Proceedings of the 20th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems 2019
DOI: 10.1145/3316482.3326355
|View full text |Cite
|
Sign up to set email alerts
|

BitBench: a benchmark for bitstream computing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
3
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(5 citation statements)
references
References 47 publications
0
5
0
Order By: Relevance
“…To illustrate the benefits of bitstream computing, we use BitSAD to generate Verilog for several kernels from the BitBench suite [7]. Floating point (FP) and fixed point (FXP) baselines are created using Vivado High-Level Synthesis (HLS).…”
Section: Hardware Resultsmentioning
confidence: 99%
See 3 more Smart Citations
“…To illustrate the benefits of bitstream computing, we use BitSAD to generate Verilog for several kernels from the BitBench suite [7]. Floating point (FP) and fixed point (FXP) baselines are created using Vivado High-Level Synthesis (HLS).…”
Section: Hardware Resultsmentioning
confidence: 99%
“…Stochastic bitstreams are generated using an LFSR, but we do not include these in the hardware costs. As mentioned in the benchmark [7], these kernels are meant to be end-to-end stochastic circuits, so the LFSRs would not exist in real systems, and they are only a side-effect of our testing environment. The SVF, BQ, and MA filters are deterministic bitstream designs, and they are evaluated on one second of audio data [15].…”
Section: Hardware Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…In our current implementation, the binary frames are treated as real numbers (e.g., when warping them during the merging stage). One potential way to improve the efficiency is to utilize specialized computing architectures and algorithms for binary data [Daruwalla et al 2019;Pfeiffer and Pfeil 2018].…”
Section: Limitations and Discussionmentioning
confidence: 99%