Simultaneous Multikernel: Fine-Grained Sharing of GPUs
نویسندگان
چکیده
منابع مشابه
A Fine Grained Cycle Sharing System with Cooperative Multitasking on GPUs
The emergence of compute unified device architecture (CUDA), which has relieved application developers from having to understand complex graphics pipelines, has made the graphics processing unit (GPU) useful not only for graphics applications but also for general applications. In this paper, we present a cycle sharing system named GPU grid, which exploits idle GPU cycles to accelerate scientifi...
متن کاملFine-grained parallelization of lattice QCD kernel routine on GPUs
Simulation time for the classical problem of Lattice Quantum Chromodynamics (Lattice QCD) is dominated by one kernel routine responsible for computing the actions of a Dirac operator. This paper describes an experience in parallelizing this kernel routine. We explore parallelization granularities for this kernel routine on Graphical Processing Units (GPUs). We show that fine-grained parallelism...
متن کاملUltra-Fine Grained Dual-Phase Steels
This paper provides an overview on obtaining low-carbon ultra-fine grained dual-phase steels through rapid intercritical annealing of cold-rolled sheet as improved materials for automotive applications. A laboratory processing route was designed that involves cold-rolling of a tempered martensite structure followed by a second tempering step to produce a fine grained aggregate of ferrite and ca...
متن کاملFine-Grained Data Sharing Supporting Attribute Extension in Cloud Computing
Attribute-based encryption (ABE) can be used for implementing fine-grained data sharing in cloud computing. However, most of the existing ABE schemes cannot realize attribute extension and provable security simultaneously. In this paper, we propose a fine-grained attribute-based data sharing system based on a hybrid encryption mechanism. A rigorous security proof indicates that the proposed sch...
متن کاملSupporting Fine-Grained Synchronization on a Simultaneous Multithreading Processor
Existing multiprocessor synchronization mechanisms are relatively heavyweight, due in part to the level of the memory hierarchy (typically main memory) at which threads must synchronize. Multithreaded processors, on the other hand, have the potential to significantly reduce synchronization cost, because threads share the processor simultaneously and can synchronize using processor-internal stat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Computer Architecture Letters
سال: 2016
ISSN: 1556-6056
DOI: 10.1109/lca.2015.2477405