CUDA

Q: How deeply does Starting Data Analytics with Generative AI and Python cover CUDA?

Demonstrates a CuPy rewrite of bootstrap computation and notes that benefits depend on workload size and GPU hardware.

As explained in Starting Data Analytics with Generative AI and Python

CUDA is NVIDIA's parallel-computing platform and programming interface for executing general-purpose computations on compatible GPUs.

CUDA provides an interface for directing suitable computations to an NVIDIA GPU. GPUs perform many identical vector or matrix operations in parallel, making them useful for some scaling tasks. section 7.2.2

CUDA acceleration works best when:

The computation operates on sufficiently large data or performs intensive repeated operations. section 7.2.2
The data and functions use compatible GPU operations rather than relying on NumPy-only behavior. section 7.2.2

GPU-accelerated bootstrapping

Install CuPy, replace NumPy operations with CuPy equivalents, generate bootstrap samples on the GPU, calculate percentiles there, and convert the interval bounds back to NumPy values.

How Starting Data Analytics with Generative AI and Python covers it

Cover of Starting Data Analytics with Generative AI and Python

liveBook manning.com

Read Starting Data Analytics with Generative AI and Python on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Fast Python: High performance techniques for large datasets
liveBook manning.com

Hugging Face in ActionCUDA is NVIDIA's parallel computing platform and programming model for executing general-purpose computations on GPUs.
liveBook manning.com

Inside Deep Learning: Math, Algorithms, ModelsNVIDIA's GPU computing software stack used here as the compute interface for running PyTorch operations on a GPU.

Compare how 4 books explain CUDA →

Related concepts

GPUuses · A graphics processing unit (GPU) is a processor designed for highly parallel computation, especially graphics and data-parallel workloads.
PyTorchused by · PyTorch is an open-source machine-learning framework for Python that provides tensor computation, automatic differentiation, and tools for building and training neural networks.
shared memoryconfigures · Shared memory is a memory region or storage area accessible to multiple processes, threads, or other execution components for accessing or exchanging data.

This explainer was generated by Manning's knowledge graph from the text of Starting Data Analytics with Generative AI and Python. The section links point to the parts of the book it draws on.