NDS abstracts memory arrays as native storage that applications can use to describe data locations and uses coordinates in any application-defined multi-dimensional space, thereby avoiding the software overhead associated with data-object transformations.
This paper presents N-Dimensional Storage (NDS), a novel, multi-dimensional memory/storage system that fulfills the demands of modern hardware accelerators and applications. Yet the front-end for these processors/accelerators is inefficient, as memory/storage systems often expose only entrenched linear-space abstractions to an application, and they often ignore the benefits of modern memory/storage systems, such as support for multi-dimensionality through different types of parallel access. NDS: N-Dimensional Storage Yu-Chia Liu (University of California, Riverside) Hung-Wei Tseng (University of California, Riverside) Ībstract: Demands for efficient computing among applications that use high-dimensional datasets have led to multi-dimensional computers-computers that leverage heterogeneous processors/accelerators offering various processing models to support multi-dimensional compute kernels. Mainly, his research focuses on developing efficient testing frameworks for persistent memory programs to facilitate the adoption of normal programs on this new type of memory. His research interests are software design, compilers, and testing frameworks. He currently works at the Programming Languages Research Group advised by Brian Demsky. candidate in the Department of Electrical Engineering and Computer Science at the University of California, Irvine (UCI). Jaaru is also orders of magnitude more efficient than Yat, a model checker that eagerly explores all possible states. We have evaluated Jaaru with PMDK and RECIPE, and found 25 persistency bugs, 18 of which are new. This exploration technique effectively leverages commit stores, a common coding pattern, to reduce the model checking complexity from exponential in the length of program executions to quadratic. Key to Jaaru's efficiency is a new technique based on constraint refinement that can reduce the number of executions that must be explored by many orders of magnitude. We present Jaaru, a fully-automated and ultra-efficient model checker for PM programs. It is more challenging to test crash consistency for PM than for disks given the PM's byte-addressability that leads to significantly more states. Stores to persistent memory are not immediately made persistent - they initially reside in processor cache and are only written to PM when a flush occurs due to space constraints or explicit flush instructions. Ensuring that these persistent data structures are crash consistent (i.e., power failures) is a major challenge. Jaaru: Efficiently model checking persistent memory programs Hamed Gorjiara (UC Irvine) Guoqing Harry Xu (UCLA) Brian Demsky (University of California, Irvine) Ībstract: Persistent memory (PM) technologies combine near DRAM performance with persistency and open the possibility of using one copy of a data structure as both a working copy and a persistent store of the data. Her main research interest is hardware-software co-design for emerging applications and non-volatile and storage device management in that system. She is advised by Myongsoo Jung who leads the Computer Architecture, Non-volatile memory, and operating system. Candidate of Korea Advanced Institute of Science and Technology (KAIST). Our empirical evaluations show that the inference time of HolisticGNN outperforms GNN inference services using high-performance GPU by 7.1x while reducing energy consumption by 33.2x, on average. We fabricate HolisticGNN's hardware RTL and implement its software on an FPGA-based computational SSD (CSSD). To achieve the best end-to-end latency and high energy efficiency, HolisticGNN allows users to implement various GNN algorithms and directly executes them where the data exist in a holistic manner. We propose a novel deep learning framework on large graphs, HolisticGNN, that provides an easy-to-use, near-storage inference infrastructure for fast, energy-efficient GNN processing. However, as GNNs are engaged with a large set of graphs and embedding data on storage, they suffer from heavy I/O accesses and irregular computation. Abstract: Graph neural networks (GNNs) process large-scale graphs consisting of a hundred billion edges, which exhibit much higher accuracy in a variety of prediction tasks.
0 kommentar(er)
