Related papers: Dynamic read & write optimization with TurtleKV

Distributed storage systems typically maintain strong consistency between data nodes and metadata nodes by adopting ordered writes: 1) first installing data; 2) then updating metadata to make data visible.We propose SwitchDelta to…

Recent years have witnessed the booming of various differentiable optimization algorithms. These algorithms exhibit different execution patterns, and their execution needs massive computational resources that go beyond a single CPU and GPU.…

Finite-precision arithmetic computations face an inherent tradeoff between accuracy and efficiency. The points in this tradeoff space are determined, among other factors, by different data types but also evaluation orders. To put it simply,…

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and…

Emerging reconfigurable datacenters allow to dynamically adjust the network topology in a demand-aware manner. These datacenters rely on optical switches which can be reconfigured to provide direct connectivity between racks, in the form of…

Index structures are one of the most important tools that DBAs leverage to improve the performance of analytics and transactional workloads. However, building several indexes over large datasets can often become prohibitive and consume…

Existing visual token pruning methods target prompt alignment and visual preservation with static strategies, overlooking the varying relative importance of these objectives across tasks, which leads to inconsistent performance. To address…

Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works…

Models based on the Transformer architecture have seen widespread application across fields such as natural language processing, computer vision, and robotics, with large language models like ChatGPT revolutionizing machine understanding of…

In this demo, we realize data indexes that can morph from being write-optimized at times to being read-optimized at other times nonstop with zero-down time during the workload transitioning. These data indexes are useful for HTAP systems…

Selecting appropriate values for the configurable parameters of Database Management Systems (DBMS) to improve performance is a significant challenge. Recent machine learning (ML)-based tuning systems have shown strong potential, but their…

Reinforcement learning with verifiable rewards (RLVR) generates hundreds of thousands of tokens per training step, with rollout generation dominating the computational cost. The overall token budget can be controlled along two main…

In this work we study the overheads of virtual-to-physical address translation in processor architectures, like x86-64, that implement paged virtual memory using a radix tree which are walked in hardware. Translation Lookaside Buffers are…

Retrieving data from large-scale source code archives is vital for AI training, neural-based software analysis, and information retrieval, to cite a few. This paper studies and experiments with the design of a compressed key-value store for…

Modern foundation models are trained on diverse datasets to enhance generalization across tasks and domains A central challenge in this process is determining how to effectively mix and sample data from multiple sources This naturally leads…

We present the Cuckoo Trie, a fast, memory-efficient ordered index structure. The Cuckoo Trie is designed to have memory-level parallelism -- which a modern out-of-order processor can exploit to execute DRAM accesses in parallel -- without…

Log-Structured Merge trees (LSM trees) are increasingly used as the storage engines behind several data systems, frequently deployed in the cloud. Similar to other database architectures, LSM trees take into account information about the…

Progress in artificial intelligence and machine learning over the past decade has been driven by the ability to train larger deep neural networks (DNNs), leading to a compute demand that far exceeds the growth in hardware performance…

We observe two major trends in LLM-based generative AI: (1) inference is becoming the dominant factor in terms of cost and power consumption, surpassing training, and (2) retrieval augmented generation (RAG) is becoming prevalent. When…

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…