Search events for 'all'
Blockchain Abstract Data Type
Posters People: Emmanuelle Anceaume, Antonella Del Pozzo, Romaric Ludinard, Maria Potop-Butucaru, Sara Tucci-Piergiovanni
… This paper is the first to specify blockchains as a composition of abstract data types all together with a hierarchy of consistency criteria that formally characterizes the histories admissible for distributed programs that use them …
Semantics-Aware Scheduling Policies for Synchronization Determinism
Main Conference When: Tue 19 Feb 2019 14:00 - 14:25 People: Qi Zhao, Zhengyi Qiu, Guoliang Jin
… A common task for all deterministic multithreading (DMT) systems is to enforce synchronization determinism. However, synchronization determinism has not been …. Consequently, existing scheduling policies for synchronization determinism all have …
Incremental Flattening for Nested Data Parallelism
Main Conference When: Mon 18 Feb 2019 11:45 - 12:10 People: Troels Henriksen, Frederik Thorøe, Martin Elsman, Cosmin Oancea
… a multitude of code versions, which together cover all possible mappings … a single version, best suited for a specific dataset or on average for all datasets …
GPOP: A cache and memory-efficient framework for Graph Processing Over Partitions
Posters People: Kartik Lakhotia, Rajgopal Kannan, Sourav Pati, Viktor Prasanna
… over-all performance and scalability.
In this paper, we generalize a recent …
GOPipe: A Granularity-Oblivious Programming Framework for Pipelined Stencil Executions on GPU
Posters People: Chanyoung Oh, Zhen ZHENG, Xipeng Shen, Jidong Zhai, Youngmin Yi
… all inter-task and inter-stage data dependencies. In our experiments on four …
GPU-based 3D Cryo-EM Reconstruction with Key-Value Streams
Posters People: Kunpeng Wang, Shizhen Xu, Hongkun Yu, Haohuan Fu, Guangwen Yang
… and accumulate the contribution to the final 3D model from all different 2D image inputs …
LOFT: Lock-Free Transactional Data Structures
Posters People: Avner Elizarov, Guy Gueta, Erez Petrank
… manager reorders the conflicting transactions execution allowing all transactions …
Proactive Work Stealing for Futures
Main Conference When: Tue 19 Feb 2019 14:25 - 14:50 People: Kyle Singer, Yifan Xu, I-Ting Angelina Lee
… ,'' a metric for evaluating the performance of parallel executions. All prior works …)$ and is smaller than $k$, which holds true for all the benchmarks we examined. …
Encapsulated Open Nesting for STM: Fine-Grained Higher-Level Conflict Detection
Main Conference When: Wed 20 Feb 2019 09:35 - 10:00 People: Martin Bättig, Thomas Gross
… memory location using different conflict detection schemes unless all accesses …
A Round-Efficient Distributed Betweenness Centrality Algorithm
Main Conference When: Tue 19 Feb 2019 14:50 - 15:15 People: Loc Hoang, Matteo Pontecorvi, Roshan Dathathri, Gurbinder Gill, Bozhi You, Keshav Pingali, Vijaya Ramachandran
… We present Min-Rounds BC (MRBC), a distributed-memory algorithm in the CONGEST model that computes the betweenness centrality (BC) of every vertex in a directed unweighted n-node graph in O (n) rounds. Min-Rounds BC also computes all-pairs …
Throughput-Oriented GPU Memory Allocation
Main Conference When: Mon 18 Feb 2019 10:55 - 11:20 People: Isaac Gelado, Michael Garland
… efficiency.
Using all these techniques, our throughput-oriented memory allocator …
Managing Application Parallelism via Parallel Efficiency Regulation
Posters People: Sharanyan Srikanthan, Princeton Ferro, Sandhya Dwarkadas, Sayak Chakraborti
… Regulation. MAPPER monitors and coordinates all participating applications …
Efficient Race Detection with Futures
Main Conference When: Wed 20 Feb 2019 10:25 - 10:50 People: Robert Utterback, Kunal Agrawal, Jeremy Fineman, I-Ting Angelina Lee
… growing function (upper bounded by $4$ for all practical purposes), it can be treated …
Checking Linearizability Using Hitting Families
Main Conference When: Wed 20 Feb 2019 11:45 - 12:10 People: Burcu Kulahcioglu Ozkan, Rupak Majumdar, Filip Niksic
… } of schedules, which is guaranteed to cover all linearizability witnesses of depth …
Tutorial: Implementing Parallel and Concurrent Tree Structures
Workshops and Tutorials When: Sat 16 Feb 2019 13:00 - 17:00 People: Yihan Sun, Guy Blelloch
… trees, which bases all tree algorithms on a single primitive Join. This framework …, weight-balance trees, and treaps, and all algorithms except Join are generic … is lock-free and all algorithms on trees are work-efficient with poly-logarithmic …
A Coordinated Tiling and Batching Framework for Efficient GEMM on GPUs
Main Conference When: Tue 19 Feb 2019 12:10 - 12:35 People: Xiuhong Li, Eric Liang, Shengen Yan, Jia Liancheng, Yinghan Li
… by designing a single CUDA kernel for all of these GEMMs.
However, the current …