Filters








14 Hits in 2.6 sec

iGPU: Exception support and speculative execution on GPUs

Jaikrishnan Menon, Marc de Kruijf, Karthikeyan Sankaralingam
2012 2012 39th Annual International Symposium on Computer Architecture (ISCA)  
Exception support and speculative execution are the next steps to expand the scope and improve the usability of GPUs.  ...  This paper builds on two related insights to provide a unified lightweight mechanism for supporting exceptions and speculation on GPUs.  ...  Acknowledgments We thank the anonymous reviewers, the Vertical group, and Mark Gebhart for comments. Many thanks to Steve  ... 
doi:10.1109/isca.2012.6237007 dblp:conf/isca/MenonKS12 fatcat:l7js6vnw2bcctduetmpjacmrdy

iGPU

Jaikrishnan Menon, Marc De Kruijf, Karthikeyan Sankaralingam
2012 SIGARCH Computer Architecture News  
Exception support and speculative execution are the next steps to expand the scope and improve the usability of GPUs.  ...  This paper builds on two related insights to provide a unified lightweight mechanism for supporting exceptions and speculation on GPUs.  ...  Acknowledgments We thank the anonymous reviewers, the Vertical group, and Mark Gebhart for comments. Many thanks to Steve  ... 
doi:10.1145/2366231.2337168 fatcat:tylnlqwudrgjjllwvx5oxhkqiq

iGPU-Accelerated Pattern Matching on Event Streams

Marius Kuhrt, Michael Körber, Bernhard Seeger
2022 Data Management on New Hardware  
In addition, hardware accelerators based on dedicated GPUs also offer limited support due to the overhead of transferring data between their local and main memory.  ...  This paper presents the first full-fledged implementation of pattern matching cooperatively using iGPUs and CPUs.  ...  ACKNOWLEDGMENTS This work has been supported by the German Research Foundation (DFG) under grant no. SE 553/9-1.  ... 
doi:10.1145/3533737.3535099 fatcat:tcrj6saitjh7jbmte3o6dd5soe

Pattern of Pediatric Toxicity in Saudi Arabia-Eastern Province (Incidence, Demographics and Predisposing Factors)

Ahmed Refat Ragab
2015 Pediatrics & Therapeutics  
Exception support and speculative execution are the next steps to expand the scope and improve the usability of GPUs.  ...  This paper builds on two related insights to provide a unified lightweight mechanism for supporting exceptions and speculation on GPUs.  ...  Acknowledgments We thank the anonymous reviewers, the Vertical group, and Mark Gebhart for comments. Many thanks to Steve  ... 
doi:10.4172/2161-0665.1000220 fatcat:5sdip55i6zepzj4yd2gtzvupri

APUNet: Revitalizing GPU as Packet Processing Accelerator

Younghwan Go, Muhammad Asim Jamshed, YoungGyoun Moon, Changho Hwang, KyoungSoo Park
2017 Symposium on Networked Systems Design and Implementation  
to the Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation is sponsored by USENIX.  ...  Acknowledgments We would like to thank our shepherd Fabián Bustamante and anonymous reviewers of NSDI'17 for their insightful comments and suggestions on the paper.  ...  We also thank Anuj Kalia at CMU for in-depth discussion on experiment results and further suggestions, and Seong Hwan Kim and Dipak Bhattacharyya at AMD, Inc., for their help in understanding the internals  ... 
dblp:conf/nsdi/GoJMHP17 fatcat:3ght6653hfhbfmawnmz2likfkm

Enabling GPGPU Low-Level Hardware Explorations with MIAOW

Raghuraman Balasubramanian, Pradip Valathol, Karthikeyan Sankaralingam, Vinay Gangadhar, Ziliang Guo, Chen-Han Ho, Cherin Joseph, Jaikrishnan Menon, Mario Paulo Drumond, Robin Paul, Sharath Prasad
2015 ACM Transactions on Architecture and Code Optimization (TACO)  
Further, as GPGPU research evolves, design ideas and modifications demand detailed estimates of impact on overall area and power.  ...  Today's tools for GPU analysis include simulators like GPGPU-Sim, Multi2Sim, and Barra.  ...  We have also implemented in MIAOW the modifications for idempotent re-execution [Menon et al. 2012 ] from the iGPU design, which supports timing speculation.  ... 
doi:10.1145/2764908 fatcat:utj6prgm2zcctlb36ikgejny2e

Microarchitectural Attacks in Heterogeneous Systems: A Survey

Hoda Naghibijouybari, Esmaeil Mohammadian Koruyeh, Nael Abu-Ghazaleh
2022 ACM Computing Surveys  
In this survey article, we consider the security of heterogeneous systems against microarchitectural attacks, with a focus on covert- and side-channel attacks, as well as fault injection attacks.  ...  We review works that have explored the vulnerability of the individual accelerators (such as Graphical Processing Units, GPUs and Field Programmable Gate Arrays, FPGAs) against these attacks, as well as  ...  The work is supported by the National Science Foundation under CNS-2053383, CNS-2130978, and CNS-1955650 grants.  ... 
doi:10.1145/3544102 fatcat:dm3l4etg5vealdqyodhuopjhgy

Chimera

Jason Jong Kyu Park, Yongjun Park, Scott Mahlke
2015 Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '15  
Preemptive multitasking on CPUs has been primarily supported through context switching. However, the same preemption strategy incurs substantial overhead due to the large context in GPUs.  ...  Chimera first introduces streaming multiprocessor (SM) flushing, which can instantly preempt an SM by detecting and exploiting idempotent execution.  ...  Khudia, Shruti Padmanabha, and Ankit Sethia for their valuable comments and feedbacks. This work is supported by the National Science Foundation under grants CNS-0964478 and CCF-1438996.  ... 
doi:10.1145/2694344.2694346 dblp:conf/asplos/ParkPM15 fatcat:kaqig6ktkjhfrjxgbaavpiy33i

GDM

Kaibo Wang, Xiaoning Ding, Rubao Lee, Shinpei Kato, Xiaodong Zhang
2014 Performance Evaluation Review  
Device memory is the primary onboard DRAM storage for the computation performed on GPU.  ...  Managing device memory space at application level becomes even more difficult when there are multiple applica-1 We use GPU and GPGPU interchangeably, with the latter emphasizing more on general-purpose  ...  Inc. and the anonymous reviewers for their help and feedback. This work was partially supported by the National Science Foundation under grants CCF-0913050, OCI-1147522, and CNS-1162165.  ... 
doi:10.1145/2637364.2592002 fatcat:zcpzph5qfzh3jczn7nsnj2iruy

Fine-grained containment domains for throughput processors [article]

Ikhwan Lee
2017
A similar approach has been proposed for GPUs to support exceptions as well as speculative execution [57] .  ...  Recent proposals on in-order processors [56] and GPUs [57] revisit the concept of idempotence to implement software-based fault recovery on processors without hardware speculation support.  ...  Chapter 5 Methodology In this chapter, we discuss the methodologies we use to evaluate the applicability of fine-grained containment domains to timing speculation on GPUs.  ... 
doi:10.15781/t2h41js69 fatcat:5usb4eurr5bcpnlzbnfynt2vnu

Accelerating Event Stream Processing in On- and Offline Systems

Michael Körber, Datenbanksysteme, Seeger, Bernhard (Prof. Dr.)
2022
While this naturally ensures unified query semantics for on- and offline processing, the costs for reading the entire stream from non-volatile storage quickly dominate the overall processing costs.  ...  Both modes are supported by widely used scale-out general-purpose stream processing engines (SPEs) like Apache Flink or Spark Streaming.  ...  However, without the help and support from my colleagues, family, and friends, this work would not have been possible. Acknowledgments viii  ... 
doi:10.17192/z2022.0078 fatcat:x64m6dluzjhhzi7mycwod7lkhq

Opportunistic acceleration of array-centric Python computation in heterogeneous environments

Dejice Jacob
2020
However, such managed program execution comes with a significant performance penalty arising from the interpreter having to decode and dispatch based on dynamic type checking.  ...  Parallel GPU kernels are customised to the runtime dependence graph, JIT compiled and executed. A systematic analysis of the execution speed of loop nests is performed using [...]  ...  Samadi et al [126] and Wang et al [156] use speculative kernel execution on GPUs and require post-execution correctness checking before committing the results.  ... 
doi:10.5525/gla.thesis.82011 fatcat:cokrisg5fncu7a2z4iubykf6lm

Software-hardware co-design for energy efficient datacenter computing

Tayler Hicklin Hetherington
2019
GNoM facilitates the design of MemcachedGPU, an end-to-end Memcached implementation on contemporary Ethernet and GPU hardware.  ...  GNoM highlights limitations in the traditional GPU programming model, which relies on a CPU for managing GPU tasks. Consequently, the CPU may be unnecessarily invol [...]  ...  [117] propose iGPU, a set of compiler, ISA, and hardware extensions that enable preemption support and speculative execution on GPUs. iGPU identifies and exploits sparse idempotent regions to minimize  ... 
doi:10.14288/1.0384819 fatcat:x2f5bfzndjhgdpcxlonwsj7uoe

Ανάπτυξη Συστοιχιών Υπολογιστών (Beowulf Clusters) με τη Χρήση Desktop Η/Υ, Graphics Processing Units (GPUs) και Ελεύθερου Λογισμικού για Παράλληλη Επεξεργασία (Parallel Computing) με Εφαρμογές στη Βιοϊατρική Τεχνολογία [article]

Alexandros Divolis, National Technological University Of Athens
2021
Intel Wide Dynamic Execution Πρόκειται για έναν συνδυασμό τεχνικών (data flow analysis, speculative execution, out-of- order execution και superscalar (=ανάλυση ροής δεδομένων, υποθετική εκτέλεση, εκτέλεση  ...  (IGPUs): χρησιμοποιούν ένα ποσοστό της RAM του συστήματος.  ... 
doi:10.26240/heal.ntua.21315 fatcat:7zl44e6xdbgs3idml7b3nj7u4q