01c GPU Architecture Overview (SIGGRAPH 2007)

01c GPU Architecture Overview (SIGGRAPH 2007) - GPU...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
GPU Architecture Overview GPU Architecture Overview John Owens John Owens UC Davis UC Davis
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
The Right-Hand Turn The Right-Hand Turn [H&P Figure 1.1]
Background image of page 2
3 Why? [Architecture Reasons] Why? [Architecture Reasons] ILP increasingly difficult to extract from instruction stream Control hardware dominates µ processors – Complex, difficult to build and verify – Takes substantial fraction of die – Scales poorly • Pay for max throughput, sustain average throughput • Quadratic dependency checking – Control hardware doesn’t do any math! • Intel Core Duo: 48 GFLOPS, ~10 GB/s • NVIDIA G80: 330 GFLOPS, 80+ GB/s
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 AMD AMD Deerhound Deerhound (K8L) (K8L) chip-architect.com
Background image of page 4
5 Why? [Technology Reasons] Why? [Technology Reasons] Industry moving from “instructions per second” to “instructions per watt” – “Power wall” now all-important – Traditional µ proc techniques are not power-efficient We can continue to put more transistors on a chip … – … but we can’t scale their voltage like we used to … – … and we can’t clock them as fast …
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Go Parallel Go Parallel Time of architectural innovation – GPUs let us explore using hundreds of processors now, not 10 years from now Major CPU vendors supporting multicore Interest in general-purpose programmability on GPUs Universities must teach thinking in parallel
Background image of page 6
7 What What s Different about the GPU? s Different about the GPU? The future of the desktop is parallel – We just don’t know what kind of parallel GPUs and multicore are different – Multicore: Coarse, heavyweight threads, better
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/29/2010 for the course CSE 4190.410 taught by Professor Shinyeonggil during the Spring '09 term at Seoul National.

Page1 / 22

01c GPU Architecture Overview (SIGGRAPH 2007) - GPU...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online