GPGPUs for High Performance Computing

22 slides
7.48 MB

Similar Presentations

Presentation Transcript


GPGPUs and CUDA Guest LectureComputing with GPGPUsRaj Singh National Center for Microscopy and Imaging Research


GPGPUs and CUDA Guest LectureHaze


GPGPUs and CUDA Guest LectureGraphics Processing Unit (GPU)Development driven by the multi-billion dollar game industry Bigger than Hollywood Need for physics, AI and complex lighting models Impressive Flops / dollar performance Hardware has to be affordable Evolution speed surpasses Moore’s law Performance doubling approximately 6 months


GPGPUs and CUDA Guest LectureGPU evolution curve*Courtesy: Nvidia Corporation


GPGPUs and CUDA Guest LectureGPGPUs (General Purpose GPUs)A natural evolution of GPUs to support a wider range of applications Widely accepted by the scientific community Cheap high-performance GPGPUs are now available Its possible to buy a $500 card which can provide almost 2 TFlops of computing.


GPGPUs and CUDA Guest LectureTeraflop computingSupercomputers are still rated in Teraflops Expensive and power hungry Not exclusive and have to be shared by several organizations Custom built in several cases National Center for Atmospheric Research, Boulder installed a 12 Tflop supercomputer in 2007


GPGPUs and CUDA Guest LectureWhat does it mean for the scientist ?Desktop supercomputers are possible Energy efficient Approx 200 Watts / Teraflop Turnaround time can be cut down by magnitudes. Simulations/Jobs can take several days


GPGPUs and CUDA Guest LectureGPU hardwareHighly parallel architecture Akin to SIMD Designed initially for efficient matrix operations and pixel manipulations pipelines Computing core is lot simpler No memory management support 64-bit native cores Little or no cache Double precision support.


GPGPUs and CUDA Guest LectureMulti-core HorsepowerLatest Nvidia card has 480 cores for simultaneous processing Very high memory bandwidth > 100 GBytes / sec and increasing Perfect for embarrassingly parallel compute intensive problems Clusters of GPGPUs available in GreenLight Figures courtesy: Nvidia programming guide 2.0


GPGPUs and CUDA Guest LectureCPU v/s GPU


GPGPUs and CUDA Guest LectureProgramming modelThe GPU is seen as a compute device to execute a portion of an application that Has to be executed many times Can be isolated as a function Works independently on different data Such a function can be compiled to run on the device. The resulting program is called a Kernel C like language helps in porting existing code. Copies of kernel execute simultaneously as threads.Figure courtesy: Nvidia programming guide 2.0


GPGPUs and CUDA Guest LectureLook Ma no cache ..Cache is expensive By running thousands of fast-switching light threads large memory latency can be masked Context switching of threads is handled by CUDA Users have little control, only synchronization


GPGPUs and CUDA Guest LectureCUDA / OpenCLA non-OpenGL oriented API to program the GPUs Compiler and tools allow porting of existing C code fairly rapidly Libraries for common math functions like trigonometric, pow(), exp() Provides support for general DRAM memory addressing Scatter / gather operations


GPGPUs and CUDA Guest LectureWhat do we do at NCMIR / CALIT2 ?Research on large data visualization, optical networks and distributed system. Collaborate with Earth sciences, Neuroscience, Gene research, Movie industry Large projects funded by NSF / NIHNSF EarthScope


GPGPUs and CUDA Guest LectureElectron and Light Microscopes


GPGPUs and CUDA Guest LectureCluster Driven High-Resolution displays data end-points


GPGPUs and CUDA Guest LectureElectron TomographyUsed for constructing 3D view of a thin biological samples Sample is rotated around an axis and images are acquired for each ‘tilt’ angle Electron tomography enables high resolution views of cellular and neuronal structures. 3D reconstruction is a complex problem due to high noise to signal ratio, curvilinear electron path, sample deformation, scattering, magnetic lens aberrations…Biological sampleTilt series imagesCurvilinear electron path


GPGPUs and CUDA Guest LectureChallengesUse a Bundle Adjustment procedure to correct for curvilinear electron path and sample deformation Evaluation of electron micrographs correspondences needs to be done with double precision when using high-order polynomial mappings Non-linear electron projection makes reconstruction computationally intensive. Wide field of view for large datasets CCD cameras are up to 8K x 8K


GPGPUs and CUDA Guest LectureReconstruction on GPUsLarge datasets take up to several days to reconstruct on a fast serial processor. Goal is to achieve real-time reconstruction Computation is embarrassingly parallel at the tilt level GTX 280 with double-precision support and 240 cores has shown speedups between 10X – 50X for large data Tesla units with 4Tflops are the next target for the code.


GPGPUs and CUDA Guest LectureReally ? Free Lunch ?C-like language support Missing support for function pointers, recursion, double precision not as accurate as CPUs, no direct access to I/O Cannot pass structures, unions Code has to be fairly simple and free of dependencies Completely self contained in terms of data and variables. Speedups depend on efficient code Programmers have to code the parallelism. No magic spells available for download Combining CPU and GPU code might be better in cases


GPGPUs and CUDA Guest LectureAnd more cons …Performance is best for computation intensive apps. Data intensive apps can be tricky. Bank conflicts hurt performance It’s a black-box with little support for runtime debugging.


GPGPUs and CUDA Guest LectureResources

Browse More Presentations

Last Updated: 8th March 2018

Recommended PPTs