FAWN: a fast array of wimpy nodes
- D. Andersen, Jason Franklin, M. Kaminsky, Amar Phanishayee, Lawrence Tan, V. Vasudevan
- Computer ScienceSymposium on Operating Systems Principles
- 11 October 2009
The key contributions of this paper are the principles of the FAWN architecture and the design and implementation of FAWN-KV--a consistent, replicated, highly available, and high-performance key-value storage system built on a FAWN prototype.
FAWNdamentally Power-efficient Clusters
- V. Vasudevan, Jason Franklin, Iulian Moraru
- Computer ScienceUSENIX Workshop on Hot Topics in Operating…
- 18 May 2009
Long-lasting, fundamental trends in the scaling of computation and energy suggest that the FAWN approach will become dominant for increasing classes of workloads, and this work proposes a cluster architecture called a Fast Array of Wimpy Nodes, or FAWN, for data-intensive computing.
Energy-efficient cluster computing with FAWN: workloads and implications
- V. Vasudevan, D. Andersen, M. Kaminsky, Lawrence Tan, Jason Franklin, Iulian Moraru
- Computer ScienceEnergy-Efficient Computing and Networking
- 13 April 2010
The architecture and motivation for a cluster-based, many-core computing architecture for energy-efficient, data-intensive computing, and the longer-term implications of FAWN lead us to select a tightly integrated stacked chip-and-memory architecture for future FAWN development are presented.
Challenges and opportunities for efficient computing with FAWN
- V. Vasudevan, D. Andersen, Lawrence Tan
- Computer ScienceOPSR
- 18 February 2011
The architecture and motivation for a clusterbased, many-core computing architecture for energy-efficient, dataintensive computing, and the longer-term implications of FAWN lead us to select a tightly integrated stacked chip and-memory architecture for future FAWN development are presented.
A Fast Array of Wimpy Nodes
- D. Andersen, Jason Franklin, Amar Phanishayee, Lawrence Tan, V. Vasudevan
- Computer Science
- 2008
It is suggested that FAWN can be a practical approach to building large-scale storage for seek-intensive workloads and that a FAWN cluster is cost-competitive with other approaches to providing high query rates, while consuming 3-10x less power.
FAWNSort : Energy-efficient Sorting of 10 GB
- V. Vasudevan, Lawrence Tan, M. Kaminsky, M. Kozuch, D. Andersen, P. Pillai
- Computer Science
- 2010
This system consists of a machine with a low-power server processor and five flash drives, sorting the 10GB dataset in 21.2 seconds (±0.227s) seconds with an average power of 104.9W, providing 44884 sorted records per Joule.
FAWN
- D. Andersen, Jason Franklin, M. Kaminsky, Amar Phanishayee, Lawrence Tan, V. Vasudevan
- Computer Science
- 1 July 2011
The design centers around purely log-structured datastores that provide the basis for high performance on flash storage, as well as for replication and consistency obtained using chain replication on a consistent hashing ring.
FAWN: A Fast Array of Wimpy Nodes (CMU-PDL-08-108)
- D. Andersen, Jason Franklin, Amar Phanishayee, Lawrence Tan, V. Vasudevan
- Computer Science
- 2008
Evaluation of a small-scale FAWN cluster and several candidate FAWN node systems suggest that FAWN can be a practical approach to building large-scale storage for seek-intensive workloads and indicates that aFAWN cluster is cost-competitive with other approaches to providing high query rates, while consuming 3-10x less power.
A Low-Power Hybrid CPU-GPU Sort
- Lawrence Tan
- Computer Science
- 2014
A balanced architecture with sufficient I/O to saturate available compute capacity is significantly more energy efficient compared to traditional machines and the CPU-GPU hybrid sort is marginally more efficient than a CPU-only sort.