- 于 2009-06-15 加入CSDN
This Best Practices Guide is a manual to help developers obtain the best performance from NVIDIA® CUDA® GPUs. It presents established parallelization and optimization techniques and explains coding metaphors and idioms that can greatly simplify programming for CUDA-capable GPU architectures.
发布资源于 6 年前
‣ Added new section C++11 Language Features, ‣ Clarified that values of const-qualified variables with builtin floating-point types cannot be used directly in device code when the Microsoft compiler is used as the host compiler, ‣ Documented the extended lambda feature, ‣ Documented that typeid, std::type_info, and dynamic_cast are only supported in host code, ‣ Documented the restrictions on trigraphs and digraphs, ‣ Clarified the conditions under which layout mismatch can occur on Windows.
发布资源于 6 年前
Hamiltonian Monte Carlo
Hamiltonian dynamics can be used to produce distant proposals for the Metropolis algorithm, thereby avoiding the slow exploration of the state space that results from the diffusive behaviour of simple random-walk proposals. Though originating in physics, Hamiltonian dynamics can be applied to most problems with continuous state spaces by simply introducing fictitious “momentum” variables. A key to its usefulness is that Hamiltonian dynamics preserves volume, and its trajectories can thus be used to define complex mappings without the need to account for a hard-to-compute Jacobian factor — a property that can be exactly maintained even when the dynamics is approximated by discretizing time. In this review, I discuss theoretical and practical aspects of Hamiltonian Monte Carlo, and present some of its variations, including using windows of states for deciding on acceptance or rejection, computing trajectories using fast approximations, tempering during the course of a trajectory to handle isolated modes, and short-cut methods that prevent useless trajectories from taking much computation time.
发布资源于 7 年前
Discrete Inverse Problems: Insight and Algorithms
Inverse problems arise when we reconstruct a sharper image from a blurred one or reconstruct the underground mass density from measurements of the gravity above the ground. When we solve an inverse problem, we compute the source that gives rise to some observed data using a mathematical model for the relation between the source and the data. This book gives an introduction to the practical treatment of inverse problems by means of numerical methods, with a focus on basic mathematical and computational aspects. To solve inverse problems, we demonstrate that insight about them goes hand in hand with algorithms. Discrete Inverse Problems: Insight and Algorithms includes a number of tutorial exercises that give the reader hands-on experience with the methods, difficulties, and challenges associated with the treatment of inverse problems. It also includes examples and figures that illustrate the theory and algorithms. Audience This book is written for graduate students, researchers, and professionals in engineering and other areas that depend on solving inverse problems with noisy data. The aim is to provide readers with enough background that they can solve simple inverse problems and read more advanced literature on the subject. Contents Preface; List of Symbols; Chapter 1: Introduction and Motivation; Chapter 2: Meet the Fredholm Integral Equation of the First Kind; Chapter 3: Getting to Business: Discretizations of Linear Inverse Problems; Chapter 4: Computational Aspects: Regularization Methods; Chapter 5: Getting Serious: Choosing the Regularization Parameter; Chapter 6: Toward Real-World Problems: Iterative Regularization; Chapter 7: Regularization Methods at Work: Solving Real Problems; Chapter 8: Beyond the 2-Norm: The Use of Discrete Smoothing Norms; Appendix A: Linear Algebra Stuff; Appendix B: Symmetric Toeplitz-Plus-Hankel Matrices and the DCT; Appendix C: Early Work on 揟ikhonov Regularization? Bibliography; Index. About the Author Per Christian Hansen
发布资源于 10 年前