Understanding sources of inefficiency in general-purpose chips

Rehan Hameed; Wajahat Qadeer; Megan Wachs; Omid Azizi; Alex Solomatnikov; Benjamin C Lee; Stephen Richardson; Christos Kozyrakis; Mark Horowitz

doi:10.1145/2001269.2001291

Understanding sources of inefficiency in general-purpose chips

Rehan Hameed Stanford

Wajahat Qadeer

Megan Wachs

Omid Azizi

Alex Solomatnikov

Benjamin C Lee

Stephen Richardson

Christos Kozyrakis Stanford

Mark Horowitz Stanford

Communications of the ACM (CACM), 2011

DOI: 10.1145/2001269.2001291

Abstract

Scaling the performance of a power-limited processor requires decreasing the energy expended per instruction. This article quantifies the performance and energy overheads of a 720p HD H.264 encoder running on a general-purpose four-processor CMP system, then explores how broadly applicable and algorithm-specific hardware customizations can eliminate those overheads. The final customized CMP reaches the same performance as an ASIC solution, within three times its energy and in comparable area.

Materials

paper
CACM

Bibtex

@inproceedings{2011understandingsourcesofinefficiencyingeneralpurposechipscacm,
  title = {Understanding sources of inefficiency in general-purpose chips},
  author = {Rehan Hameed and Wajahat Qadeer and Megan Wachs and Omid Azizi and Alex Solomatnikov and Benjamin C Lee and Stephen Richardson and Christos Kozyrakis and Mark Horowitz},
  booktitle = {Communications of the ACM (CACM)},
  year = {2011},
  doi = {10.1145/2001269.2001291},
}

Hi, we are the Stanford MAST team

Understanding sources of inefficiency in general-purpose chips

Abstract

Materials

Bibtex