Visual comparison of high-dimensional machine learning datasets helps practitioners identify gaps in data coverage, diagnose distribution shifts, and understand their potential influence on downstream tasks such as classification and object detection. However, the commonly used density map often blurs details and is computationally expensive. We present DiffGrid, a grid-based tool for comparing differences in large datasets. A regularized, grid-based density difference visualization method is developed to enable multi-level analysis of the differences. Interactive zooming and image labels are provided for efficiently exploring differences from overview to detail. We demonstrate the practical value of DiffGrid with two case studies, comparing coresets with full datasets and comparing synthetic infographics with real ones, and validate its effectiveness and usefulness with a quantitative experiment and a user study.

Computation state construction is an indispensable step to achieve fault tolerance and computation mobility for scientific applications by saving and restoring the state during program execution. However, there is no effective state construction scheme yet due to the GPU's batch-mode execution manner as the GPU takes on a larger role in high performance computing. The GPU's complex memory hierarchy means the states are scattered in different memory locations that are difficult to fetch. Programs that are running in parallel make the states difficult to construct for each thread. The paper proposes an application-level computation state construction scheme to support GPU programs. A precompiler and run-time support module are developed to construct and save states in the CPU system memory dynamically. Memory blocks are registered, and new data structures are proposed to save and restore the computation states represented by variables and pointers in the GPU. Secondary storage can be utilized for scalability and long-term fault tolerance.

Checkpoint/restart has been an effective mechanism to achieve fault tolerance for many scientific applications. However, as GPU becomes a much bigger role in high performance computing, there is no effective checkpoint/restart scheme yet due to GPU's batch-mode execution manner. The paper proposes an application-level checkpoint/restart scheme to save and restore GPU computation states. A precompiler and run-time support module are developed to construct and save states in CPU system memory dynamically. Secondary storage can be utilized for scalability and long-term fault tolerance. CUDA applications with complicated memory use are support as well. Experimental results have demonstrated the effectiveness of the proposed scheme.