اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدEdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference
87
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to resource-constrained edge platforms with strict latency requirements. We present EdgeBERT, an in-depth algorithm-hardware co-design for latency-aware energy optimization for multi-task NLP. EdgeBERT employs entropy-based early exit predication in order to perform dynamic voltage-frequency scaling (DVFS), at a sentence granularity, for minimal energy consumption while adhering to a prescribed target latency. Computation and memory footprint overheads are further alleviated by employing a calibrated combination of adaptive attention span, selective network pruning, and floating-point quantization. Furthermore, in order to maximize the synergistic benefits of these algorithms in always-on and intermediate edge computing settings, we specialize a 12nm scalable hardware accelerator system, integrating a fast-switching low-dropout voltage regulator (LDO), an all-digital phase-locked loop (ADPLL), as well as, high-density embedded non-volatile memories (eNVMs) wherein the sparse floating-point bit encodings of the shared multi-task parameters are carefully stored. Altogether, latency-aware multi-task NLP inference acceleration on the EdgeBERT hardware system generates up to 7x, 2.5x, and 53x lower energy compared to the conventional inference without early stopping, the latency-unbounded early exit approach, and CUDA adaptations on an Nvidia Jetson Tegra X2 mobile GPU, respectively.
قيم البحث
اقرأ أيضاً
Deep neural networks have become the standard approach to building reliable Natural Language Processing (NLP) applications, ranging from Neural Machine Translation (NMT) to dialogue systems. However, improving accuracy by increasing the model size re
quires a large number of hardware computations, which can slow down NLP applications significantly at inference time. To address this issue, we propose a novel vector-vector-matrix architecture (VVMA), which greatly reduces the latency at inference time for NMT. This architecture takes advantage of specialized hardware that has low-latency vector-vector operations and higher-latency vector-matrix operations. It also reduces the number of parameters and FLOPs for virtually all models that rely on efficient matrix multipliers without significantly impacting accuracy. We present empirical results suggesting that our framework can reduce the latency of sequence-to-sequence and Transformer models used for NMT by a factor of four. Finally, we show evidence suggesting that our VVMA extends to other domains, and we discuss novel hardware for its efficient use.
Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible re
sponses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentence-tree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2Tree framework outperforms baseline methods over 11.15% increase of acceptance ratio.
There is a small but growing body of research on statistical scripts, models of event sequences that allow probabilistic inference of implicit events from documents. These systems operate on structured verb-argument events produced by an NLP pipeline
. We compare these systems with recent Recurrent Neural Net models that directly operate on raw tokens to predict sentences, finding the latter to be roughly comparable to the former in terms of predicting missing events in documents.
This paper presents the results of the RepEval 2017 Shared Task, which evaluated neural network sentence representation learning models on the Multi-Genre Natural Language Inference corpus (MultiNLI) recently introduced by Williams et al. (2017). All
of the five participating teams beat the bidirectional LSTM (BiLSTM) and continuous bag of words baselines reported in Williams et al.. The best single model used stacked BiLSTMs with residual connections to extract sentence features and reached 74.5% accuracy on the genre-matched test set. Surprisingly, the results of the competition were fairly consistent across the genre-matched and genre-mismatched test sets, and across subsets of the test data representing a variety of linguistic phenomena, suggesting that all of the submitted systems learned reasonably domain-independent representations for sentence meaning.
Despite the superb performance of State-Of-The-Art (SOTA) DNNs, the increasing computational cost makes them very challenging to meet real-time latency and accuracy requirements. Although DNN runtime latency is dictated by model property (e.g., archi
tecture, operations), hardware property (e.g., utilization, throughput), and more importantly, the effective mapping between these two, many existing approaches focus only on optimizing model property such as FLOPS reduction and overlook the mismatch between DNN model and hardware properties. In this work, we show that the mismatch between the varied DNN computation workloads and GPU capacity can cause the idle GPU tail effect, leading to GPU under-utilization and low throughput. As a result, the FLOPs reduction cannot bring effective latency reduction, which causes sub-optimal accuracy versus latency trade-offs. Motivated by this, we propose a GPU runtime-aware DNN optimization methodology to eliminate such GPU tail effect adaptively on GPU platforms. Our methodology can be applied on top of existing SOTA DNN optimization approaches to achieve better latency and accuracy trade-offs. Experiments show 11%-27% latency reduction and 2.5%-4.0% accuracy improvement over several SOTA DNN pruning and NAS methods, respectively
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
