LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching

As Large Language Models (LLMs) broaden their capabilities to manage thousands of API calls, they are confronted with complex data operations across vast datasets with significant overhead to the underlying system. In this work, we introduce LLM-dCache to optimize data accesses by treating cache operations as callable API functions exposed to the tool-augmented agent. We grant LLMs the autonomy to manage cache decisions via prompting, seamlessly integrating with existing function-calling mechanisms. Tested on an industry-scale massively parallel platform that spans hundreds of GPT endpoints and terabytes of imagery, our method improves Copilot times by an average of 1.24x across various LLMs and prompting techniques.

Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for running sophisticated DNN-based services on resource constrained embedded devices. In this paper, we target energy-efficient inference on embedded DNN accelerators. To that end, we propose an automated framework to compress DNNs in a hardware-aware manner by jointly employing pruning and quantization. We explore, for the first time, per-layer fine- and coarse-grained pruning, in the same DNN architecture, in addition to low bit-width mixed-precision quantization for weights and activations. Reinforcement Learning (RL) is used to explore the associated design space and identify the pruning-quantization configuration so that the energy consumption is minimized whilst the prediction accuracy loss is retained at acceptable levels. Using our novel composite RL agent we are able to extract energy-efficient solutions without requiring retraining and/or fine tuning. Our extensive experimental evaluation over widely used DNNs and the CIFAR-10/100 and ImageNet datasets demonstrates that our framework achieves $39\%$ average energy reduction for $1.7\%$ average accuracy loss and outperforms significantly the state-of-the-art approaches.

OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload

Modern Deep Neural Networks (DNNs) exhibit profound efficiency and accuracy properties. This has introduced application workloads that comprise of multiple DNN applications, raising new challenges regarding workload distribution. Equipped with a diverse set of accelerators, newer embedded system present architectural heterogeneity, which current run-time controllers are unable to fully utilize. To enable high throughput in multi-DNN workloads, such a controller is ought to explore hundreds of thousands of possible solutions to exploit the underlying heterogeneity. In this paper, we propose OmniBoost, a lightweight and extensible multi-DNN manager for heterogeneous embedded devices. We leverage stochastic space exploration and we combine it with a highly accurate performance estimator to observe a x4.6 average throughput boost compared to other state-of-the-art methods. The evaluation was performed on the HiKey970 development board.

Energy-efficient DNN Inference on Approximate Accelerators Through Formal Property Exploration

Deep Neural Networks (DNNs) are being heavily utilized in modern applications and are putting energy-constraint devices to the test. To bypass high energy consumption issues, approximate computing has been employed in DNN accelerators to balance out the accuracy-energy reduction trade-off. However, the approximation-induced accuracy loss can be very high and drastically degrade the performance of the DNN. Therefore, there is a need for a fine-grain mechanism that would assign specific DNN operations to approximation in order to maintain acceptable DNN accuracy, while also achieving low energy consumption. In this paper, we present an automated framework for weight-to-approximation mapping enabling formal property exploration for approximate DNN accelerators. At the MAC unit level, our experimental evaluation surpassed already energy-efficient mappings by more than $\times2$ in terms of energy gains, while also supporting significantly more fine-grain control over the introduced approximation.

Positive/Negative Approximate Multipliers for DNN Accelerators

Recent Deep Neural Networks (DNNs) managed to deliver superhuman accuracy levels on many AI tasks. Several applications rely more and more on DNNs to deliver sophisticated services and DNN accelerators are becoming integral components of modern systems-on-chips. DNNs perform millions of arithmetic operations per inference and DNN accelerators integrate thousands of multiply-accumulate units leading to increased energy requirements. Approximate computing principles are employed to significantly lower the energy consumption of DNN accelerators at the cost of some accuracy loss. Nevertheless, recent research demonstrated that complex DNNs are increasingly sensitive to approximation. Hence, the obtained energy savings are often limited when targeting tight accuracy constraints. In this work, we present a dynamically configurable approximate multiplier that supports three operation modes, i.e., exact, positive error, and negative error. In addition, we propose a filter-oriented approximation method to map the weights to the appropriate modes of the approximate multiplier. Our mapping algorithm balances the positive with the negative errors due to the approximate multiplications, aiming at maximizing the energy reduction while minimizing the overall convolution error. We evaluate our approach on multiple DNNs and datasets against state-of-the-art approaches, where our method achieves 18.33% energy gains on average across 7 NNs on 4 different datasets for a maximum accuracy drop of only 1%.

Reliability-Aware Quantization for Anti-Aging NPUs

Transistor aging is one of the major concerns that challenges designers in advanced technologies. It profoundly degrades the reliability of circuits during its lifetime as it slows down transistors resulting in errors due to timing violations unless large guardbands are included, which leads to considerable performance losses. When it comes to Neural Processing Units (NPUs), where increasing the inference speed is the primary goal, such performance losses cannot be tolerated. In this work, we are the first to propose a reliability-aware quantization to eliminate aging effects in NPUs while completely removing guardbands. Our technique delivers a graceful inference accuracy degradation over time while compensating for the aging-induced delay increase of the NPU. Our evaluation, over ten state-of-the-art neural network architectures trained on the ImageNet dataset, demonstrates that for an entire lifetime of 10 years, the average accuracy loss is merely 3%. In the meantime, our technique achieves 23% higher performance due to the elimination of the aging guardband.

Control Variate Approximation for DNN Accelerators

In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Monte Carlo methods to achieve variance reduction. Our approach significantly decreases the induced error due to approximate multiplications in DNN inference, without requiring time-exhaustive retraining compared to state-of-the-art. Leveraging our control variate method, we use highly approximated multipliers to generate power-optimized DNN accelerators. Our experimental evaluation on six DNNs, for Cifar-10 and Cifar-100 datasets, demonstrates that, compared to the accurate design, our control variate approximation achieves same performance and 24% power reduction for a merely 0.16% accuracy loss.