General Programming on the GPU - Confoo

General Programming on the GPU - Confoo

• 1.
  GPUs: Not Justfor Graphics Anymore David Ostrovsky | Couchbase
• 2.
  GPGPU refers tousing a Graphics Processing Unit (GPU) to perform computation in applications traditionally handled by the CPU.
• 3.
  CPU vs. GPUArchitecture
• 4.
  • Image processing,graphics rendering • Fractal images (e.g. Mandelbrot set) • String matching • Distributed queries, MapRecuce • Brute-force cryptographic attacks • Bitcoin mining Embarrassingly Parallel Problems
• 5.
  Amdahl’s Law The speedupof a program using multiple processors in parallel computing is limited by the sequential fraction of the program.
• 6.
  GPGPU Concepts • Texture:A common way to provide the read-only input data stream as a 2D grid. • Frame Buffer: A write-only memory interface for output. • Kernel: The operation to perform on each unit of data. Roughly similar to the body of a loop.
• 7.
  Parallelizing Your Code voidcompute(float in[10000], float *out[10000]) { for(int i=0; i < 10000; i++) *out[i] = func(in[i]); } Texture Frame Buffer Kernel
• 8.
  • OpenCL • Subsetof C99 • Implementations for Intel, AMD, and nVidia GPUs • CUDA • C++ SDK, wrappers for other languages • Only supported on nVidia GPUs GPGPU Frameworks • C++ AMP • Subset of C++ • Microsoft implementation based on DirectX, integrated into Visual Studio • Supports most modern GPUs
• 9.
  • OpenCL • Vendor-specificSDKs, available from Intel, AMD, IBM, and nVidia • Wrappers for popular languages, including C#, Python, Java, etc. • Supports multiple vendor- specific debuggers Client Integration • C++ AMP • Native C++ projects, P/Invoke from .NET, WinRT component, any language that can interoperate with native libraries • Supports GPU debugging, profiling
• 10.
  Using C++ AMP extern"C" __declspec ( dllexport ) void _stdcall square_array(float* arr, int n) { array_view<float,1> dataView(n, &arr[0]); parallel_for_each(dataView.extent, [=] (index<1> idx) restrict(amp) { dataView[idx] = dataView[idx] * dataView[idx]; }); dataView.synchronize(); } Native DLL
• 11.
  Using C++ AMP [DllImport("NativeAmpLibrary",CallingConvention = CallingConvention.StdCall)] extern unsafe static void square_array(float* array, int length); float[] arr = new[] { 1.0f, 2.0f, 3.0f, 4.0f }; fixed (float* arrPt = &arr[0]) { square_array(arrPt, arr.Length); } Managed Code
• 12.
  Using OpenCL C# ProjectNuGet Package
• 13.
  Using OpenCL OpenCL Code
• 14.
  Using Aparapi (OpenCL) AparapiJava Code • Converts Java bytecode to OpenCL at runtime • Syntax somewhat similar to C++ AMP final float[] data = new float[size]; Kernel kernel = new Kernel(){ @Override public void run() { int gid = getGlobalId(); data[gid] = data[gid] * data[gid]; } }; kernel.execute(Range.create(512));
• 15.
  Demo Time! Simple GPGPUApplications
• 16.
  Case Study 1:Edge Detection Sobel Operator Pixels can be checked in parallel Find all the points in the image where the brightness changes sharply.
• 17.
  More Demo Time! Processinga Video Stream
• 18.
  Case Study 2:Password Cracking Passwords are commonly stored as hashes of the original plain text: "12345" = "5994471abb01112afcc18159f6cc74b4f511b99806da59b3caf5a9c173cacfc5" Cracking a password by brute force requires repeatedly hashing guesses until a match is found – can be parallelized effectively.
• 19.
  Even More Demos! Crackinga Single Password Hash with a Dictionary Attack
• 21.
  Thank you! @DavidOstrovsky CodeHardBlog.azurewebsites.net linkedin.com/in/davidostrovsky davido@couchbase.com David Ostrovsky| Couchbase