Back to Search
Start Over
TASO: Time and Space Optimization for Memory-Constrained DNN Inference
- Source :
- SBAC-PAD
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- Convolutional neural networks (CNNs) are used in many embedded applications, from industrial robotics and automation systems to biometric identification on mobile devices. State-of-the-art classification is typically achieved by large networks, which are prohibitively expensive to run on mobile and embedded devices with tightly constrained memory and energy budgets. We propose an approach for ahead-of-time domain specific optimization of CNN models, based on an integer linear programming (ILP) for selecting primitive operations to implement convolutional layers. We optimize the trade-off between execution time and memory consumption by: 1) attempting to minimize execution time across the whole network by selecting data layouts and primitive operations to implement each layer; and 2) allocating an appropriate workspace that reflects the upper bound of memory footprint per layer. These two optimization strategies can be used to run any CNN on any platform with a C compiler. Our evaluation with a range of popular ImageNet neural architectures (GoogleNet, AlexNet, VGG, ResNet and SqueezeNet) on the ARM Cortex-A15 yields speedups of 8x compared to a greedy algorithm based primitive selection, reduces memory requirement by 2.2x while sacrificing only 15% of inference time compared to a solver that considers inference time only. In addition, our optimization approach exposes a range of optimal points for different configurations across the Pareto frontier of memory and latency trade-off, which can be used under arbitrary system constraints.
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
business.industry
05 social sciences
Inference
Machine Learning (stat.ML)
020206 networking & telecommunications
02 engineering and technology
Parallel computing
Solver
computer.software_genre
Convolutional neural network
Automation
050105 experimental psychology
Machine Learning (cs.LG)
Statistics - Machine Learning
0202 electrical engineering, electronic engineering, information engineering
Memory footprint
0501 psychology and cognitive sciences
Compiler
business
Greedy algorithm
computer
Integer programming
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2020 IEEE 32nd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)
- Accession number :
- edsair.doi.dedup.....4ae833b1b410fa923d50b9d8577074f3
- Full Text :
- https://doi.org/10.1109/sbac-pad49847.2020.00036