International Symposium on Microarchitecture
9 papers1 directions
The International Symposium on Microarchitecture is a research venue focused on the design and implementation of computer microarchitectures. While its scope encompasses general computer architecture, it serves as a location for research at the intersection of hardware design and artificial intelligence. The venue publishes work related to the development of hardware for machine learning workloads, including deep learning accelerators and neuromorphic computing systems.
Research presented at this venue often addresses the efficiency and optimization of neural network execution. Specific topics include dataflow analysis for deep learning accelerators, as seen in the MAESTRO infrastructure, and the optimization of Long Short-Term Memory (LSTM) networks on graphics processing units. Other contributions explore hardware-software co-design under neuromorphic constraints and memory system designs tailored for image processing and computer vision tasks. Prolific contributors to this field at the venue include researchers such as Hyoukjun Kwon, Mayank Parasar, and Stephen W. Keckler.
Beyond machine learning, the venue covers broader architectural topics such as network topology, computer security through functional programming architectures, and power management policies for mobile users. The corpus of work from 1988 to 2018 demonstrates a transition toward addressing the computational demands of modern AI, balancing hardware constraints with the requirements of complex neural models.
Papers by Year
| 2018 | 4 |
| 2016 | 3 |
| 1993 | 1 |
| 1988 | 1 |
Top Research Directions
Research directions most represented by papers from this venue.
| Inter-Layer Error Compensation in Neural Network Quantization | 1 |
Top Authors
| Author | Papers |
|---|---|
| Peng Qu | 1 |
| Xin Fu | 1 |
Impactful Papers
Papers from this venue that shaped research clusters.
Foundational
NEUTRAMS: neural network transformation and co-design under neuromorphic hardware constraints
foundational
Inter-Layer Error Compensation in Neural
2016