Trinayan Baruah

TL;DR: This work presents MGPUSim, a cycle-accurate, extensively validated, multi-GPU simulator, based on AMD's Graphics Core Next 3 (GCN3) instruction set architecture, and proposes the Locality API, an API extension that allows the GPU programmer to both avoid the complexity of multi- GPU programming, while precisely controlling data placement in the multi- GPUs memory.

TL;DR: This work compares the performance of different programming frameworks, including OpenCL, HC++, and HIP on both integrated APUs and discrete GPUs, using the Hetero-Mark and DNNMark benchmark suites and provides guidance on best practices to programmers when developing applications leveraging the ROC platform.

TL;DR: GNNMark is presented, a feature-rich benchmark suite that covers the diversity present in GNN training workloads, datasets, and GNN frameworks that utilizes a variety of different graph-based data structures, including homogeneous graphs, dynamic graphs, and heterogeneous graphs commonly used in a number of application domains.

TL;DR: Griffin introduces programmer-transparent modifications to both the IOMMU and GPU architecture, supporting efficient runtime page migration based on locality information, and employs a novel mechanism to detect and move pages at runtime between GPUs, increasing the frequency of resolving accesses locally, which in turn improves the performance.

TL;DR: This paper analyzes the performance implications of a CNN model using microarchitectural details on a layer-by-layer basis, and characterize the memory access behavior in the context of a typical GPU memory hierarchy, considering hardware resource utilization associated with each primitive in the CNN model.