Search Results for author:
Found 25 papers, 8 papers with code
Data-Driven Offline Optimization For Architecting Hardware Accelerators
An alternative paradigm is to use a "data-driven", offline approach that utilizes logged simulation data, to architect hardware accelerators, without needing any form of simulations.
An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
Then, we extensively evaluate three classes of Edge TPUs, covering different computing ecosystems, that are either currently deployed in Google products or are the product pipeline, across 423K unique convolutional neural networks.
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
JaxPruner: A concise library for sparsity research
This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research.
Learning Performance-Improving Code Edits
Next, we propose a broad range of adaptation strategies for code optimization; for prompting, these include retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation
In this paper, we introduce GRANITE, a new machine learning model that estimates the throughput of basic blocks across different microarchitectures.
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
In this work, we study the effectiveness of existing sparse training recipes at \textit{high-sparsity regions} and argue that these methods fail to sustain the model quality on par with low-sparsity regions.
GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
Even though there is a convolution stage in this operator, the inserted zeros lead to underutilization of the compute resources when a conventional convolution accelerator is employed.
ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
We show how ReLeQ can balance speed and quality, and provide an asymmetric general solution for quantization of a large variety of deep networks (AlexNet, CIFAR-10, LeNet, MobileNet-V1, ResNet-20, SVHN, and VGG-11) that virtually preserves the accuracy (=< 0. 3% loss) while minimizing the computation and storage cost.
Mixed-Signal Charge-Domain Acceleration of Deep Neural networks through Interleaved Bit-Partitioned Arithmetic
Low-power potential of mixed-signal design makes it an alluring option to accelerate Deep Neural Networks (DNNs).
Hardware Architecture
TPO: TREE SEARCH POLICY OPTIMIZATION FOR CONTINUOUS ACTION SPACES
In our experiments, we use PPO as our baseline policy optimization algorithm.
Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
This solution dubbed Chameleon leverages reinforcement learning whose solution takes fewer steps to converge, and develops an adaptive sampling algorithm that not only focuses on the costly samples (real hardware measurements) on representative points but also uses a domain-knowledge inspired logic to improve the samples itself.
NAHAS: Neural Architecture and Hardware Accelerator Search
In this paper, we study the importance of co-designing neural architectures and hardware accelerators.
Apollo: Transferable Architecture Exploration
We further show that by transferring knowledge between target architectures with different design constraints, Apollo is able to find optimal configurations faster and often with better objective value (up to 25% improvements).
Rethinking Co-design of Neural Architectures and Hardware Accelerators
In our work, we target the optimization of hardware and software configurations on an industry-standard edge accelerator.
FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks
In contrast, FLAT unblocks transformer models for inputs with up to 64K elements
Policy Optimization by Local Improvement through Search
On the other end of the spectrum, approaches rooted in Policy Iteration, such as Dual Policy Iteration do not choose next step actions based on an expert, but instead use planning or search over the policy to choose an action distribution to train towards.
Accelerating Attention through Gradient-Based Learned Runtime Pruning
To best utilize this mathematical innovation, we devise a bit-serial architecture, dubbed LeOPArd, for transformer language models with bit-level early termination microarchitectural mechanism.
Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation
The combined in-memory pruning and on-chip recompute of the relevant attention scores enables SPRINT to transform quadratic complexity to a merely linear one.
Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango
Our empirical and qualitative analysis reveals that a symbiotic relationship between text and patterns explains the success of few-shot prompting: text helps extract commonsense from the question to help patterns, and patterns enforce task understanding and direct text generation.
Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask
In this work, we focus on N:M sparsity and extensively study and evaluate various training recipes for N:M sparsity in terms of the trade-off between model accuracy and compute cost (FLOPs).
STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
Recent innovations on hardware (e. g. Nvidia A100) have motivated learning N:M structured sparsity masks from scratch for fast model inference.
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
We conducted extensive experiments with a 2-billion parameter USM on a large-scale voice search dataset to evaluate our proposed method.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics
Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots.
Tao: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements.
