Export Citations
2018 Proceeding
Artificial Intelligence (AI), Machine Learning (ML) and other emerging workloads demand efficient computer systems from the cloud to the edge. Systems designers, however, face numerous challenges from tackling the ever-growing space of design and optimization choices (including algorithms, models, software frameworks, libraries, hardware platforms, optimization techniques) to balancing off multiple objectives (including accuracy, speed, throughput, power, size, price). Furthermore, the lack of a common experimental framework and methodology makes it even more challenging to keep up with and build upon the latest research advances.
The Reproducibly Quality-Efficient Systems Tournaments () initiative is a community effort to develop a rigorous methodology, open platform and for co-designing the efficient and reliable software/hardware stack for emerging workloads. ReQuEST invites a multidisciplinary community to collaborate on benchmarking and optimizing workloads across diverse platforms, models, data sets, libraries and tools, while gradually adopting best practice. The community effectively creates a "marketplace" for trading Pareto-efficient implementations (code and data) as portable, customizable and reusable and . We envision that such a community-driven and decentralized marketplace will help accelerate adoption and technology transfer of novel AI/ML techniques similar to the open-source movement.
Please see the front matter for the 1st ReQuEST tournament on Co-designing Pareto-efficient Deep Learning Inference at ASPLOS'18 to learn more about the shared workflows and validated results, as well as about our next steps for the ReQuEST initiative.
Proceeding Downloads
Keynote
Reducing power consumption has been one of the most important goals since the creation of electronic systems. Energy efficiency is increasingly important as battery-powered systems (such as smartphones, drones, and body cameras) are widely used. It is ...
Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe
- Jiong Gong,
- Haihao Shen,
- Guoming Zhang,
- Xiaoli Liu,
- Shane Li,
- Ge Jin,
- Niharika Maheshwari,
- Evarist Fomenko,
- Eden Segal
High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel(R) optimized deep learning framework ...
Optimizing Deep Learning Workloads on ARM GPU with TVM
With the great success of deep learning, the demand for deploying deep neural networks to mobile devices is growing rapidly. However, current popular deep learning frameworks are often poorly optimized for mobile devices, especially mobile GPU. In this ...
Real-Time Image Recognition Using Collaborative IoT Devices
Internet of things (IoT) devices capture and create various forms of sensor data such as images and videos. However, such resource-constrained devices lack the capability to efficiently process data in a timely and real-time manner. Therefore, IoT ...
Leveraging the VTA-TVM Hardware-Software Stack for FPGA Acceleration of 8-bit ResNet-18 Inference
We present a full-stack design to accelerate deep learning inference with FPGAs. Our contribution is two-fold. At the software layer, we leverage and extend TVM, the end-to-end deep learning optimizing compiler, in order to harness FPGA-based ...
Multi-objective autotuning of MobileNets across the full software/hardware stack
We present a customizable Collective Knowledge workflow to study the execution time vs. accuracy trade-offs for the MobileNets CNN family. We use this workflow to evaluate MobileNets on Arm Cortex CPUs using TensorFlow and Arm Mali GPUs using several ...
PANEL: Open panel and discussion on tackling complexity, reproducibility and tech transfer challenges in a rapidly evolving AI/ML/systems research
Discussion is centered around the following questions:
* How do we facilitate tech transfer between academia and industry in a quickly evolving research landscape?
* How do we incentivize companies and academic researchers to release more artifacts and ...
Index Terms
- Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning
Recommendations
On envy-free pareto efficient pricing
FAW-AAIM'12: Proceedings of the 6th international Frontiers in Algorithmics, and Proceedings of the 8th international conference on Algorithmic Aspects in Information and ManagementIn a centralized combinatorial market, the market maker has a number of items for sale to potential consumers, who wish to purchase their preferred items. Different solution concepts (allocations of items to players) capture different perspectives in ...
Comparison of the voluntary contribution and Pareto-efficient mechanisms under voluntary participation
AbstractWe compare the voluntary contribution mechanism with any mechanism attaining Pareto-efficient allocations when each agent can choose whether he/she participates in the mechanism for the provision of a non-excludable public good. We find that, in ...