Related papers: DINOMO: An Elastic, Scalable, High-Performance Key…
Modern large-scale language model pre-training relies heavily on the single program multiple data (SPMD) paradigm, which requires tight coupling across accelerators. Due to this coupling, transient slowdowns, hardware failures, and…
User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 10^7, results in expensive storage and computational cost. This prohibits fast…
Today, deep learning is an essential technology for our life. To solve more complex problems with deep learning, both sizes of training datasets and neural networks are increasing. To train a model with large datasets and networks,…
The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications. %, due to the intensive data movements. The decade-old idea of leveraging in-memory processing…
Big data storage management is one of the most challenging issues for Grid computing environments, since large amount of data intensive applications frequently involve a high degree of data access locality. Grid applications typically deal…
The current mobile applications have rapidly growing memory footprints, posing a great challenge for memory system design. Insufficient DRAM main memory will incur frequent data swaps between memory and storage, a process that hurts…
Computing-in-Memory (CIM) architectures have emerged as a promising solution for accelerating Deep Neural Networks (DNNs) by mitigating data movement bottlenecks. However, realizing the potential of CIM requires specialized dataflow…
Non-volatile memory is expected to co-exist or replace DRAM in upcoming architectures. Durable concurrent data structures for non-volatile memories are essential building blocks for constructing adequate software for use with these…
Persistent or Non Volatile Memory (PMEM or NVM) has recently become commercially available under several configurations with different purposes and goals. Despite the attention to the topic, we are not aware of a comprehensive empirical…
Volumetric data structures typically prioritize data locality, focusing on efficient memory access patterns. This singular focus can neglect other critical performance factors, such as occupancy, communication, and kernel fusion. We…
Memory disaggregation addresses memory imbalance in a cluster by decoupling CPU and memory allocations of applications while also increasing the effective memory capacity for (memory-intensive) applications beyond the local memory limit…
Data management applications store their data using structured files in which data are usually sorted to serve indexing and queries. However, in-place insertions and removals of data are not naturally supported in a file's address space. To…
Processing-in-memory (PIM) architectures bring computation closer to data, reducing the processor-memory transfer bottleneck in traditional processor-centric designs. Novel hardware solutions, such as UPMEM's in-memory processing…
Memory disaggregation is being considered as a strong alternative to traditional architecture to deal with the memory under-utilization in data centers. Disaggregated memory can adapt to dynamically changing memory requirements for the data…
Deep neural networks (DNN) have shown superior performance in a variety of tasks. As they rapidly evolve, their escalating computation and memory demands make it challenging to deploy them on resource-constrained edge devices. Though…
Non-volatile main memory (NVMM) allows programmers to build complex, persistent, pointer-based data structures that can offer substantial performance gains over conventional approaches to managing persistent state. This programming model…
Wearable devices are revolutionizing personal technology, but their usability is often hindered by frequent charging due to high power consumption. This paper introduces Distributed Neural Networks (DistNN), a framework that distributes…
Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that…
Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different resource usage. However, its wide adoption is hindered by a fundamental conflict with the…
We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs). We develop a novel algorithm to…