Asmdb: Understanding and mitigating front-end stalls in warehouse-scale computers

Nayana Prasad Nagendra; Grant Ayers; David I August; Hyoun Kyu Cho; Svilen Kanev; Christos Kozyrakis; Trivikram Krishnamurthy; Heiner Litz; Tipp Moseley; Parthasarathy Ranganathan

doi:10.1145/3307650.3322234

Asmdb: Understanding and mitigating front-end stalls in warehouse-scale computers

Nayana Prasad Nagendra

Grant Ayers Stanford

David I August

Hyoun Kyu Cho

Svilen Kanev

Christos Kozyrakis Stanford

Trivikram Krishnamurthy

Heiner Litz Stanford

Tipp Moseley

Parthasarathy Ranganathan Google

International Symposium on Computer Architecture (ISCA), 2020

DOI: 10.1145/3307650.3322234

Abstract

It is well known that the datacenters hosting today’s cloud services waste a significant number of cycles on front-end stalls. However, prior work has provided little insights about the source of these front-end stalls and how to address them. This work analyzes the cause of instruction cache misses at a fleet-wide scale and proposes a new compiler-driven software code prefetching strategy to reduce instruction caches misses by 90%.

Materials

Bibtex

@inproceedings{2020asmdbunderstandingandmitigatingfrontendstallsinwarehousescalecomputers,
  title = {Asmdb: Understanding and mitigating front-end stalls in warehouse-scale computers},
  author = {Nayana Prasad Nagendra and Grant Ayers and David I August and Hyoun Kyu Cho and Svilen Kanev and Christos Kozyrakis and Trivikram Krishnamurthy and Heiner Litz and Tipp Moseley and Parthasarathy Ranganathan},
  booktitle = {International Symposium on Computer Architecture (ISCA)},
  year = {2020},
  doi = {10.1145/3307650.3322234},
}

Hi, we are the Stanford MAST team

Asmdb: Understanding and mitigating front-end stalls in warehouse-scale computers

Abstract

Materials

Bibtex