Related papers: Conduit: Programmer-Transparent Near-Data Processi…

For NVIDIA GPUs, CUDA is the primary interface through which applications orchestrate GPU execution, yet much of the logic that realizes CUDA operations resides in NVIDIA's closed-source userspace driver. As a result, the translation from…

As the cost-per-byte of storage systems dramatically decreases, SSDs are finding their ways in emerging cloud infrastructure. Similar trend is happening for main memory subsystem, as advanced DRAM technologies with higher capacity,…

Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and…

Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to…

Improving the performance and reducing the cost of cloud data systems is increasingly challenging. Data processing units (DPUs) are a promising solution, but utilizing them for data processing needs characterizing the new hardware and…

Deep Neural Networks (DNNs) are widely used by engineers to solve difficult problems that require predictive modeling from data. However, these models are often massive, with millions or billions of parameters, and require substantial…

When executing a deep neural network (DNN), its model parameters are loaded into GPU memory before execution, incurring a significant GPU memory burden. There are studies that reduce GPU memory usage by exploiting CPU memory as a swap…

Serverless computing promises enhanced resource efficiency and lower user costs, yet is burdened by a heavyweight, CPU-bound data plane. Prior efforts exploiting shared memory reduce overhead locally but fall short when scaling across…

Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient backpropagation in large backbones, thus significantly…

Absence of large-scale labeled data in the practitioner's target domain can be a bottleneck to applying machine learning algorithms in practice. Transfer learning is a popular strategy for leveraging additional data to improve the…

Synthesizing user-intended programs from a small number of input-output examples is a challenging problem with several important applications like spreadsheet manipulation, data wrangling and code refactoring. Existing synthesis systems…

In semidefinite programming (SDP), a number of pre-processing techniques have been developed including chordal-completion procedures, which reduce the dimension of individual constraints by exploiting sparsity therein, and facial reduction,…

Deploying deep neural networks (DNNs) on those resource-constrained edge platforms is hindered by their substantial computation and storage demands. Quantized multi-precision DNNs, denoted as MP-DNNs, offer a promising solution for these…

Deep operator networks (DeepONets) are powerful architectures for fast and accurate emulation of complex dynamics. As their remarkable generalization capabilities are primarily enabled by their projection-based attribute, we investigate…

Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable…

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computationally expensive model…

Spreadsheet software is the tool of choice for interactive ad-hoc data management, with adoption by billions of users. However, spreadsheets are not scalable, unlike database systems. On the other hand, database systems, while highly…

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy…

Non-volatile memory (NVM) technologies such as spin-transfer torque magnetic random access memory (STT-MRAM) and spin-orbit torque magnetic random access memory (SOT-MRAM) have significant advantages compared to conventional SRAM due to…

Data compression and decompression have become vital components of big-data applications to manage the exponential growth in the amount of data collected and stored. Furthermore, big-data applications have increasingly adopted GPUs due to…