Results 61 to 70 of about 220,437 (272)

Modulo scheduling with reduced register pressure [PDF]

, 1998
Software pipelining is a scheduling technique that is used by some product compilers in order to expose more instruction level parallelism out of innermost loops. Module scheduling refers to a class of algorithms for software pipelining.
Ayguadé Parra, Eduard, González Colás, Antonio María, Llosa Espuny, José Francisco, Valero Cortés, Mateo   +3 more
core   +2 more sources

A Method to Detect Hazards in Pipeline Processor

MATEC Web of Conferences, 2017
In order to improve the throughput of the processors, pipeline technique is widely used to implement the instruction-level parallelism. However, this technique also leads to data hazards which has a great influence on the performance. This paper proposed
He Yihui, Wan Han, Jiang Bo, Gao Xiaopeng   +3 more
doaj   +1 more source

AI‐Driven Defect Engineering for Advanced Thermoelectric Materials

Advanced Materials, EarlyView.
This review presents how AI accelerates the design of defect‐tuned thermoelectric materials. By integrating machine learning with high‐throughput data and physics‐informed representations, it enables efficient prediction of thermoelectric performance from complex defect landscapes.
Chu‐Liang Fu, Mouyang Cheng, Nguyen Tuan Hung, Eunbi Rha, Zhantao Chen, Ryotaro Okabe, Denisse Córdova Carrizales, Manasi Mandal, Yongqiang Cheng, Mingda Li   +9 more
wiley   +1 more source

Investigating performance metrics for container-based HPC environments using x86 and OpenPOWER systems

Journal of Cloud Computing: Advances, Systems and Applications, 2023
Container-based High-Performance Computing (HPC) is changing the way computation is performed and reproduced without sacrificing the raw performance compared to hypervisor-assisted virtualization technologies.
Animesh Kuity, Sateesh K. Peddoju
doaj   +1 more source

From Physics Model to Results: An Optimizing Framework for Cross-Architecture Code Generation [PDF]

, 2013
Starting from a high-level problem description in terms of partial differential equations using abstract tensor notation, the Chemora framework discretizes, optimizes, and generates complete high performance codes for a wide range of compute ...
Blazewicz, Marek, Brandt, Steven R., Ciznicki, Milosz, Hinder, Ian, Kierzynka, Michal, Koppelman, David M., Löffler, Frank, Schnetter, Erik, Tao, Jian   +8 more
core   +4 more sources

Superior Electromechanical Power at Rare‐Earth Manipulated Glassy Morphotropic Phase Transitions

Advanced Science, EarlyView.
An effective physical approach named Rare‐earth Manipulated Glassy Morphotropic Phase Transitions has been experimentally developed and theoretically validated to achieve significant enhancements of 135% and 50% in electrostrain and elastic modulus of lead‐free ferroelectrics respectively, further enabling the significant boost of requisite driving ...
Le Zhang, Liqiang He, Shuyuan Xu, Haoyu Wang, Yunlong Sun, Yating Ran, Dong Wang, Kaiyun Chen, Junkai Deng, Zibin Chen, Danyang Wang, Michael A. Carpenter, Sen Yang   +12 more
wiley   +1 more source

Efficient Prefetch and Issue Scheduling Approaches for Simultaneous Multithreading Applied to Superscalar RISC-V Processor

IEEE Access
Thread level parallelism (TLP) is a common approach to achieve parallelism where Instruction level parallelism (ILP) is insufficient. Hardware multithreading is a prevalent approach in the micro-architecture layer for tolerating long events such as ...
Hananya Ribo, Shlomo Greenberg
doaj   +1 more source

Accelerating SAR Image Registration Using Swarm-Intelligent GPU Parallelization

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
Image registration is an important processing step in synthetic aperture radar (SAR) image applications, such as change detection, and elevation extraction.
Yingbing Liu, Yingcheng Zhou, Yongsheng Zhou, Lixiang Ma, Bingnan Wang, Fan Zhang   +5 more
doaj   +1 more source

On the efficiency of reductions in µ-SIMD media extensions [PDF]

, 2001
Many important multimedia applications contain a significant fraction of reduction operations. Although, in general, multimedia applications are characterized for having high amounts of Data Level Parallelism, reductions and accumulations are difficult ...
Corbal San Adrián, Jesús, Espasa Sans, Roger, Valero Cortés, Mateo   +2 more
core   +1 more source

Enhancing Synaptic Plasticity in Strontium Titanate‐Based Sensory Processing Devices: A Study on Oxygen Vacancy Modulation and Performance in Artificial Neural Networks

Advanced Intelligent Discovery, EarlyView.
This article presents the artificial synapse based on strontium titanate thin films via spin‐coating followed by forming gas annealing to introduce oxygen vacancies. Characterizations (X‐ray photoelectron spectroscopy, electron paramagnetic resonance, Ultraviolet photoelectron spectroscopy (UPS)) confirm increased oxygen vacancies and downward energy ...
Fandi Chen, Zijian Feng, Shuo Zhang, Jie Min, Long Hu, Tianxu Huang, Tingting Mei, Jiyun Kim, Beining Dong, Xinyu Ma, Tao Yin, Jintao Wang, Peiyuan Guan, Tao Wan, Chun‐Ho Lin, Zhi Li, Dewei Chu   +16 more
wiley   +1 more source