DX100: Programmable Data Access Accelerator for Indirection
Authors:
- Alireza KhademAKAlireza Khadem
- Kamalavasan KamalakkannanKKKamalavasan Kamalakkannan
- Zhenyan ZhuZZZhenyan Zhu
- Akash PoptaniAPAkash Poptani
- Yufeng GuYGYufeng Gu
- Jered Benjamin Dominguez-TrujilloJDJered Benjamin Dominguez-Trujillo
- Nishil TalatiNTNishil Talati
- Daichi FujikiDFDaichi Fujiki
- Scott MahlkeSMScott Mahlke
- Galen ShipmanGSGalen Shipman
- Reetuparna DasRDReetuparna Das
Open Access
- 20 June 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1641-1658
Abstract
No abstract availableAll Related Versions
Funding Information
- NSF (National Science Foundation) (1908601)
- JST PRESTO (JPMJPR22P7)
- National Nuclear Security Administration (89233218CNA000001)
This publication has 119 references indexed in Scilit:
- MLIR: Scaling Compiler Infrastructure for Domain Specific Computation2021
- Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nmIntegration, 2017
- Software prefetching for indirect memory accesses2017
- The RAGE radiation-hydrodynamic codeComputational Science & Discovery, 2008
- Δ-stepping: a parallelizable shortest path algorithmJournal of Algorithms, 2003
- A faster algorithm for betweenness centrality*The Journal of Mathematical Sociology, 2001
- Dynamic access ordering for streamed computationsIEEE Transactions on Computers, 2000
- Tolerating latency through software-controlled prefetching in shared-memory multiprocessorsJournal of Parallel and Distributed Computing, 1991
- Adaptive mesh refinement for hyperbolic partial differential equationsJournal of Computational Physics, 1984
- An O(logn) parallel connectivity algorithmJournal of Algorithms, 1982