What is he best known for?
The fields of study he is best known for:
- Operating system
- Central processing unit
- Parallel computing
The scientist’s investigation covers issues in Parallel computing, Field-programmable gate array, Embedded system, Computer architecture and Page cache.
His work often combines Parallel computing and Efficient energy use studies.
His work deals with themes such as Design space exploration, Convolutional neural network and Speedup, which intersect with Field-programmable gate array.
Yun Liang combines subjects such as Artificial intelligence and FLOPS with his study of Embedded system.
His Page cache research incorporates themes from Cache pollution and Cache-oblivious algorithm, Bus sniffing, Cache coloring.
The study incorporates disciplines such as Smart Cache and Cache invalidation in addition to Cache pollution.
His most cited work include:
- Automated Systolic Array Architecture Synthesis for High Throughput CNN Inference on FPGAs (197 citations)
- Chronos: A timing analyzer for embedded software (173 citations)
- Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs (131 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Parallel computing, Field-programmable gate array, Speedup, Cache and Embedded system.
His Parallel computing study integrates concerns from other disciplines, such as Scalability and Thread.
His research in Field-programmable gate array intersects with topics in Computer architecture, Design space exploration and Convolutional neural network.
In his research on the topic of Speedup, Computer hardware and Artificial neural network is strongly related with Overhead.
He has researched Cache in several fields, including Real-time computing, High memory and Task.
His Embedded system study combines topics from a wide range of disciplines, such as Software and Programming paradigm.
He most often published in these fields:
- Parallel computing (57.02%)
- Field-programmable gate array (37.72%)
- Speedup (26.32%)
What were the highlights of his more recent work (between 2017-2021)?
- Field-programmable gate array (37.72%)
- Parallel computing (57.02%)
- Speedup (26.32%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Field-programmable gate array, Parallel computing, Speedup, Efficient energy use and Computation.
The Field-programmable gate array study combines topics in areas such as Design space exploration, Convolutional neural network, Computer engineering and Dataflow.
The concepts of his Convolutional neural network study are interwoven with issues in Convolution and Pipeline.
His CUDA study in the realm of Parallel computing connects with subjects such as Throughput.
The various areas that Yun Liang examines in his Speedup study include Thread, Overhead, Memory hierarchy, Deep learning and General-purpose computing on graphics processing units.
His Computation research integrates issues from Fast Fourier transform, Data transmission and Computer architecture.
Between 2017 and 2021, his most popular works were:
- C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs (108 citations)
- SpWA: an efficient sparse winograd convolutional neural networks accelerator on FPGAs (44 citations)
- TGPA: tile-grained pipeline architecture for low latency CNN inference (29 citations)
In his most recent research, the most cited papers focused on:
- Operating system
- Central processing unit
- Parallel computing
His primary scientific interests are in Field-programmable gate array, Parallel computing, Speedup, Convolutional neural network and Hardware acceleration.
His Field-programmable gate array research is within the category of Computer hardware.
His work in the fields of Parallel computing, such as Xeon, intersects with other areas such as Sparse matrix.
His Speedup research is multidisciplinary, incorporating perspectives in Image, CUDA, Heuristic and General-purpose computing on graphics processing units.
Yun Liang focuses mostly in the field of Convolutional neural network, narrowing it down to matters related to Pipeline and, in some cases, Residual neural network and Algorithm.
His Hardware acceleration research is multidisciplinary, relying on both Operand and Design space exploration.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
