CSC 2231: Parallel Computer Architecture and ... - cs.toronto.edu

CSC 2231: Parallel Computer Architecture and Programming GPUs Prof. Gennady Pekhimenko University of Toronto Fall 2017 The content of this lecture is adapted from the slides of Tor Aamodt (UBC) Project Progress Report Due next week Friday (Nov. 3rd) Ask questions after the class 2 Review #7 GPUs and the Future of Parallel Computin

g Steve Keckler et al., IEEE Micro 2011 Due Nov. 10 3 Review #5 Results Grades (out of 10) Mean: 9.05 10 9 8 7 6 5 4 3

2 1 0 6s 7s 8s 9s 10s 4 What is a GPU?

GPU = Graphics Processing Unit Accelerator for raster based graphics (OpenGL, DirectX) Highly programmable (Turing complete) Commodity hardware 100s of ALUs; 10s of 1000s of concurrent threads NVIDIA Volta: V100 5 +

The GPU is Ubiquitous [APU13 keynote] 6 Early GPU History 1981: 1996: 1999: 2001: 2002: 2005: 2006: IBM PC Monochrome Display Adapter (2D) 3D graphics (e.g., 3dfx Voodoo)

register combiner (NVIDIA GeForce 256) programmable shaders (NVIDIA GeForce 3) floating-point (ATI Radeon 9700) unified shaders (ATI R520 in Xbox 360) compute (NVIDIA GeForce 8800) 7 + process commands Host / Front End / Vertex Fetch transform vertices to screen-space

Vertex Processing generate pertriangle equations Primitive Assembly, Setup generate pixels, delete pixels that cannot be seen Rasterize & Zcull Pixel Shader determine the colors , transparencies and depth of the pixel Texture

do final hidden surface test,blend and write out color and new depth Pixel Engines (ROP) [David Kirk / Wen-mei Hwu] Frame Buffer Controller GPU: The Life of a Triangle 8 + pixel color result of running shader program

9 Why use a GPU for computing? GPU uses larger fraction of silicon for computation than CPU. At peak performance GPU uses order of magnitude less energy per operation than CPU. Rewrite Application CPU 2nJ/op GPU 200pJ/op Order of Magnitude More Energy Efficient However.

Application must perform well 10 + GPU uses larger fraction of silicon for computation than CPU? Control ALU ALU ALU

ALU Cache DRAM DRAM CPU [NVIDIA] GPU 11 CSC 2231: Parallel Computer

Architecture and Programming GPUs Prof. Gennady Pekhimenko University of Toronto Fall 2017 The content of this lecture is adapted from the slides of Tor Aamodt (UBC)