Search Results for author:
Found 13 papers, 6 papers with code
Machine Learning in Compiler Optimisation
In the last decade, machine learning based compilation has moved from an an obscure research niche to a mainstream activity.
Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are extremely computationally demanding, presenting a large barrier to their deployment on resource-constrained devices.
A Closer Look at Structured Pruning for Neural Network Compression
Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network.
Pruning neural networks: is it time to nip it in the bud?
First, when time-constrained, it is better to train a simple, smaller network from scratch than prune a large network.
Distilling with Performance Enhanced Students
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size.
BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
The desire to map neural networks to varying-capacity devices has led to the development of a wealth of compression techniques, many of which involve replacing standard convolutional blocks in a large network with cheap alternative blocks.
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task.
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs
We evaluate higher level libraries, which analyze the input characteristics of a convolutional layer, based on which they produce optimized OpenCL (Arm Compute Library and TVM) and CUDA (cuDNN) code.
Optimizing Grouped Convolutions on Edge Devices
We observe that our new implementation scales well with the number of groups and provides the best inference times in all settings, improving the existing implementations of grouped convolutions in TVM, PyTorch and TensorFlow Lite by 3. 4x, 8x and 4x on average respectively.
M3: Semantic API Migrations
Our approach is integrated with standard compiler tooling, and we use this integration to evaluate migration opportunities in 9 existing C/C++ applications with over 1MLoC.
Software Engineering
Deep Data Flow Analysis
Compiler architects increasingly look to machine learning when building heuristics for compiler optimization.
Neural Architecture Search as Program Transformation Exploration
This unification allows us to express existing NAS operations as combinations of simpler transformations.
DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack
Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices.
