Learn in 21 days - 9798183777802 - cuda programming in 21 days: a hands-on course in c++ and python (learn in 21 days) von saqib, mohammad (3 Ergebnisse)

PAP. Zustand: New. New Book. Shipped from UK. Established seller since 2000.

PAP. Zustand: New. New Book. Shipped from UK. Established seller since 2000.

Taschenbuch. Zustand: Neu. Neuware - CUDA Programming in 21 DaysA Hands-On Course in C++ and Python>================================================================Go from 'what even is a GPU ' to writing, debugging, and tuningyour own CUDA kernels - in three focused weeks.>Most GPU books are either a wall of reference material or a thinlayer of copy-paste recipes. This one is a course. Each day is asingle sitting that builds on the last, teaches one ideaproperly, and ends with a workshop so the knowledge lands in your>You write REAL CUDA C++ that compiles with nvcc, and you see thePython equivalent (CuPy and Numba) alongside every step, so youcan run and experiment even before your C++ is fluent. Every>WHAT YOU GET- 21 chapters (3 weeks x 7 days), 1.2 million words of careful, worked teaching - no filler.- 229 figures, diagrams, and plots, every one generated from areal computation or a clean schematic.- Hundreds of runnable listings in CUDA C++, CuPy, and Numba.>THE THREE WEEKSWeek 1 - Get onto the GPU: why GPUs win, the toolkit, yourfirst kernel, thread indexing, moving data, and debugging.Week 2 - Make it fast: the memory hierarchy, coalescing, shared memory and tiling, synchronization, warps anddivergence, occupancy, and honest profiling with a roofline.Week 3 - Patterns, libraries, and a real project: reduction, atomics, scan, streams and overlap, Thrust/cuBLAS/cuFFT/CuPy, >WHO IT'S FORYou know a little C or C++ and a little Python. You do NOT needany GPU experience. You do not even need an expensive GPU - anyrecent NVIDIA card works, and Day 2 shows you how to run every>BY DAY 21 YOU CAN- decide whether a problem suits a GPU, and why;- write, launch, and debug your own kernels;- lay out memory and choose a launch configuration for speed;- use reductions, scans, atomics, and streams with confidence;- reach for the right library - and verify its result;>The GPU stops being a black box. Go build something that neededall those threads.…