47 citations · 55 across the 5 of their papers we have counts for
6 papers
Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
Ziqi Yuan, Haoyang Zhang, Yirui Eric Zhou +4
We present the design and implementation of a new lifetime-aware tensor offloading framework for GPU memory expansion using low-cost PCIe-based solid-state drives (SSDs). Our frame…
CODAG: Characterizing and Optimizing Decompression Algorithms for GPUs
Jeongmin Park, Zaid Qureshi, Vikram Mailthody +10
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, b…
Overload: Latency Attacks on Object Detection for Edge Devices
Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung +1
Nowadays, the deployment of deep learning-based applications is an essential task owing to the increasing demands on intelligent services. In this paper, we investigate latency att…
GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture
Zaid Qureshi, Vikram Sharma Mailthody, Isaac Gelado +10
Graphics Processing Units (GPUs) have traditionally relied on the host CPU to initiate access to the data storage. This approach is well-suited for GPU applications with known data…
TEMPI: An Interposed MPI Library with a Canonical Representation of CUDA-aware Datatypes
Carl Pearson, Kun Wu, I-Hsin Chung +2
MPI derived datatypes are an abstraction that simplifies handling of non-contiguous data in MPI applications. These datatypes are recursively constructed at runtime from primitive…
Tearing Down the Memory Wall
Zaid Qureshi, Vikram Sharma Mailthody, Seung Won Min +3
We present a vision for the Erudite architecture that redefines the compute and memory abstractions such that memory bandwidth and capacity become first-class citizens along with c…