Tabular data embedded in PDF files, web pages, and other types of documents is prevalent in various domains. These tables, which we call human-centric tables (HCTs for short), are dense in information but often exhibit complex structural and semantic layouts. To query these HCTs, some existing solutions focus on transforming them into relational formats. However, they fail to handle the diverse and complex layouts of HCTs, making them not amenable to easy querying with SQL-based approaches. Another emerging option is to use Large Language Models (LLMs) and Vision Language Models (VLMs). However, there is a lack of standard evaluation benchmarks to measure and compare the performance of models to query HCTs using natural language. To address this gap, we propose the HumanCentric Tables Question-Answering extensive benchmark (HCTQA) consisting of thousands of HCTs with several thousands of natural language questions with their respective answers. More specifically, HCT-QA includes 1,880 real-world HCTs with 9,835 QA pairs in addition to 4,679 synthetic HCTs with 67.7K QA pairs. Also, we show through extensive experiments the performance of 25 and 9 different LLMS and VLMs, respectively, in an answering HCT-QA's questions. In addition, we show how finetuning an LLM on HCT-QA improves F1 scores by up to 25 percentage points compared to the off-the-shelf model. Compared to existing benchmarks, HCT-QA stands out for its broad complexity and diversity of covered HCTs and generated questions, its comprehensive metadata enabling deeper insight and analysis, and its novel synthetic data and QA generator.

Processing-in-Memory (PIM) is a new computing paradigm aimed at minimizing data movement, which is a bottleneck in modern and emerging applications. PIM upgrades the otherwise passive memory subsystem to an active computation role along with the processor. PIM achieves this by moving processing cores to where the data resides, thereby reducing memory access latency, increasing overall memory bandwidth and decreasing energy consumption. In this paper, we leverage the commercially available real UPMEM PIM system to accelerate the execution of the aggregation operator, which is data-intensive and involves large amounts of data movements. We tailor the operator to PIM, propose various performance optimizations with regards to the architectural peculiarities of the UPMEM PIM system and conduct evaluations in comparison with a CPU baseline implementation. Our PIM-based aggregation outperforms the CPU baseline by up to a speedup of 2.41 x.

Distributed in-memory processing frameworks accelerate application runs by caching important datasets in memory. Allocating a suitable cluster configuration for caching these datasets plays a crucial role in achieving minimal cost. We present Agile-ant, a self-managing framework that identifies important datasets and scales out the cluster memory to cache them on the fly without any human interaction, without any prior knowledge of the application, the characteristics of the input data, the specification of the computing resources and their utilization by multiple-tenants. We evaluate Agile-ant on various real-world applications. Compared with our baseline, Agile-ant reduces execution cost by 78.3% on average and provides better performance than the related work.

Distributed in-memory processing frameworks accelerate iterative workloads by caching suitable datasets in memory rather than recomputing them in each iteration. Selecting appropriate datasets to cache as well as allocating a suitable cluster configuration for caching these datasets play a crucial role in achieving optimal performance. In practice, both are tedious, time-consuming tasks and are often neglected by end users, who are typically not aware of workload semantics, sizes of intermediate data, and cluster specification.

Developers of Apache Spark applications can accelerate their workloads by caching suitable intermediate results in memory and reusing them rather than recomputing them all over again every time they are needed. However, as scientific workflows are becoming more complex, application developers are becoming more prone to making wrong caching decisions, which we refer to as caching anomalies , that lead to poor performance. We present and give a demonstration of Spark Caching Anomalies Detector (SparkCAD) , a developer decision support tool that visualizes the logical plan of Spark applications and detects caching anomalies.

Abstract Apache Spark jobs are often characterized by processing huge data sets and, therefore, require runtimes in the range of minutes to hours. Thus, being able to predict the runtime of such jobs would be useful not only to know when the job will finish, but also for scheduling purposes, to estimate monetary costs for cloud deployment, or to determine an appropriate cluster configuration, such as the number of nodes. However, predicting Spark job runtimes is much more challenging than for standard database queries: cluster configuration and parameters have a significant performance impact and jobs usually contain a lot of user-defined code making it difficult to estimate cardinalities and execution costs. In this paper, we present a gray-box modeling methodology for runtime prediction of Apache Spark jobs. Our approach comprises two steps: first, a white-box model for predicting the cardinalities of the input RDDs of each operator is built based on prior knowledge about the behavior and application parameters such as applied filters data, number of iterations, etc. In the second step, a black-box model for each task constructed by monitoring runtime metrics while varying allocated resources and input RDD cardinalities is used. We further show how to use this gray-box approach not only for predicting the runtime of a given job, but also as part of a decision model for reusing intermediate cached results of Spark jobs. Our methodology is validated with experimental evaluation showing a highly accurate prediction of the actual job runtime and a performance improvement if intermediate results can be reused.