2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) 2019
DOI: 10.1109/iccad45719.2019.8942122
|View full text |Cite
|
Sign up to set email alerts
|

FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA

Abstract: Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several stacked layers of dilated convolution that is used for sequence generation. While WaveNet produces state-of-the art audio generation results, the naive inference implementation is quite slow; it takes a few minutes to generate just one second of audio on a high-end GPU. In … Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
8
0

Year Published

2020
2020
2025
2025

Publication Types

Select...
6
4

Relationship

2
8

Authors

Journals

citations
Cited by 20 publications
(8 citation statements)
references
References 20 publications
0
8
0
Order By: Relevance
“…Additionally, the dimensionality reduction and restoring components in the feature analyzer are realized using MVMs with weight matrices , 2 R ;⇥A and , 2 R A ⇥; , respectively, where ; is the dimensionality of the input and A is the SVD rank. We devise an FPGA core for MVM and vector addition, realized using DSP blocks with Multiplication Accumulation (MAC) functionality [17,31]. Figure 8 presents the high-level schematic of CLEANN vector-matrix multiplication.…”
Section: Cleann Hardwarementioning
confidence: 99%
“…Additionally, the dimensionality reduction and restoring components in the feature analyzer are realized using MVMs with weight matrices , 2 R ;⇥A and , 2 R A ⇥; , respectively, where ; is the dimensionality of the input and A is the SVD rank. We devise an FPGA core for MVM and vector addition, realized using DSP blocks with Multiplication Accumulation (MAC) functionality [17,31]. Figure 8 presents the high-level schematic of CLEANN vector-matrix multiplication.…”
Section: Cleann Hardwarementioning
confidence: 99%
“…Additionally, the dimensionality reduction and restoring components in the feature analyzer are realized using MVMs with weight matrices W ∈ R l ×r and W ∈ R r ×l , respectively, where l is the dimensionality of the input and r is the SVD rank. We devise an FPGA core for MVM and vector addition, realized using DSP blocks with Multiplication Accumulation (MAC) functionality [17,31]. Figure 8 presents the high-level schematic of CLEANN vector-matrix multiplication.…”
Section: Cleann Hardwarementioning
confidence: 99%
“…As convolutional neural networks (CNN) finding their way more and more into a wide range of vision-based applications, there has been a significant focus on realizing low power custom hardware accelerators to attain their services on the edge/remote devices [ 1 , 2 , 3 , 4 ]. However, CNNs are computationally intensive, consuming vast amounts of dynamic power and computational resources [ 5 ].…”
Section: Introductionmentioning
confidence: 99%