Accelerating Genomic Data Analytics With Composable Hardware Acceleration Framework
Not provided.
SEARCH · Engineering Papers
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Not provided.
Abstract not provided.
Abstract not provided.
This paper considers the optimal energy management for a microgrid. The goal of optimal energy management is to minimize the total generation cost while meeting total demand and satisfying individual generator output limits. To achieve this goal, we develop a distributed algorithm based on the consensus theory and gradient estimation technique. Compared to the existing algorithms with diminishing step-sizes, the proposed algorithm enjoys a faster convergence speed due to the fixed step-size, and thus increases the computation speed, and reduces the computation and communication burden. The proposed distributed algorithm is applicable to both fixed and time-varying directed communication networks. We show that the convergence of the proposed distributed algorithm is achieved if the fixed communication network is strongly connected, or if the time-varying communication network is uniformly jointly strongly connected. Numerical simulation results are used to illustrate and demonstrate the effectiveness of the proposed algorithm.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Concentrating photovoltaic (CPV) systems have great potential to reduce photovoltaic (PV) electricity costs because of the relatively low cost of optical components as compared to PV cells. A transparent polymeric material is used to optically couple the PV cell to optical components and is thus exposed to the concentrated light source at elevated temperatures. In this work polymeric encapsulant materials are positioned close to a Xenon arc lamp to expose them to ultraviolet radiation (UV) that is about 42 times as intense as sunlight. Furthermore, different glass types are used as filters to modify the spectral distribution of light in the UV range. A strong sensitivity of non-silicone-based encapsulants to light below ~350 nm is demonstrated. Of all the materials examined in this study, the polydimethyl silicone samples performed the best. The next best material was an ionomer which maintained optical transmission but became photo-oxidized where exposed to the atmosphere.
Abstract not provided.
In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.
Explore the source record for details and available documents.
Abstract not provided.
The primary goal of this study was to ascertain the presence and types of mechanisms affecting CdS/CdTe device stability in the temperature range of 60 to 120 ..deg..C. It should be noted that the results presented were specific to cells made using the specific growth conditions described.
Not provided.
Writing large amounts of data concurrently to stable storage is a typical I/O pattern of many HPC workflows. This pattern introduces high I/O overheads and results in increased storage space utilization especially for workflows that need to capture the evolution of data structures with high frequency as checkpoints. In this context, many applications, such as graph pattern matching, perform sparse updates to large data structures between checkpoints. For these applications, incremental checkpointing techniques that save only the differences from one checkpoint to another can dramatically reduce the checkpoint sizes, I/O bottlenecks, and storage space utilization. However, such techniques are not without challenges: it is non-trivial to transparently determine what data has changed since a previous checkpoint and assemble the differences in a compact fashion that does not result in excessive metadata. State-of-art data reduction techniques (e.g., compression and de-duplication) have significant limitations when applied to modern HPC applications that leverage GPUs: slow at detecting the differences, generate a large amount of metadata to keep track of the differences, and ignore crucial spatiotemporal checkpoint data redundancy. This paper addresses these challenges by proposing a Merkle tree-based incremental checkpointing method to exploit GPUs' high memory bandwidth and massive parallelism. Experimental results at scale show a significant reduction of the I/O overhead and space utilization of checkpointing compared with state-of-the-art incremental checkpointing and compression techniques.