Data-Level Parallelism in Vector, SIMD, and GPU Architectures - Computer Architecture: A Quantitative Approach - page 290

FIGURE 4.12 Quick guide to GPU terms used in this chapter . We use the first column for
hardware terms. Four groups cluster these 11 terms. From top to bottom: Program Abstrac-
tions, Machine Objects, Processing Hardware, and Memory Hardware. Figure 4.21 on page
309 associates vector terms with the closest terms here, and Figure 4.24 on page 313 and
Figure 4.25 on page 314 reveal the official CUDA/NVIDIA and AMD terms and definitions
along with the terms used by OpenCL.
We use NVIDIA systems as our example as they are representative of GPU architectures.
Speciically, we follow the terminology of the CUDA parallel programming language above
and use the Fermi architecture as the example (see Section 4.7 ).