Related papers: Transparent Checkpoint-Restart for Hardware-Accele…
This work presents transparent checkpointing of OpenGL applications, refining the split-process technique[1] for application in GPU-based 3D graphics. The split-process technique was earlier applied to checkpointing MPI and CUDA programs,…
Deep learning training at scale is resource-intensive and time-consuming, often running across hundreds or thousands of GPUs for weeks or months. Efficient checkpointing is crucial for running these workloads, especially in multi-tenant…
InfiniBand is widely used for low-latency, high-throughput cluster computing. Saving the state of the InfiniBand network as part of distributed checkpointing has been a long-standing challenge for researchers. Because of a lack of a…
Fault-tolerance has always been an important topic when it comes to running massively parallel programs at scale. Statistically, hardware and software failures are expected to occur more often on systems gathering millions of computing…
GPUReplay (GR) is a novel way for deploying GPU-accelerated computation on mobile and embedded devices. It addresses high complexity of a modern GPU stack for deployment ease and security. The idea is to record GPU executions on the full…
The share of the top 500 supercomputers with NVIDIA GPUs is now over 25% and continues to grow. While fault tolerance is a critical issue for supercomputing, there does not currently exist an efficient, scalable solution for CUDA…
Reproducing executions of multithreaded programs is very challenging due to many intrinsic and external non-deterministic factors. Existing RnR systems achieve significant progress in terms of performance overhead, but none targets the…
Fault tolerance for the upcoming exascale generation has long been an area of active research. One of the components of a fault tolerance strategy is checkpointing. Petascale-level checkpointing is demonstrated through a new mechanism for…
It is common today to deploy complex software inside a virtual machine (VM). Snapshots provide rapid deployment, migration between hosts, dependability (fault tolerance), and security (insulating a guest VM from the host). Yet, for each…
Purpose: Image reconstruction in challenging scenarios requires accurate characterisations of coil sensitivity profiles, local off-resonances (B0) and effective encoding fields. Reconstruction methods utilising all of this information rely…
The conversion of traditional film into stereo 3D has become an important problem in the past decade. One of the main bottlenecks is a disocclusion step, which in commercial 3D conversion is usually done by teams of artists armed with a…
Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge. Existing methods particularly those based on experience…
University campuses host abundant but fragmented GPU resources whose voluntary sharing is blocked by a mismatch between revocable, autonomous ownership and migration mechanisms that assume stationary failure hazards, homogeneous…
In LHC Run 3, ALICE will increase the data taking rate significantly to 50 kHz continuous read-out of minimum bias Pb-Pb collisions. The reconstruction strategy of the online-offline computing upgrade foresees a first synchronous online…
3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow.…
The accuracy of large language models (LLMs) improves with increasing model size, but increasing model complexity also poses significant challenges to training stability. Periodic checkpointing is a key mechanism for fault recovery and is…
Integration of CPU and GPU technologies is a key enabler for modern AI and graphics workloads, combining control-oriented processing with massive parallel compute capability. As systems evolve toward chiplet-based architectures, pre-silicon…
Unified Virtual Memory (UVM) was recently introduced on recent NVIDIA GPUs. Through software and hardware support, UVM provides a coherent shared memory across the entire heterogeneous node, migrating data as appropriate. The older CUDA…
Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overhead can become a major bottleneck, sometimes exceeding the…
GPUs have become essential in modern high performance computing, but programming them correctly remains a significant challenge. This difficulty arises from subtle concurrency bugs that result from the explicit management of synchronization…