• Publications
  • Influence
TimeGraph: GPU Scheduling for Real-Time Multi-Tasking Environments
TLDR
TimeGraph is presented, a real-time GPU scheduler at the device-driver level for protecting important GPU workloads from performance interference and supports two priority-based scheduling policies in order to address the tradeoff between response times and throughput introduced by the asynchronous and non-preemptive nature of GPU processing.
The International Exascale Software Project roadmap
TLDR
The work of the community to prepare for the challenges of exascale computing is described, ultimately combing their efforts in a coordinated International Exascale Software Project.
Gang EDF Scheduling of Parallel Task Systems
TLDR
An algorithm, called Gang EDF, which applies the Earliest Deadline First (EDF) policy to the traditional Gang scheduling scheme is presented and new ideas for the parallel task model are introduced.
Semi-partitioned Scheduling of Sporadic Task Systems on Multiprocessors
TLDR
A new algorithm for scheduling of sporadic task systems with arbitrary deadlines on identical multiprocessor platforms based on the concept of semi-partitioned scheduling, in which most tasks are fixed to specific processors, while a few tasks migrate across processors.
RGEM: A Responsive GPGPU Execution Model for Runtime Engines
TLDR
The experiments demonstrate that the response times of high-priority GPGPU tasks can be protected under RGEM, whereas their response times increase in an unbounded fashion without RGEM support, as the data sizes of competing workload increase.
Al-1/d: a distributed programming system with multi-model reflection framework
TLDR
The application of Multi-Model Re ection Framework to a distributed system is reported and the requirement of the network transparency, by which the user do not need to take the nature of the distributed environment into account, is reported.
Scalable Distributed Monte-Carlo Tree Search
TLDR
This work presents a massively parallel MCTS algorithm, that applies the TDS parallelism to the Upper Confidence bound Applied to Trees (UCT) algorithm, which is the most representative M CTS algorithm and introduces a reformulation of UCT called Depth-First UCT to drastically decrease communication overhead.
Resource Sharing in GPU-Accelerated Windowing Systems
TLDR
This paper proposes two protocols that enable application tasks to efficiently share the GPU resource in the X Window System and identifies and addresses resource-sharing problems raised in GPU-accelerated windowing systems.
Design and Evaluation of Precise Software Pacing Mechanisms for Fast Long-Distance Networks
TLDR
An IPGaware packet scheduling mechanism is proposed, in order to merge multiple streams which go through each of different bottleneck links, where the pacing ratios are appropriately maintained.
EZTrace: A Generic Framework for Performance Analysis
TLDR
Eztrace, a generic trace generation framework that aims at providing a simple way to analyze applications, is presented, based on plugins that allow it to trace different programming models such as MPI, pthread or OpenMP as well as user-defined libraries or applications.
...
1
2
3
4
5
...