Tabla de Contenidos: “…An Example Objective FunctionA Complete Functor for Multiple GPU Devices and the Host Processors; Brief Discussion of a Complete Nelder-Mead Optimization Code; Performance Results on XOR; Performance Discussion; Summary; The C++ Nelder-Mead Template; 3 The CUDA Tool Suite: Profiling a PCA/NLPCA Functor; PCA and NLPCA; Autoencoders; An Example Functor for PCA Analysis; An Example Functor for NLPCA Analysis; Obtaining Basic Profile Information; Gprof: A Common UNIX Profiler; The NVIDIA Visual Profiler: Computeprof; Parallel Nsight for Microsoft Visual Studio; The Nsight Timeline Analysis…”

Tabla de Contenidos: “…Front Cover -- CUDA Fortran for Scientists and Engineers -- Copyright -- Contents -- Preface to the Second Edition -- Preface to the First Edition -- Acknowledgments -- 1 CUDA Fortran programming -- 1 Introduction -- 1.1 A brief history of GPU computing -- 1.2 Parallel computation -- 1.3 Basic concepts -- 1.3.1 A first CUDA Fortran program -- 1.3.1.1 CUDA Fortran compilation -- 1.3.2 Extending to larger arrays -- 1.3.3 Multidimensional arrays -- 1.3.4 Interfaces for device code -- 1.3.5 Managed data -- 1.3.6 Kernel loop directives and CUF kernels -- 1.4 Determining CUDA hardware features and limits -- 1.4.1 Choosing a device to run on -- 1.4.2 Floating point precision -- 1.4.2.1 Accommodating variable precision -- 1.5 Error handling -- 1.6 Compiling CUDA Fortran code -- 1.7 CUDA Driver, Toolkit, and compatibility -- 2 Correctness, accuracy, and debugging -- 2.1 Assessing correctness of results -- 2.1.1 Non-associativity of floating point arithmetic -- 2.1.2 Fused-multiply add -- 2.1.3 Flags affecting floating-point accuracy -- 2.2 Debugging -- 2.2.1 Printing from device code -- 2.2.2 Debugging with cuda-gdb -- 2.2.2.1 System requirements -- 2.2.2.2 Compilation -- 2.2.2.3 Setting breakpoints -- 2.2.2.4 Focus - software and hardware coordinates -- 2.2.2.5 CUDA activity status -- 2.2.2.6 Single-stepping in device code -- 2.2.2.7 Examining program state -- 2.2.3 compute-sanitizer -- 3 Performance measurement and metrics -- 3.1 Measuring execution time -- 3.1.1 Host-device synchronization and CPU timers -- 3.1.2 Timing via CUDA events -- 3.1.3 Nsight Systems command-line interface nsys -- 3.1.3.1 Nsight Systems graphical user interface nsys-ui -- 3.1.4 Customizing profiling with nvtx -- 3.1.4.1 Basic NVTX tooling interfaces -- 3.1.4.2 Advanced NVTX tooling interfaces -- 3.1.4.3 Automated NVTX instrumentation…”

Materias:

“…Para el hombre de hoy…”

Materias: “…Vida cristiana…”