Cloud computing landscape and research challenges regarding trust and reputation
Cloud Computing is an emerging computing paradigm. It shares massively scalable, elastic
resources (eg, data, calculations, and services) transparently among the users over a …
resources (eg, data, calculations, and services) transparently among the users over a …
Energy efficient architecture for graph analytics accelerators
Specialized hardware accelerators can significantly improve the performance and power
efficiency of compute systems. In this paper, we focus on hardware accelerators for graph …
efficiency of compute systems. In this paper, we focus on hardware accelerators for graph …
[图书][B] General-purpose graphics processor architectures
Originally developed to support video games, graphics processor units (GPUs) are now
increasingly used for general-purpose (non-graphics) applications ranging from machine …
increasingly used for general-purpose (non-graphics) applications ranging from machine …
Efficient GPU synchronization without scopes: Saying no to complex consistency models
As GPUs have become increasingly general purpose, applications with more general
sharing patterns and fine-grained synchronization have started to emerge. Unfortunately …
sharing patterns and fine-grained synchronization have started to emerge. Unfortunately …
Parallel graph analytics
A Lenharth, D Nguyen, K Pingali - Communications of the ACM, 2016 - dl.acm.org
Parallel graph analytics Page 1 78 COMMUNICATIONS OF THE ACM | MAY 2016 | VOL. 59 |
NO. 5 contributed articles DOI:10.1145/2901919 Data-centric abstractions and execution …
NO. 5 contributed articles DOI:10.1145/2901919 Data-centric abstractions and execution …
Spandex: A flexible interface for efficient heterogeneous coherence
Recent heterogeneous architectures have trended toward tighter integration and shared
memory largely due to the efficient communication and programmability enabled by this …
memory largely due to the efficient communication and programmability enabled by this …
Minnow: Lightweight offload engines for worklist management and worklist-directed prefetching
The importance of irregular applications such as graph analytics is rapidly growing with the
rise of Big Data. However, parallel graph workloads tend to perform poorly on general …
rise of Big Data. However, parallel graph workloads tend to perform poorly on general …
Hmg: Extending cache coherence protocols across modern hierarchical multi-gpu systems
Prior work on GPU cache coherence has shown that simple hardware-or software-based
protocols can be more than sufficient. However, in recent years, features such as multi-chip …
protocols can be more than sufficient. However, in recent years, features such as multi-chip …
Laperm: Locality aware scheduler for dynamic parallelism on gpus
Recent developments in GPU execution models and architectures have introduced dynamic
parallelism to facilitate the execution of irregular applications where control flow and …
parallelism to facilitate the execution of irregular applications where control flow and …
Free launch: optimizing GPU dynamic kernel launches through thread reuse
G Chen, X Shen - Proceedings of the 48th International Symposium on …, 2015 - dl.acm.org
Supporting dynamic parallelism is important for GPU to benefit a broad range of
applications. There are currently two fundamental ways for programs to exploit dynamic …
applications. There are currently two fundamental ways for programs to exploit dynamic …