CUDA Architecture
Download as PPT, PDF16 likes4,381 views
This document provides an overview of CUDA architecture and programming. It discusses key CUDA concepts like the host/device model, CUDA C extensions, GPU memory management, and parallel programming using CUDA threads and blocks. CUDA allows developers to speed up applications by offloading work to the GPU. It provides a scalable parallel programming model that maps threads to GPU threads to express data-level parallelism across thousands of lightweight threads for applications like high-bandwidth computing and visual computing.
CUDA Architecture
- 1. CUDAArchitecture Prof. Shashikant V. Athawale Assistant Professor | Computer Engineering Department | AISSMS College of Engineering, Kennedy Road, Pune , MH, India - 411001
- 2. Contents ❖ CUDAArchitecture ❖ Applications of CUDA ❖ Introduction to CUDA C-Write and launch CUDA C kernels ❖ Manage GPU memory ❖ Manage communication and synchronization ❖ Parallel programming in CUDA- C.
- 3. Communication And Synchronization in Thread
- 4. Communication And Synchronization in Thread
- 8. CUDA C : The Basics ❖ Based on industry-standard C ❖ A handful of language extensions to allow heterogeneous programs ❖ Straightforward APIs to manage devices, memory, etc. ❖ Terminology: ➢ Host – The CPU and its memory (host memory) ➢ Device – The GPU and its memory (device memory) Device
- 9. CUDA Kernels
- 11. Data Transfer Directions Keywords ❖ cudaMemcpyHostToHost ❖ cudaMemcpyHostToDevice ❖ cudaMemcpyDeviceToHost ❖ cudaMemcpyDeviceToDevice
- 12. Parallel Programming in CUDA C ❖ CUDA brings data-parallel computing to the masses. ❖ CUDA is a scalable parallel programming model. ❖ Program runs on any number of processors without recompiling.
- 13. Architecture Of Parallel CUDA Programming
- 14. CUDA Uses Extensive Multithreading ❖ CUDA threads express fine-grained data parallelism. ➢ Map threads to GPU threads. ➢ Virtualize the processors. ❖ CUDA thread blocks express coarse-grained parallelism. ➢ Blocks hold arrays of GPU threads, define shared memory boundaries. ➢ Allow scaling between smaller and larger GPUs.
- 15. CUDA Uses Extensive Multithreading ❖ GPUs execute thousands of lightweight threads. ➢ In graphics, each thread computes one pixel. ➢ One CUDA thread computes one result (or several results). ➢ Hardware multithreading & zero-overhead scheduling.
- 16. Applications ❖ High bandwidth ❖ Visual computing ❖ High arithmetic intensity