Related papers: Performance Evaluation of Advanced Features in CUD…

While selecting the hyper-parameters of Neural Networks (NNs) has been so far treated as an art, the emergence of more complex, deeper architectures poses increasingly more challenges to designers and Machine Learning (ML) practitioners,…

Matrix extensions have emerged as an essential feature in modern CPUs to address the surging demands of AI workloads. However, existing designs often incur substantial hardware and software design overhead. Tight coupling with the CPU…

Tensor cores are specialized processing units within GPUs that have demonstrated significant efficiency gains in compute-bound applications such as Deep Learning Training by accelerating dense matrix operations. Given their success,…

Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under tight cost and energy budgets. Most prior evaluations rely on desktop-grade GPUs, obscuring…

GPUs have been favored for training deep learning models due to their highly parallelized architecture. As a result, most studies on training optimization focus on GPUs. There is often a trade-off, however, between cost and efficiency when…

The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of…

With the growing number of data-intensive workloads, GPU, which is the state-of-the-art single-instruction-multiple-thread (SIMT) processor, is hindered by the memory bandwidth wall. To alleviate this bottleneck, previously proposed…

Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…

Edge computing is a popular target for accelerating machine learning algorithms supporting mobile devices without requiring the communication latencies to handle them in the cloud. Edge deployments of machine learning primarily consider…

Gradient boosting decision trees (GBDTs) have seen widespread adoption in academia, industry and competitive data science due to their state-of-the-art performance in many machine learning tasks. One relative downside to these models is the…

As GPUs scale their low precision matrix math throughput to boost deep learning (DL) performance, they upset the balance between math throughput and memory system capabilities. We demonstrate that converged GPU design trying to address…

This paper provides an in-depth characterization of GPU-accelerated systems, to understand the interplay between overlapping computation and communication which is commonly employed in distributed training settings. Due to the large size of…

Approximate memory is a technique to mitigate the performance gap between memory subsystems and CPUs with its reduced access latency at a cost of data integrity. To gain benefit from approximate memory for realistic applications, it is…

Memristor crossbars are circuits capable of performing analog matrix-vector multiplications, overcoming the fundamental energy efficiency limitations of digital logic. They have been shown to be effective in special-purpose accelerators for…

Edge devices like Nvidia Jetson platforms now offer several on-board accelerators -- including GPU CUDA cores, Tensor Cores, and Deep Learning Accelerators (DLA) -- which can be concurrently exploited to boost deep neural network (DNN)…

Machine learning based on neural networks has advanced rapidly, but the high energy consumption required for training and inference remains a major challenge. Hyperdimensional Computing (HDC) offers a lightweight, brain-inspired alternative…

Transformers and LLMs have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is slow and often takes in the order…

Although advances in brain surgery techniques have led to fewer postoperative complications requiring Intensive Care Unit (ICU) monitoring, the routine transfer of patients to the ICU remains the clinical standard, despite its high cost.…

As neural networks are increasingly employed in machine learning practice, how to efficiently share limited training resources among a diverse set of model training tasks becomes a crucial issue. To achieve better utilization of the shared…

This paper proposes TRAININGCXL that can efficiently process large-scale recommendation datasets in the pool of disaggregated memory while making training fault tolerant with low overhead. To this end, i) we integrate persistent memory…