混洗SRAM:SRAM中的并行按位数据混洗

向量处理单元(vector processing unit,VPU)已被广泛应用于神经网络、信号处理和高性能计算等处理器设计中,但其总体性能仍受限于专门用于对齐数据的混洗操作.传统上,处理器使用其数据混洗单元来处理混洗操作.然而,使用数据混洗单元来处理混洗指令将带来昂贵的数据移动开销,并且数据混洗单元只能串行混洗数据.事实上,混洗操作只会改变数据的布局,理想情况下混洗操作应在内存中完成.随着存内计算技术的发展,SRAM不仅可以作为存储部件,同时还能作为计算单元.为了实现存内混洗,提出了混洗SRAM,它可以在SRAM体中逐位地并行混洗多个向量.混洗SRAM的关键思想是利用SRAM体中位线的数据移动能力来改变数据的布局.这样SRAM体中位于同一位线上不同数据的相同位可以同时被移动,从而使混洗操作拥有高度的并行性.通过适当的数据布局和向量混洗扩展指令的支持,混洗SRAM可以高效地处理常用的混洗操作.评测结果表明,对于常用的混洗操作,混洗SRAM可以实现平均28倍的性能增益,对于FFT,AlexNet,VggNet等实际的应用,可以实现平均3.18倍的性能增益.混洗SRAM相较于传统SRAM的面积开销仅增加了4.4%.

多重散射对40nm SRAM和3D-SRAM单粒子翻转的影响

基于RPP(rectangular parallelepiped)模型,利用Geant4软件包,构建了一个40 nm SRAM器件模型用于单粒子翻转效应模拟,通过Weibull函数拟合得到σ_(sat)和LET_(th)分别为8.98×10^(-9)cm^(2)·bit^(-1)和0.084 MeV/(mg·cm^(-2)).基于3D-IC技术设计了一种新的3D-SRAM器件,通过Geant4进行了建模和单粒子翻转模拟,结果表明,在同一3D-SRAM器件中上层单元对下层单元有防护作用.通过改变覆盖层中的高Z材料,发现高Z材料可以有效地减少Fe离子在射程末端的多重散射,且Ta的效果优于W.在同一3D-SRAM器件中,下层单元(die3)的多重散射截面峰值更低.

The complex roles of m^(6)A modifications in neural stem cell proliferation, differentiation, and self-renewal and implications for memory and neurodegenerative diseases

N6-methyladenosine(m^(6)A), the most prevalent and conserved RNA modification in eukaryotic cells, profoundly influences virtually all aspects of mRNA metabolism. mRNA plays crucial roles in neural stem cell genesis and neural regeneration, where it is highly concentrated and actively involved in these processes. Changes in m^(6)A modification levels and the expression levels of related enzymatic proteins can lead to neurological dysfunction and contribute to the development of neurological diseases. Furthermore, the proliferation and differentiation of neural stem cells, as well as nerve regeneration, are intimately linked to memory function and neurodegenerative diseases. This paper presents a comprehensive review of the roles of m^(6)A in neural stem cell proliferation, differentiation, and self-renewal, as well as its implications in memory and neurodegenerative diseases. m^(6)A has demonstrated divergent effects on the proliferation and differentiation of neural stem cells. These observed contradictions may arise from the time-specific nature of m^(6)A and its differential impact on neural stem cells across various stages of development. Similarly, the diverse effects of m^(6)A on distinct types of memory could be attributed to the involvement of specific brain regions in memory formation and recall. Inconsistencies in m^(6)A levels across different models of neurodegenerative disease, particularly Alzheimer's disease and Parkinson's disease, suggest that these disparities are linked to variations in the affected brain regions. Notably, the opposing changes in m^(6)A levels observed in Parkinson's disease models exposed to manganese compared to normal Parkinson's disease models further underscore the complexity of m^(6)A's role in neurodegenerative processes. The roles of m^(6)A in neural stem cell proliferation, differentiation, and self-renewal, and its implications in memory and neurodegenerative diseases, appear contradictory. These inconsistencies may be attributed to the timespecific nature of m^(6)A and its varying effects on distinct brain regions and in different environments.

Exercise preconditioning alleviates ischemia-induced memory deficits by increasing circulating adiponectin

Cerebral ischemia is a major health risk that requires preventive approaches in addition to drug therapy.Physical exercise enhances neurogenesis and synaptogenesis,and has been widely used for functional rehabilitation after stroke.In this study,we determined whether exercise training before disease onset can alleviate the severity of cerebral ischemia.We also examined the role of exercise-induced circulating factors in these effects.Adult mice were subjected to 14 days of treadmill exercise training before surgery for middle cerebral artery occlusion.We found that this exercise pre-conditioning strategy effectively attenuated brain infarct area,inhibited gliogenesis,protected synaptic proteins,and improved novel object and spatial memory function.Further analysis showed that circulating adiponectin plays a critical role in these preventive effects of exercise.Agonist activation of adiponectin receptors by Adipo Ron mimicked the effects of exercise,while inhibiting receptor activation abolished the exercise effects.In summary,our results suggest a crucial role of circulating adiponectin in the effects of exercise pre-conditioning in protecting against cerebral ischemia and supporting the health benefits of exercise.

Recombinant chitinase-3-like protein 1 alleviates learning and memory impairments via M2 microglia polarization in postoperative cognitive dysfunction mice

Postoperative cognitive dysfunction is a seve re complication of the central nervous system that occurs after anesthesia and surgery,and has received attention for its high incidence and effect on the quality of life of patients.To date,there are no viable treatment options for postoperative cognitive dysfunction.The identification of postoperative cognitive dysfunction hub genes could provide new research directions and therapeutic targets for future research.To identify the signaling mechanisms contributing to postoperative cognitive dysfunction,we first conducted Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analyses of the Gene Expression Omnibus GSE95426 dataset,which consists of mRNAs and long non-coding RNAs differentially expressed in mouse hippocampus3 days after tibial fracture.The dataset was enriched in genes associated with the biological process"regulation of immune cells,"of which Chill was identified as a hub gene.Therefore,we investigated the contribution of chitinase-3-like protein 1 protein expression changes to postoperative cognitive dysfunction in the mouse model of tibial fractu re surgery.Mice were intraperitoneally injected with vehicle or recombinant chitinase-3-like protein 124 hours post-surgery,and the injection groups were compared with untreated control mice for learning and memory capacities using the Y-maze and fear conditioning tests.In addition,protein expression levels of proinflammatory factors(interleukin-1βand inducible nitric oxide synthase),M2-type macrophage markers(CD206 and arginase-1),and cognition-related proteins(brain-derived neurotropic factor and phosphorylated NMDA receptor subunit NR2B)were measured in hippocampus by western blotting.Treatment with recombinant chitinase-3-like protein 1 prevented surgery-induced cognitive impairment,downregulated interleukin-1βand nducible nitric oxide synthase expression,and upregulated CD206,arginase-1,pNR2B,and brain-derived neurotropic factor expression compared with vehicle treatment.Intraperitoneal administration of the specific ERK inhibitor PD98059 diminished the effects of recombinant chitinase-3-like protein 1.Collectively,our findings suggest that recombinant chitinase-3-like protein 1 ameliorates surgery-induced cognitive decline by attenuating neuroinflammation via M2 microglial polarization in the hippocampus.Therefore,recombinant chitinase-3-like protein1 may have therapeutic potential fo r postoperative cognitive dysfunction.

Regulator of G protein signaling 6 mediates exercise-induced recovery of hippocampal neurogenesis,learning,and memory in a mouse model of Alzheimer’s disease

Hippocampal neuronal loss causes cognitive dysfunction in Alzheimer’s disease.Adult hippocampal neurogenesis is reduced in patients with Alzheimer’s disease.Exercise stimulates adult hippocampal neurogenesis in rodents and improves memory and slows cognitive decline in patients with Alzheimer’s disease.However,the molecular pathways for exercise-induced adult hippocampal neurogenesis and improved cognition in Alzheimer’s disease are poorly understood.Recently,regulator of G protein signaling 6(RGS6)was identified as the mediator of voluntary running-induced adult hippocampal neurogenesis in mice.Here,we generated novel RGS6fl/fl;APP_(SWE) mice and used retroviral approaches to examine the impact of RGS6 deletion from dentate gyrus neuronal progenitor cells on voluntary running-induced adult hippocampal neurogenesis and cognition in an amyloid-based Alzheimer’s disease mouse model.We found that voluntary running in APP_(SWE) mice restored their hippocampal cognitive impairments to that of control mice.This cognitive rescue was abolished by RGS6 deletion in dentate gyrus neuronal progenitor cells,which also abolished running-mediated increases in adult hippocampal neurogenesis.Adult hippocampal neurogenesis was reduced in sedentary APP_(SWE) mice versus control mice,with basal adult hippocampal neurogenesis reduced by RGS6 deletion in dentate gyrus neural precursor cells.RGS6 was expressed in neurons within the dentate gyrus of patients with Alzheimer’s disease with significant loss of these RGS6-expressing neurons.Thus,RGS6 mediated voluntary running-induced rescue of impaired cognition and adult hippocampal neurogenesis in APP_(SWE) mice,identifying RGS6 in dentate gyrus neural precursor cells as a possible therapeutic target in Alzheimer’s disease.

Therapeutic potential of Carum carvi in depression,memory loss,and hippocampal sclerosis reversal in temporal lobe epilepsy

Background:Epilepsy is a disease characterized by unprovoked seizures,and it affects around 70 million people worldwide.Standard treatment is ineffective in one third of all epilepsy patients.Temporal Lobe Epilepsy with Hippocampal Sclerosis(TLE-HS)is the most drug-resistant form of epilepsy,and it also impacts physical,mental,and psychological well-being of patients.Carum carvi extract has demonstrated anti-convulsant,anti-depressant,and anxiolytic properties.This study was designed to investigate if Carum carvi extract can alleviate depression and memory loss symptoms in a TLE-HS animal model.Methods:Male Sprague Dawley rats were used to create a model of TLE-HS and Carum carvi extract treatment,along with appropriate controls,was used to test the efficacy of this herbal extract in reducing the symptoms of depression and memory loss.Results:Forced swim test showed that Carum carvi extract treated TLE-HS rats resulted in significant improvement of the symptoms of depression.However,novel object recognition test showed that memory improvement did not occur.Conclusion:Depression significantly impacts the quality of life in TLE-HS patients,and this study has shown that Carum carvi extract should be explored further as an adjuvant treatment for TLE-HS patients to improve their quality of life.

The collaborative cross mouse for studying the effect of host genetic background on memory impairments due to obesity and diabetes

Background:Over the past few decades,a threefold increase in obesity and type 2 diabetes(T2D)has placed a heavy burden on the health-care system and society.Previous studies have shown correlations between obesity,T2D,and neurodegenera-tive diseases,including dementia.It is imperative to further understand the relation-ship between obesity,T2D,and cognitive deficits.Methods:This investigation tested and evaluated the cognitive impact of obesity and T2D induced by high-fat diet(HFD)and the effect of the host genetic background on the severity of cognitive decline caused by obesity and T2D in collaborative cross(CC)mice.The CC mice are a genetically diverse panel derived from eight inbred strains.Results:Our findings demonstrated significant variations in the recorded phenotypes across different CC lines compared to the reference mouse line,C57BL/6J.CC037 line exhibited a substantial increase in body weight on HFD,whereas line CC005 ex-hibited differing responses based on sex.Glucose tolerance tests revealed significant variations,with some lines like CC005 showing a marked increase in area under the curve(AUC)values on HFD.Organ weights,including brain,spleen,liver,and kidney,varied significantly among the lines and sexes in response to HFD.Behavioral tests using the Morris water maze indicated that cognitive performance was differentially affected by diet and genetic background.Conclusions:Our study establishes a foundation for future quantitative trait loci map-ping using CC lines and identifying genes underlying the comorbidity of Alzheimer's disease(AD),caused by obesity and T2D.The genetic components may offer new tools for early prediction and prevention.

Targeting vulnerable microcircuits in the ventral hippocampus of male transgenic mice to rescue Alzheimer‑like social memory loss

Background:Episodic memory loss is a prominent clinical manifestation of Alzheimer’s disease(AD),which is closely related to tau pathology and hippocampal impairment.Due to the heterogeneity of brain neurons,the specific roles of different brain neurons in terms of their sensitivity to tau accumulation and their contribution to AD-like social memory loss remain unclear.Therefore,further investigation is necessary.Methods:We investigated the effects of AD-like tau pathology by Tandem mass tag proteomic and phosphoproteomic analysis,social behavioural tests,hippocampal electrophysiology,immunofluorescence staining and in vivo optical fibre recording of GCaMP6f and iGABASnFR.Additionally,we utilized optogenetics and administered ursolic acid(UA)via oral gavage to examine the effects of these agents on social memory in mice.Results:The results of proteomic and phosphoproteomic analyses revealed the characteristics of ventral hippocampal CA1(vCA1)under both physiological conditions and AD-like tau pathology.As tau progressively accumulated,vCA1,especially its excitatory and parvalbumin(PV)neurons,were fully filled with mislocated and phosphorylated tau(p-Tau).This finding was not observed for dorsal hippocampal CA1(dCA1).The overexpression of human tau(hTau)in excitatory and PV neurons mimicked AD-like tau accumulation,significantly inhibited neuronal excitability and suppressed distinct discrimination-associated firings of these neurons within vCA1.Photoactivating excitatory and PV neurons in vCA1 at specific rhythms and time windows efficiently ameliorated tau-impaired social memory.Notably,1 month of UA administration efficiently decreased tau accumulation via autophagy in a transcription factor EB(TFEB)-dependent manner and restored the vCA1 microcircuit to ameliorate tau-impaired social memory.Conclusion:This study elucidated distinct protein and phosphoprotein networks between dCA1 and vCA1 and highlighted the susceptibility of the vCA1 microcircuit to AD-like tau accumulation.Notably,our novel findings regarding the efficacy of UA in reducing tau load and targeting the vCA1 microcircuit may provide a promising strategy for treating AD in the future.

Data-Driven Method for Predicting Remaining Useful Life of Bearings Based on Multi-Layer Perception Neural Network and Bidirectional Long Short-Term Memory Network

The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.

NMOS晶体管电荷共享导致的SRAM单元单粒子翻转恢复效应研究

基于Synopsys公司的三维器件模拟软件TCAD,本文研究了NMOS晶体管电荷共享导致SRAM单元的单粒子翻转恢复(SEUR)效应。分析了NMOS晶体管电荷共享导致SEUR效应的物理机制,系统研究了NMOS晶体管偏置(如电源电压、P阱偏置电压)和工艺参数(如P+深阱掺杂浓度、P阱接触距离)对线性能量传输翻转恢复阈值(LETrec)以及单粒子翻转脉冲宽度(PWrec)的影响。研究发现:PWrec随着电源电压的增大而增大;PWrec和LETrec随着P阱偏置电压的增大而减小;LETrec随着P+深阱掺杂浓度的增大而增大;PWrec随着P阱接触与NMOS晶体管之间距离的增大而增大,而LETrec随着P阱接触与NMOS晶体管之间距离增大而减小。本文研究结论有助于优化SRAM单元抗单粒子效应设计,尤其是基于SEUR效应的SRAM单元的抗辐照加固设计提供了理论指导。

A review on SRAM-based computing in-memory:Circuits,functions,and applications

Artificial intelligence(AI)processes data-centric applications with minimal effort.However,it poses new challenges to system design in terms of computational speed and energy efficiency.The traditional von Neumann architecture cannot meet the requirements of heavily datacentric applications due to the separation of computation and storage.The emergence of computing inmemory(CIM)is significant in circumventing the von Neumann bottleneck.A commercialized memory architecture,static random-access memory(SRAM),is fast and robust,consumes less power,and is compatible with state-of-the-art technology.This study investigates the research progress of SRAM-based CIM technology in three levels:circuit,function,and application.It also outlines the problems,challenges,and prospects of SRAM-based CIM macros.

A Low Power SRAM/SOI Memory Cell Design

A modified four transistor （4T） self-body-bias structured SRAM/SOI memory cell is proposed. The structure is designed and its parameters are obtained by performance simulation and analysis with TSUPREM4 and MEDICI.The structure saves area and its process is simplified by using the body resistor with buried p^＋ channel beneath the nMOS gate instead of the pMOS of 6T CMOS SRAM. Furthermore, this structure can operate safely with a 0.5V supply voltage, which may be prevalent in the near future. Finally, compared to conventional 6T CMOS SRAM,this structure＇s transient responses are normal and its power dissipation is 10 times smaller.

Virtex-5系列SRAM型FPGA单粒子效应重离子辐照试验技术研究

针对SRAM型FPGA在空间辐射环境下易发生单粒子效应,影响星载设备正常工作甚至导致功能中断的问题,开展了SRAM型FPGA单粒子效应地面辐照试验方法研究,提出了配置存储器(CRAM)和块存储器(BRAM)的单粒子翻转效应测试方法,并以Xilinx公司工业级Virtex-5系列SRAM型FPGA为测试对象,设计了单粒子效应测试系统,开展了重离子辐照试验,获取了器件的单粒子闩锁试验数据和CRAM、BRAM以及典型用户电路三模冗余前后的单粒子翻转试验数据;最后利用空间环境模拟软件进行了在轨翻转率分析,基于CREME96模型计算得到XC5VFX130T器件配置存储器GEO轨道的单粒子翻转概率为6.41×10^(-7)次/比特·天。

基于SRAM和NVM的存内计算技术综述

集存储与计算于一身的快速低功耗存内计算架构,突破了存储与计算分离的传统冯·诺依曼体系,解决了限制处理器算力的“内存墙”问题,成为新型计算架构的研究热点.存内计算的基础器件包括高速且工艺成熟的静态随机存取存储器(static RAM,SRAM)、低功耗高响应且非易失的忆阻器(memristor)、高密度低静态功耗非易失的磁性随机存取存储器(magnetic RAM,MRAM).研究者们基于上述器件完成大量存内计算研究,但是关于这些存内计算架构全面且系统总结的文献综述仍然缺失.首先从SRAM、忆阻器、MRAM方向出发概述了不同器件的存内计算原理、当前存内计算架构发展状况和实际应用场景等.然后针对当前存内计算架构存在的各种问题和挑战给出了现有解决方案和未来解决方向.最后对基于以上器件的存内计算研究重点进行了总结并概述了目前的研究短板、展望未来的发展方向.

基于数据残留时间的SRAM-PUF预选算法

静态随机存取存储器(Static Random-Access Memory,SRAM)物理不可克隆函数(Physical Unclonable Function,PUF)利用参数设计完全相同的晶体管在制造过程中存在的工艺偏差,生成每块芯片无法克隆的密钥响应.由于SRAM-PUF内部错误分布的随机性,密钥重构需要使用纠错码,而纠错电路的面积与其纠错能力呈正相关,为了降低SRAM-PUF错误分布,减小纠错电路面积,本文通过对SRAM数据残留特性的研究,提出一种数据残留预选算法,对SRAM单元进行筛选,提高PUF响应稳定性,使用区块择优算法筛选SRAM区块,减小响应的分散度,以更短的时间和资源消耗生成SRAM-PUF响应,测试结果表明,在不同温度(-40℃~80℃)和±10%电压波动下,256位SRAM-PUF响应拥有99.8%的稳定性及1.9×10^(-8)的误码率,相对于通用的临时多数表决(Temporal Majority Voting,TMV)算法提升了1.7%的稳定性,降低2.1×10^(5)倍误码率,与1000次TMV相比,时间复杂度从O(2000n)线性降低到O(900n).经过72小时老化测试后,采用数据残留算法预选的SRAM-PUF稳定性仅下降0.2%.

一种同步流水线SRAM读写控制模型

设计了一种同步流水线静态随机存储器读写控制系统的行为级模型。分析了存储器芯片的控制信号和工作时序要求,利用Verilog硬件描述语言对存储器芯片的读写系统进行了行为级建模。系统包括主机、总控制器和存储器三部分,其中总控制器又包括信号源发生器和数据收发控制器两个子模块。利用Modelsim软件对系统行为级模型进行了仿真验证,结果表明系统控制模型在非猝发(常规)、线性猝发、交织猝发三种工作模式下均可对存储器进行正确读写操作。该模型将主机端源控制信号数量减至最少,极大简化了读写控制流程;采用系统时钟双沿对数据采样传输,提升了系统的稳定性。

双埋氧绝缘体上硅SRAM铀离子单粒子效应研究

随着集成电路技术的进步,提高电路的单粒子翻转(single event upset,SEU)阈值变得愈发困难。双埋氧层绝缘体上硅(double silicon-on-insulator,DSOI)技术为单粒子加固技术提供了新方法。利用哈尔滨工业大学空间地面模拟装置(space environment simulation and research infrastructure,SESRI)产生的铀离子对中国科学院微电子研究所研制的DSOI静态随机存取存储器(static random access memory,SRAM)开展了SEU效应研究。铀离子是目前可获得的线性能量传递(linear energy transfer,LET)最高的重离子。2种不同SEU加固能力的DSOI 4 kbit SRAM试验结果显示,通过对NMOS和PMOS的背栅实施独立偏压控制,可实现DSOI SRAM电路抗SEU能力的宽范围调制。最优条件下,使用LET为118 MeV·cm ^(2)·mg^(-1)的铀离子,累积注量为1×10^(7) cm^(-2)时,被测器件无SEU发生。

基于Back-n白光中子实验装置的SRAM翻转截面测量

本文主要研究静态随机存取存储器(static random-access memory,SRAM)的单粒子效应翻转截面的测量方法。基于宽能谱白光中子束流,采用了一种操作更方便的SRAM翻转截面测量方法。在SRAM前面放置聚乙烯中子慢化材料改变入射到SRAM表面上的中子能谱,利用模拟计算得到改变后的中子能谱。利用奇异值分解法求解翻转率的矩阵方程得到SRAM的翻转截面。结果表明在4~15 MeV的能量范围内,使用反角白光中子源测试的SRAM翻转截面信息和参考文献中使用单能中子源测试拟合的SRAM翻转截面信息基本吻合。

Fabrication and integration of photonic devices for phase-change memory and neuromorphic computing

In the past decade,there has been tremendous progress in integrating chalcogenide phase-change materials(PCMs)on the silicon photonic platform for non-volatile memory to neuromorphic in-memory computing applications.In particular,these non von Neumann computational elements and systems benefit from mass manufacturing of silicon photonic integrated circuits(PICs)on 8-inch wafers using a 130 nm complementary metal-oxide semiconductor line.Chip manufacturing based on deep-ultraviolet lithography and electron-beam lithography enables rapid prototyping of PICs,which can be integrated with high-quality PCMs based on the wafer-scale sputtering technique as a back-end-of-line process.In this article,we present an overview of recent advances in waveguide integrated PCM memory cells,functional devices,and neuromorphic systems,with an emphasis on fabrication and integration processes to attain state-of-the-art device performance.After a short overview of PCM based photonic devices,we discuss the materials properties of the functional layer as well as the progress on the light guiding layer,namely,the silicon and germanium waveguide platforms.Next,we discuss the cleanroom fabrication flow of waveguide devices integrated with thin films and nanowires,silicon waveguides and plasmonic microheaters for the electrothermal switching of PCMs and mixed-mode operation.Finally,the fabrication of photonic and photonic–electronic neuromorphic computing systems is reviewed.These systems consist of arrays of PCM memory elements for associative learning,matrix-vector multiplication,and pattern recognition.With large-scale integration,the neuromorphic photonic computing paradigm holds the promise to outperform digital electronic accelerators by taking the advantages of ultra-high bandwidth,high speed,and energy-efficient operation in running machine learning algorithms.