Related papers: Leyenda: An Adaptive, Hybrid Sorting Algorithm for…
We study the problem of list ranking in the parallel external memory (PEM) model. We observe an interesting dual nature for the hardness of the problem due to limited information exchange among the processors about the structure of the…
Deep learning-based models are utilized to achieve state-of-the-art performance for recommendation systems. A key challenge for these models is to work with millions of categorical classes or tokens. The standard approach is to learn…
The rising demand for Large Language Model (LLM) inference services has intensified pressure on computational resources, resulting in latency and cost challenges. This paper introduces a novel routing algorithm based on the Non-dominated…
The significant resource demands in LLM serving prompts production clusters to fully utilize heterogeneous hardware by partitioning LLM models across a mix of high-end and low-end GPUs. However, existing parallelization approaches often…
Merging two sorted arrays is a prominent building block for sorting and other functions. Its efficient parallelization requires balancing the load among compute cores, minimizing the extra work brought about by parallelization, and…
Partitioning graphs into blocks of roughly equal size such that few edges run between blocks is a frequently needed operation in processing graphs. Recently, size, variety, and structural complexity of these networks has grown dramatically.…
A new algorithm, Guidesort, for sorting in the uniprocessor variant of the parallel disk model (PDM) of Vitter and Shriver is presented. The algorithm is deterministic and executes a number of (parallel) I/O operations that comes within a…
Labeled Latent Dirichlet Allocation (LLDA) is an extension of the standard unsupervised Latent Dirichlet Allocation (LDA) algorithm, to address multi-label learning tasks. Previous work has shown it to perform in par with other…
We propose an $O(N\cdot M)$ sorting algorithm by Machine Learning method, which shows a huge potential sorting big data. This sorting algorithm can be applied to parallel sorting and is suitable for GPU or TPU acceleration. Furthermore, we…
Motivated by the growing demand for serving large language model inference requests, we study distributed load balancing for global serving systems with network latencies. We consider a fluid model in which continuous flows of requests…
Cassandra is a popular structured storage system with high-performance, scalability and high availability, and is usually used to store data that has some sortable attributes. When deploying and configuring Cassandra, it is important to…
The use of multi-chip modules (MCM) and/or multi-socket boards is the most suitable approach to increase the computation density of servers while keep chip yield attained. This paper introduces a new coherence protocol suitable, in terms of…
Combinatorial optimization problems have aroused extensive research interests due to its huge application potential. In practice, there are highly redundant patterns and characteristics during solving the combinatorial optimization problem,…
Lightweight containers provide an efficient approach for deploying computation-intensive applications in network edge. The layered storage structure of container images can further reduce the deployment cost and container startup time.…
Large-scale distributed training is increasingly becoming communication bound. Many gradient compression algorithms have been proposed to reduce the communication overhead and improve scalability. However, it has been observed that in some…
The paper presents a systematic study and implementation of a reconfigurable combinatorial multi-operand adder for use in Deep Learning systems. The size of carry changes with the number of operands and hence a reliable algorithm to…
Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…
Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…
Many shared-memory parallel irregular applications, such as sparse linear algebra and graph algorithms, depend on efficient loop scheduling (LS) in a fork-join manner despite that the work per loop iteration can greatly vary depending on…
A heterogeneous memory has a single address space with fast access to some addresses (a fast tier of DRAM) and slow access to other addresses (a capacity tier of CXL-attached memory or NVM). A tiered memory system aims to maximize the…