Related papers: QuadRank: Engineering a High Throughput Rank
Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse…
The memory subsystem has always been a bottleneck in performance as well as significant power contributor in memory intensive applications. Many researchers have presented multi-layered memory hierarchies as a means to design energy and…
Rank and select queries on bitmaps are essential building bricks of many compressed data structures, including text indexes, membership and range supporting spatial data structures, compressed graphs, and more. Theoretically considered yet…
The bidirectional Fano algorithm (BFA) can achieve at least two times decoding throughput compared to the conventional unidirectional Fano algorithm (UFA). In this paper, bidirectional Fano decoding is examined from the queuing theory…
Rank fusion is a powerful technique that allows multiple sources of information to be combined into a single result set. However, to date fusion has not been regarded as being cost-effective in cases where strict per-query efficiency…
While short read aligners, which predominantly use the FM-index, are able to easily index one or a few human genomes, they do not scale well to indexing databases containing thousands of genomes. To understand why, it helps to examine the…
Graphics Processing Units (GPUs) were once used solely for graphical computation tasks but with the increase in the use of machine learning applications, the use of GPUs to perform general-purpose computing has increased in the last few…
In-memory database query processing frequently involves substantial data transfers between the CPU and memory, leading to inefficiencies due to Von Neumann bottleneck. Processing-in-Memory (PIM) architectures offer a viable solution to…
Neural document ranking approaches, specifically transformer models, have achieved impressive gains in ranking performance. However, query processing using such over-parameterized models is both resource and time intensive. In this paper,…
Structured distributions, i.e. distributions over combinatorial spaces, are commonly used to learn latent probabilistic representations from observed data. However, scaling these models is bottlenecked by the high computational and memory…
Recent progress in computer vision-oriented neural network designs is mostly driven by capturing high-order neural interactions among inputs and features. And there emerged a variety of approaches to accomplish this, such as Transformers…
Quantum error-correcting codes protect fragile quantum information by encoding it redundantly, but identifying codes that perform well in practice with minimal overhead remains difficult due to the combinatorial search space and the high…
It has been shown in the indexing literature that there is an essential difference between prefix/range searches on the one hand, and predecessor/rank searches on the other hand, in that the former provably allows faster query resolution.…
Deploying Large Language Models (LLMs) efficiently on edge devices is often constrained by limited memory capacity and high power consumption. Low-bit quantization methods, particularly ternary quantization, have demonstrated significant…
Classification is at the core of data-driven prediction and decision-making, representing a fundamental task in supervised machine learning. Recently, several quantum machine learning algorithms that use quantum kernels as a measure of…
PageRank is a fundamental link analysis algorithm that also functions as a key representative of the performance of Sparse Matrix-Vector (SpMV) multiplication. The traditional PageRank implementation generates fine granularity random memory…
The two most common data-structures for genome indexing, FM-indices and hash-tables, exhibit a fundamental trade-off between memory footprint and performance. We present Ranger, a new indexing technique for nucleotide sequences that is both…
Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from attention score homogenization: middle-context documents…
Query Auto-Completion (QAC) is a widely used feature in many domains, including web and eCommerce search, suggesting full queries based on a prefix typed by the user. QAC has been extensively studied in the literature in the recent years,…
Fully provisioned Message Passing Interface (MPI) parallelism achieves near-optimal wall-clock time for Computational Fluid Dynamics (CFD) solvers. This work addresses a complementary question for shared, cloud-managed clusters: can…