Search

In recent years, open-source RISC-V microprocessors represented by Hummingbird E203 have received widespread attention and application in both academia and industry due to their low power consumption and good performance. To improve the performance of microprocessors and reduce pipeline stalls caused by branch instructions, branch prediction technology has become one of the important techniques widely used in modern microprocessors. However, the branch predictor currently used in the Hummingbird E203 is a lightweight static branch predictor, facing the challenge of low branch prediction accuracy. Since using a dynamic branch predictor with higher prediction accuracy can further reduce the overhead caused by mispredictions leading to redirecting fetching, various implementations of dynamic branch predictors have been explored based on the original microarchitecture to improve branch prediction accuracy while considering resource overhead. Experimental results show that among various dynamic branch predictors, the one achieving the best results is the adaptive dynamic branch predictor combining static branch prediction with Branch History Register (BHR). On the Dhrystone benchmark program, its branch prediction accuracy can be increased from the original 84.6% to 94.8%, and the score from 1.296 463 to 1.314 418. On the Coremark benchmark program, its branch prediction accuracy can be increased from the original 67% to 78.7%, and the score from 2.120 000 to 2.138 008. [ABSTRACT FROM AUTHOR]

Covert channels based on processor microarchitecture have become a major threat to modern processors by bypassing existing security detection to transmit or leak secrets. Based on the storage time of covert channels, this paper divides microarchitecture-based covert channels into two types: persistent covert channels and volatile covert channels. The principle of the attack, runtime characteristics, typical attacks and attack conditions of the two types of covert channels are introduced and the existing covert channels are evaluated by the existing metrics. Based on the analysis of the attack conditions, a new analysis method on how to find the potential covert channel in microprocessor resources is proposed, and the microprocessor resources that are not used by existing covert channels are analyzed. The analysis shows that, the front-end bus in the Intel processors meets the conditions for creating a new transient covert channel. Based on the working principle of microarchitecture-based covert channel, many strategies of protection and detection methods have been proposed, and they are classified according to the working principles. The working principle, existing strategies and application scope of each type are introduced in detail. Moreover, reasonable and feasible protection suggestions are proposed for potential microarchitecture-based covert channels that may exist in the future. [ABSTRACT FROM AUTHOR]

Objective: To assess the regional variation of microarchitecture and biomechanical parameters in vertebral cancellous bone. And to provide references to how to chose the appropriate region of interest of cancellous bone in the studies of vertebral cancellous bone. Methods: 6 human C5 bodies samples were scanned by micro-CT to get 3 dimensional images. The region of cancellous bone in the vertebral body were divided into 6 regions: lateral and medial, anterior and posterior, superior and inferior. The measurement of microarchitectural parameters, finite element analysis, and calculation of biomechanical parameters were performed in all those regions. All those parameters were compared between lateral and medial, anterior and posterior, superior and inferior regions. Results:The microarchitectural parameters(such as BV/TV, Tb.Th, Tb.N) and apparent elastic modulus between superior and inferior regions were significantly different (P<0.05). There were no significant differences of microarchitectural parameters(such as BV/TV, Tb.Th, Tb.N) and apparent elastic modulus between anterior and posterior regions, also between lateral and medial regions. The apparent elastic modulus between lateral and medial regions were significantly different along the secondary directions (lateral to medial direction, and anterior to posterior direction)(P<0.05), but along superior and inferior direction were same. Conclusions: When acquiring cancellous bone specimens from vertebrae or use high-resolution CT to assess vertebral structure, the region of interest should include superior and inferior regions at the same time. [ABSTRACT FROM AUTHOR]

Objective: To investigate the dynamic changes of bone microarchitecture in the lumbar vertebrae of ovariectomized osteoporostic rats. Methods: 90 healthy 3-months old female SD rats were randomly divided into the following three groups by body weight: baseline(base), sham-operation(Sham), and ovariectomized(OVX) groups. Before the surgical operation and 3, 6, 12 or 24 weeks after operation, respectively, the trabecular bone microarchitecture of the fifth lumbar vertebrae was detected by micro-CT in vitro.Results: At 3 weeks after operation, there were no significant differences in all detected parameters between the sham group and OVX group. At 6 weeks after operation, only the thickness of trabecular bone(Tb.Th) in the OVX group was significantly decreased compared with that of the sham group(P<0.05). From the 12 th to 24 th week after operation, the volume bone mineral density(v BMD), the fraction of bone tissues(BV/TV), the Tb.Th, and the number of trabecular bone(Tb.N) in the OVX group were significantly decreased compared with those of the sham group(P<0.05) while the separation of trabecular bone(Tb.Sp) and the bone structure index(SMI) were significantly increased(P<0.05). Conclusions: At 6 weeks after ovariectomy, the Tb.Th in the rat fifth lumbar trabeculae became thin. At12 weeks after operation, the v BMD and the BV/TV was decreased and the Tb.N reduced. [ABSTRACT FROM AUTHOR]

Bone mineral density （BMD） measurement using dual energy X-ray absorptiometry （DXA） has been widely accepted as a clinical method to diagnose osteoporosis．However， more and more basic and clinical studies have indicated that the variance of cancellous bone strength cannot be fully attributed to the reduction of BMD．Many experiments about microarchitecture of cancellous bone have revealed that cancellous bone strength is determined by BMD， bone architecture and other parameters．The microarchitecture of the bone is a decisive parameter independent of BMD．It is important to study the relationship between microarchitecture and bone strength of cancellous bone in order to understand the development and diagnosis of osteoporosis．Based on literature review， we summarize that the most related parameters between microarchitecture and bone strength are BV ／TV， Tb． N， connectivity， degree of Anisotropy， and structure model index．Meanwhile， the clinical application of the research results on high resolution CT is also summarized． [ABSTRACT FROM AUTHOR]