Download as PDF, PPTX
Uploaded byChakkrit (Kla) Tantithamthavorn
Introduction to GPU Programming
GPU computing provides a way to access the power of massively parallel graphics processing units (GPUs) for general purpose computing. GPUs contain over 100 processing cores and can achieve over 500 gigaflops of performance. The CUDA programming model allows programmers to leverage this parallelism by executing compute kernels on the GPU from their existing C/C++ applications. This approach democratizes parallel computing by making highly parallel systems accessible through inexpensive GPUs in personal computers and workstations. Researchers can now explore manycore architectures and parallel algorithms using GPUs as a platform.
In this document
Powered by AI
Overview of GPU computing by NVIDIA, tutorial speakers and schedule, focused on democratizing parallel computing.
Discusses the golden age of parallel computing, significant architectures, followed by a dark age marked by limited impact and shift to commodity technology.
Explains GPU capabilities as multithreaded manycore chips, highlighting NVIDIA Tesla performance and the advantages of using GPUs in various fields.
CUDA as a parallel programming model that democratizes parallel computing, showcasing sales of CUDA-capable GPUs and affordable developer kits.
Introduction to GPU computing motivation, showcasing performance metrics and speedup data in various applications.
Presents peak and sustained performance of GPUs, including theoretical benchmarks and actual application performance figures.
Describes the architecture and functionality of manycore GPUs, focusing on the CUDA programming model and heterogeneous programming strategies.
Details on CUDA programming, including kernel functions, shared memory, and thread identification, aimed at harnessing GPU power for computations.
Introduces NVIDIA's Tesla product line as high-performance computing solutions, detailing specifications of various Tesla models.
Summarizes GPUs as powerful parallel processors with CUDA offering accessible programming models and large research opportunities, followed by a Q&A.
Introduction to GPU Programming
- 1. GPU Computing: The Democratizationof Parallel Computing David Luebke NVIDIA Research
- 2. Tutorial Speakers David Luebke NVIDIA Research Kevin Skadron University of Virginia Michael Garland NVIDIA Research John Owens University of California Davis © NVIDIA Corporation 2007
- 3. Tutorial Schedule 1:30 –1:55 Introduction & Motivation Luebke 1:55 – 2:15 Manycore architectural trends Skadron 2:15 – 3:15 CUDA model & programming Garland 3:15 – 3:30 Break 3:30 – 4:00 GPU architecture & implications Luebke 4:00 – 5:00 Advanced data-parallel programming Owens 5:00 – 5:30 Architectural lessons & research opportunities Skadron © NVIDIA Corporation 2007
- 4. Parallel Computing’s GoldenAge 1980s, early `90s: a golden age for parallel computing Particularly data-parallel computing Architectures Connection Machine, MasPar, Cray True supercomputers: incredibly exotic, powerful, expensive Algorithms, languages, & programming models Solved a wide variety of problems Various parallel algorithmic models developed P-RAM, V-RAM, circuit, hypercube, etc. © NVIDIA Corporation 2007
- 5. Parallel Computing’s DarkAge But…impact of data-parallel computing limited Thinking Machines sold 7 CM-1s (100s of systems total) MasPar sold ~200 systems Commercial and research activity subsided Massively-parallel machines replaced by clusters of ever-more powerful commodity microprocessors Beowulf, Legion, grid computing, … Massively parallel computing lost momentum to the inexorable advance of commodity technology
- 6. Enter the GPU GPU = Graphics Processing Unit Chip in computer video cards, PlayStation 3, Xbox, etc. Two major vendors: NVIDIA and ATI (now AMD) © NVIDIA Corporation 2007
- 7. Enter the GPU GPUs are massively multithreaded manycore chips NVIDIA Tesla products have up to 128 scalar processors Over 12,000 concurrent threads in flight Over 470 GFLOPS sustained performance Users across science & engineering disciplines are achieving 100x or better speedups on GPUs CS researchers can use GPUs as a research platform for manycore computing: arch, PL, numeric, … © NVIDIA Corporation 2007
- 8. Enter CUDA CUDA is a scalable parallel programming model and a software environment for parallel computing Minimal extensions to familiar C/C++ environment Heterogeneous serial-parallel programming model NVIDIA’s TESLA GPU architecture accelerates CUDA Expose the computational horsepower of NVIDIA GPUs Enable general-purpose GPU computing CUDA also maps well to multicore CPUs! © NVIDIA Corporation 2007
- 9. The Democratization of Parallel Computing GPU Computing with CUDA brings data-parallel computing to the masses Over 46,000,000 CUDA-capable GPUs sold A “developer kit” costs ~$200 (for 500 GFLOPS) Data-parallel supercomputers are everywhere! CUDA makes this power accessible We’re already seeing innovations in data-parallel computing Massively parallel computing has become a commodity technology! © NVIDIA Corporation 2007
- 10. GPU Computing: Motivation
- 11. 17X 45X 100X 13–457x GPU Computing: 110-240X Motivation 35X
- 12. GPUs Are Fast Theoretical peak performance: 518 GFLOPS Sustained μbenchmark performance: Raw math: 472 GFLOPS (8800 Ultra) Raw bandwidth: 80 GB per second (Tesla C870) Actual application performance: Molecular dynamics: 290 GFLOPS (VMD ion placement) © NVIDIA Corporation 2007
- 13. GPUs Are GettingFaster, Faster © NVIDIA Corporation 2007
- 14. Manycore GPU –Block Diagram G80 (launched Nov 2006 – GeForce 8800 GTX) 128 Thread Processors execute kernel threads Up to 12,288 parallel threads active Per-block shared memory (PBSM) accelerates processing Host Input Assembler Thread Execution Manager Thread Processors Thread Processors Thread Processors Thread Processors Thread Processors Thread Processors Thread Processors Thread Processors PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM PBSM Load/store © NVIDIA Corporation 2007 Global Memory
- 15.
- 16. Heterogeneous Programming CUDA = serial program with parallel kernels, all in C Serial C code executes in a CPU thread Parallel kernel C code executes in thread blocks across multiple processing elements Serial Code Parallel Kernel KernelA<<< nBlk, nTid >>>(args); ... Serial Code Parallel Kernel KernelB<<< nBlk, nTid >>>(args); ...
- 17. GPU Computing withCUDA: A Highly Multithreaded Coprocessor The GPU is a highly parallel compute device serves as a coprocessor for the host CPU has its own device memory on the card executes many threads in parallel Parallel kernels run a single program in many threads GPU threads are extremely lightweight Thread creation and context switching are essentially free GPU expects 1000’s of threads for full utilization © NVIDIA Corporation 2007
- 18. CUDA: Programming GPUin C Philosophy: provide minimal set of extensions necessary to expose power Declaration specifiers to indicate where things live __global__ void KernelFunc(...); // kernel function, runs on device __device__ int GlobalVar; // variable in device memory __shared__ int SharedVar; // variable in per-block shared memory Extend function invocation syntax for parallel kernel launch KernelFunc<<<500, 128>>>(...); // launch 500 blocks w/ 128 threads each Special variables for thread identification in kernels dim3 threadIdx; dim3 blockIdx; dim3 blockDim; dim3 gridDim; Intrinsics that expose specific operations in kernel code __syncthreads(); // barrier synchronization within kernel
- 19. Decoder Ring GeForce® Quadro® TeslaTM Entertainment Design & Creation High Performance Computing Architecture: TESLA © NVIDIA Corporation 2007 Chips: G80, G84, G92, …
- 20. A New Platform:Tesla HPC-oriented product line C870: board (1 GPU) D870: deskside unit (2 GPUs) S870: 1u server unit (4 GPUs) © NVIDIA Corporation 2007
- 21. Conclusion GPUs are massively parallel manycore computers Ubiquitous - most successful parallel processor in history Useful - users achieve huge speedups on real problems CUDA is a powerful parallel programming model Heterogeneous - mixed serial-parallel programming Scalable - hierarchical thread execution model Accessible - minimal but expressive changes to C They provide tremendous scope for innovative, impactful research © NVIDIA Corporation 2007
- 22. Questions? David Luebke dluebke@nvidia.com