MachSuite: Benchmarks for accelerator design and customized architectures
Authors:
Top Cited Papers
- 1 October 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-119
Abstract
Recent high-level synthesis and accelerator-related architecture papers show a great disparity in workload selection. To improve standardization within the accelerator research community, we present MachSuite, a collection of 19 benchmarks for evaluating high-level synthesis tools and accelerator-centric architectures. MachSuite spans a broad application space, captures a variety of different program behaviors, and provides implementations tailored towards the needs of accelerator designers and researchers, including support for high-level synthesis. We illustrate these aspects by characterizing each benchmark along five different dimensions, highlighting trends and salient features.Keywords
This publication has 33 references indexed in Scilit:
- Triggered instructions2013
- A high-level synthesis flow for the implementation of iterative stencil loop algorithms on FPGA devices2013
- On learning-based methods for design-space exploration with high-level synthesis2013
- Building zynq® accelerators with Vivado® high level synthesis2013
- Neural Acceleration for General-Purpose Approximate Programs2012
- The accelerator storeACM Transactions on Architecture and Code Optimization, 2012
- Using Speculative Functional Units in high level synthesis2010
- Analysis of redundancy and application balance in the SPEC CPU2006 benchmark suite2007
- The cache performance and optimizations of blocked algorithms1991
- Fast Pattern Matching in StringsSIAM Journal on Computing, 1977