Processor Cell phones Laptops Consoles Desktops PSP The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GPU Commodity Processor Cell phones Laptops Consoles Desktops PSP SuperComputers The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GPU Commodity Processor Cell phones Laptops Consoles Desktops PSP The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL iPhone Graphics Processing Units GPUs Commodity processor for graphics applications Massively parallel vector processors High memory bandwidth Better hides memory latency pipeline Programmable 10 20x more operations per sec than CPUs High growth rate Power efficient The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Parallelism on GPUs Graphics FLOPS GPU 1 3 TFLOPS CPU 25 6 GFLOPS The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Quad SLI 1 3 Billion transistors Jan 2006 The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Graphics Processing Units GPUs Commodity processor for graphics applications Massively parallel vector processors High memory bandwidth Better hides latency pipeline Programmable 10x more memory bandwidth than CPUs High growth rate Power efficient The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL CPU vs GPU Memory Hierarchy Core 1 Core 2 FP FP FP FP FP Registers Registers L1 Dcache L1 Dcache L2 cache DDR2 RAM Registers L1 cache L2 cache GDDR4 RAM The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL CPU vs GPU Memory Hierarchy Broad Level Comparison Core 1 Core 2 FP FP FP FP FP Registers Registers L1 Dcache L1 Dcache L2 cache DDR2 RAM Registers L1 cache L2 cache GDDR4 RAM Write back Write through The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL CPU vs GPU Memory Hierarchy Core 1 Core 2 FP FP FP FP FP Registers Registers L1 Dcache L1 Dcache L2 cache DDR2 RAM Registers L1 cache L2 cache GDDR4 RAM Small 4MB Very small The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL CPU vs GPU Memory Hierarchy Core 1 Core 2 FP FP FP FP FP Registers Registers L1 Dcache L1 Dcache L2 cache DDR2 RAM Registers L1 cache L2 cache Low B W 8GB s GDDR4 RAM High B W 86 GB s The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Graphics Processing Units GPUs Commodity processor for graphics applications Massively parallel vector processors High memory bandwidth Better hides latency pipeline Programmable High growth rate Power efficient The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL GFLOPS for GPUs CPUs Graphics Flops Giga Flops The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Graphics Processing Units GPUs Commodity processor for graphics applications Massively parallel vector processors High memory bandwidth Better hides latency pipeline Programmable High growth rate Power efficient high throughput per watt The UNIVERSITY of NORTH CAROLINA at CHAPEL HILL Computational Power of GPUs Why are GPUs getting faster so fast Arithmetic intensity the specialized nature of GPUs makes it easier to use additional transistors for computation not cache Economics multi billion dollar video game market is the killer application that pays for innovation GPUs and Computer Architecture Current research in computer architecture is looking at Streaming computation Flexible polymorphous computing systems Multi core architecture Heterogeneous architecture More on these topics in the future GPUs and Computer Architecture Current research in computer architecture is looking at Streaming computation Flexible polymorphous computing systems Multi core architecture Heterogeneous architecture GPU like architectures have a lot in common with all these research trends GPUs and Computer Architecture Current research in computer architecture is looking at Streaming computation Flexible polymorphous computing systems Multi core architecture Heterogeneous architecture GPU like architectures have a lot in common with all these research trends We plan to touch on many of these topics as part of the course Is There a Future of GPGPU http www informationweek com news showArticle jhtml articleID 1968 00208 One of the Five Disruptive Technologies for 2007 http www wired com news technology computers 0 72090 0 html tw wn in dex 9 SuperComputing s


View Full Document

UNC-Chapel Hill COMP 790 - Computation using Graphics Processors

Download Computation using Graphics Processors
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Computation using Graphics Processors and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Computation using Graphics Processors and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?