Everything About ___
Live briefing

Everything about CUDA

Parallel computing platform and programming model

CUDA is a proprietary parallel computing platform and application programming interface (API) developed by Nvidia that allows software to use certain types of graphics processing units (GPUs) for accelerated general-purpose processing, significantly broadening their utility in artificial intelligence, scientific and high-performance computing. CUDA was created in 2004 and was officially released in 2007. When introduced, the name was an acronym for Compute Unified Device Architecture, but Nvidia later dropped the initial meaning of the acronym and now rarely expands it. Wikipedia →

🧭 Start here: a 6-step reading path

  1. Read the overview: CUDAA 5-minute orientation
  2. Skim a recent paper: Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption LibraryInfluential work since 2022
  3. Pick up a classic book: CUDA for engineersThe most-reprinted book on the subject
  4. Read the landmark paper: Scalable Parallel Programming with CUDACited 1,582 times
  5. Go sideways: CuPyA closely related topic
  6. Go sideways: ROCmA closely related topic

📖 Definitions

Noun A barracuda.

🗂️ The subject at a glance

  1. Graphics processing unit
  2. History
  3. Ontology
  4. Programming abilities
  5. Advantages
  6. Limitations
  7. Example
  8. GPUs supported
  9. Version features and specifications
  10. Usages of CUDA architecture
  11. Comparison with competitors

🏆 Landmark papers (most cited)

🆕 Influential since 2022

📚 Books worth reading

Ranked by number of editions on Open Library, a rough measure of how lasting a book is.

🔗 Related topics