Non-Volatile Main Memories (NVMMs) have recently emerged as a promising technology for future memory systems. Generally, NVMMs have many desirable properties such as high density, byte-addressability, non-volatility, ...Non-Volatile Main Memories (NVMMs) have recently emerged as a promising technology for future memory systems. Generally, NVMMs have many desirable properties such as high density, byte-addressability, non-volatility, low cost, and energy efficiency, at the expense of high write latency, high write power consumption, and limited write endurance. NVMMs have become a competitive alternative of Dynamic Random Access Memory (DRAM), and will fundamentally change the landscape of memory systems. They bring many research opportunities as well as challenges on system architectural designs, memory management in operating systems (OSes), and programming models for hybrid memory systems. In this article, we revisit the landscape of emerging NVMM technologies, and then survey the state-of-the-art studies of NVMM technologies. We classify those studies with a taxonomy according to different dimensions such as memory architectures, data persistence, performance improvement, energy saving, and wear leveling. Second, to demonstrate the best practices in building NVMM systems, we introduce our recent work of hybrid memory system designs from the dimensions of architectures, systems, and applications. At last, we present our vision of future research directions of NVMMs and shed some light on design challenges and opportunities.展开更多
The development of low-cost and high-active cocatalysts is one of the most significant links for photocatalytic water splitting.Herein,a novel strategy of electron delocalization modulation for transition metal sulfid...The development of low-cost and high-active cocatalysts is one of the most significant links for photocatalytic water splitting.Herein,a novel strategy of electron delocalization modulation for transition metal sulfides has been developed by anion hybridization.P-modified CoS_(2)(CoS_(2)|P)nanocrystals were firstly fabricated via a gas-solid reaction and coupled with CdS nanorods to construct a composite catalyst for solar H2 evolution reaction(HER).The CdS/CoS_(2)|P catalyst shows an HER rate of 57.8 pmol h-1,which is 18 times that of the bare CdS,8 times that of the CdS/CoS2,and twice that of Pt/CdS.The reduced energy barrier and suppressed reverse reaction for HER on the catalyst have been predicted and explained by density functional theory(DFT)calculation.The underlying design strategy of novel cocatalysts by electron delocalization modulation may shed light on the rational development of other advanced catalysts for energy conversion.展开更多
Development of low-cost and efficient photocatalytic materials with visible-light response is of urgent need for solving energy and environmental problems.Here,a metal-free two-dimensional(2D)π-conjugated hybrid g-C_...Development of low-cost and efficient photocatalytic materials with visible-light response is of urgent need for solving energy and environmental problems.Here,a metal-free two-dimensional(2D)π-conjugated hybrid g-C_(3)N_(4)photocatalyst with tunable band structure was prepared by a novel one-pot bottom-up method based on a supersaturated precipitation process of urea and triethanolamine(TEOA)solution.The microstructure of the hybrid g-C_(3)N_(4)is revealed to be a compound of periodic tri-s-triazine units grafted with N-doped graphene(GR)fragments.From experimental evidence and theoretical calculations,the two differentπ-conjugated fragments in the hybrid g-C_(3)N_(4)material are proved to construct a 2D in-plane junction structure,thereby expanding the light absorption range and accelerating the interface charge transfer.Theπ-conjugated electron coupling in the 2D photocatalyst eliminates the grain boundary effect,and the coupled highest occupied molecular orbital(HOMO)effectively promotes the separation of photo-induced charge carriers.Compared with the g-C_(3)N_(4)prepared by the conventional method,the visible-light H2 production activity of the optimized sample is enhanced by 253%.This work provides a new strategy of constructing metal-free g-C_(3)N_(4)hybrids for efficient photocatalytic water splitting.展开更多
With the rapid growth of real-world graphs,the size of which can easily exceed the on-chip(board)storage capacity of an accelerator,processing large-scale graphs on a single Field Programmable Gate Array(FPGA)becomes ...With the rapid growth of real-world graphs,the size of which can easily exceed the on-chip(board)storage capacity of an accelerator,processing large-scale graphs on a single Field Programmable Gate Array(FPGA)becomes difficult.The multi-FPGA acceleration is of great necessity and importance.Many cloud providers(e.g.,Amazon,Microsoft,and about:blank)now expose FPGAs to users in their data centers,providing opportunities to accelerate large-scale graph processing.In this paper,we present a communication library,called FDGLib,which can easily scale out any existing single FPGA-based graph accelerator to a distributed version in a data center,with minimal hardware engineering efforts.FDGLib provides six APIs that can be easily used and integrated into any FPGA-based graph accelerator with only a few lines of code modifications.Considering the torus-based FPGA interconnection in data centers,FDGLib also improves communication efficiency using simple yet effective torus-friendly graph partition and placement schemes.We interface FDGLib into AccuGraph,a state-of-the-art graph accelerator.Our results on a 32-node Microsoft Catapult-like data center show that the distributed AccuGraph can be 2.32x and 4.77x faster than a state-of-the-art distributed FPGA-based graph accelerator ForeGraph and a distributed CPU-based graph system Gemini,with better scalability.展开更多
基金Supported jointly by the National Natural Science Foundation of China under Grants Nos. 61672251, 61732010, 61825202, and 61929103.
文摘Non-Volatile Main Memories (NVMMs) have recently emerged as a promising technology for future memory systems. Generally, NVMMs have many desirable properties such as high density, byte-addressability, non-volatility, low cost, and energy efficiency, at the expense of high write latency, high write power consumption, and limited write endurance. NVMMs have become a competitive alternative of Dynamic Random Access Memory (DRAM), and will fundamentally change the landscape of memory systems. They bring many research opportunities as well as challenges on system architectural designs, memory management in operating systems (OSes), and programming models for hybrid memory systems. In this article, we revisit the landscape of emerging NVMM technologies, and then survey the state-of-the-art studies of NVMM technologies. We classify those studies with a taxonomy according to different dimensions such as memory architectures, data persistence, performance improvement, energy saving, and wear leveling. Second, to demonstrate the best practices in building NVMM systems, we introduce our recent work of hybrid memory system designs from the dimensions of architectures, systems, and applications. At last, we present our vision of future research directions of NVMMs and shed some light on design challenges and opportunities.
基金supported by the National Natural Science Foundation of China(Nos.51872138 and 22002060)Natural Science Foundation of Jiangsu Province(No.BK20181380)+2 种基金Qing Lan Project,Six Talent Peaks Project in Jiangsu Province(No.XCL-029)Priority Academic Program Development of the Jiangsu Higher Education Institutions(PAPD).Dr.Hengming Huang gratefully acknowledges the support provided by China Scholarships Council(CSC No.202008320109)China Postdoctoral Science Foundation(No.2020M681564).
文摘The development of low-cost and high-active cocatalysts is one of the most significant links for photocatalytic water splitting.Herein,a novel strategy of electron delocalization modulation for transition metal sulfides has been developed by anion hybridization.P-modified CoS_(2)(CoS_(2)|P)nanocrystals were firstly fabricated via a gas-solid reaction and coupled with CdS nanorods to construct a composite catalyst for solar H2 evolution reaction(HER).The CdS/CoS_(2)|P catalyst shows an HER rate of 57.8 pmol h-1,which is 18 times that of the bare CdS,8 times that of the CdS/CoS2,and twice that of Pt/CdS.The reduced energy barrier and suppressed reverse reaction for HER on the catalyst have been predicted and explained by density functional theory(DFT)calculation.The underlying design strategy of novel cocatalysts by electron delocalization modulation may shed light on the rational development of other advanced catalysts for energy conversion.
基金financially supported by National Natural Science Foundation of China(Nos.22002060 and 51872138)Natural Science Foundation of Jiangsu Province(No.BK20181380)+3 种基金Qing Lan Project,Six Talent Peaks Project in Jiangsu Province(No.XCL029)Priority Academic Program Development of the Jiangsu Higher Education Institutions(PAPD)support provided by China Scholarships Council(CSC No.202008320109)China Postdoctoral Science Foundation(No.2020M681564)。
文摘Development of low-cost and efficient photocatalytic materials with visible-light response is of urgent need for solving energy and environmental problems.Here,a metal-free two-dimensional(2D)π-conjugated hybrid g-C_(3)N_(4)photocatalyst with tunable band structure was prepared by a novel one-pot bottom-up method based on a supersaturated precipitation process of urea and triethanolamine(TEOA)solution.The microstructure of the hybrid g-C_(3)N_(4)is revealed to be a compound of periodic tri-s-triazine units grafted with N-doped graphene(GR)fragments.From experimental evidence and theoretical calculations,the two differentπ-conjugated fragments in the hybrid g-C_(3)N_(4)material are proved to construct a 2D in-plane junction structure,thereby expanding the light absorption range and accelerating the interface charge transfer.Theπ-conjugated electron coupling in the 2D photocatalyst eliminates the grain boundary effect,and the coupled highest occupied molecular orbital(HOMO)effectively promotes the separation of photo-induced charge carriers.Compared with the g-C_(3)N_(4)prepared by the conventional method,the visible-light H2 production activity of the optimized sample is enhanced by 253%.This work provides a new strategy of constructing metal-free g-C_(3)N_(4)hybrids for efficient photocatalytic water splitting.
基金supported by the National Key Research and Development Program of China under Grant No.2018YFB1003502the National Natural Science Foundation of China under Grant Nos.62072195,61825202,61832006,and 61628204.
文摘With the rapid growth of real-world graphs,the size of which can easily exceed the on-chip(board)storage capacity of an accelerator,processing large-scale graphs on a single Field Programmable Gate Array(FPGA)becomes difficult.The multi-FPGA acceleration is of great necessity and importance.Many cloud providers(e.g.,Amazon,Microsoft,and about:blank)now expose FPGAs to users in their data centers,providing opportunities to accelerate large-scale graph processing.In this paper,we present a communication library,called FDGLib,which can easily scale out any existing single FPGA-based graph accelerator to a distributed version in a data center,with minimal hardware engineering efforts.FDGLib provides six APIs that can be easily used and integrated into any FPGA-based graph accelerator with only a few lines of code modifications.Considering the torus-based FPGA interconnection in data centers,FDGLib also improves communication efficiency using simple yet effective torus-friendly graph partition and placement schemes.We interface FDGLib into AccuGraph,a state-of-the-art graph accelerator.Our results on a 32-node Microsoft Catapult-like data center show that the distributed AccuGraph can be 2.32x and 4.77x faster than a state-of-the-art distributed FPGA-based graph accelerator ForeGraph and a distributed CPU-based graph system Gemini,with better scalability.
