When implementing SPMD programs on multi core platforms, whole function vectorization is an important optimization method. SPMD program has drawback that lots of instructions across multi threads are redundant which i...
详细信息
When implementing SPMD programs on multi core platforms, whole function vectorization is an important optimization method. SPMD program has drawback that lots of instructions across multi threads are redundant which is sustained in vectorization. This paper proposes to alleviate this overhead by detecting scalar operations and extract them out in vectorization instructions. An algorithm is designed to deal with control flow and data flow synchronously in which convergent and invariance analysis is employed to statically identify convergent execution and invariant values or instructions. Our algorithm is effectively on implementing SPMD programs on multi core platforms. The experiments show our method could improve the execution efficiency by 13.3%.
Traditional multicast protocol forms multicast trees rooted at different sources to forward packets. If the multicast sources and receivers are in different domains, these trees will produce a great number of multicas...
详细信息
Traditional multicast protocol forms multicast trees rooted at different sources to forward packets. If the multicast sources and receivers are in different domains, these trees will produce a great number of multicast states in the backbone, resulting in poor scalability. Therefore, we propose a one Wide-Sense Circuit Tree per Traffic Class based inter-domain multicast (WSCT-TC), in which a Wide-Sense Circuit Tree (WSCT) is established for a class of multicast traffic. The WSCT is established in the backbone, along which multicast packets are forwarded by label switching. The spec of WSCT can be reconfigured according to the QoS (Quality of Service) requirement of multicast applications, to provide preferable QoS. Simulating experiment shows that WSCT-TC behaves better scalability.
Integrating a large number of simple cores on the chip to provide the desired performance and throughput, microprocessor has entered the many core era. In order to fully extract the ability of the many core processor,...
详细信息
ISBN:
(纸本)9781479952465
Integrating a large number of simple cores on the chip to provide the desired performance and throughput, microprocessor has entered the many core era. In order to fully extract the ability of the many core processor, we propose speedup models for many core architecture in this paper. Under the assumption of Hill-Marty model, we deduce our formulas based on Gustafson's Law and Sun-Ni's Law. Then, compared with the Hill-Marty model, we theoretically analyze the best allocation under the given resources. Furthermore, we apply the conclusions of our models to evaluate current many core processors and predict concrete future architecture. Our results show that the many core architecture is capable of extensive scalability and being beneficial to promote the performance, especially heterogeneous one. By using simple analytical models, we provide a better understanding of architecture design and our work complement existing studies.
Measurements of ZZ production in the ℓ+ℓ−ℓ′+ℓ′− channel in proton–proton collisions at 13 TeV center-of-mass energy at the Large Hadron Collider are presented. The data correspond to 36.1 fb−1 of collisions collec...
详细信息
Measurements of ZZ production in the ℓ+ℓ−ℓ′+ℓ′− channel in proton–proton collisions at 13 TeV center-of-mass energy at the Large Hadron Collider are presented. The data correspond to 36.1 fb−1 of collisions collected by the ATLAS experiment in 2015 and 2016. Here ℓ and ℓ′ stand for electrons or muons. Integrated and differential ZZ→ℓ+ℓ−ℓ′+ℓ′− cross sections with Z→ℓ+ℓ− candidate masses in the range of 66 GeV to 116 GeV are measured in a fiducial phase space corresponding to the detector acceptance and corrected for detector effects. The differential cross sections are presented in bins of twenty observables, including several that describe the jet activity. The integrated cross section is also extrapolated to a total phase space and to all standard model decays of Z bosons with mass between 66 GeV and 116 GeV, resulting in a value of 17.3±0.9[±0.6(stat)±0.5(syst)±0.6(lumi)] pb. The measurements are found to be in good agreement with the standard model. A search for neutral triple gauge couplings is performed using the transverse momentum distribution of the leading Z boson candidate. No evidence for such couplings is found and exclusion limits are set on their parameters.
For the first time, the γ decay of excited states has been observed in a nucleus situated in the quadrant south-east of doubly magic Sn132, a region in which experimental information so far is limited to ground-state...
详细信息
For the first time, the γ decay of excited states has been observed in a nucleus situated in the quadrant south-east of doubly magic Sn132, a region in which experimental information so far is limited to ground-state properties. Six γ rays with energies of 50, 86, 103, 227, 357, and 602 keV were observed following the β-delayed neutron emission from Cd85133, populated in the projectile fission of a U238 beam at the Radioactive Isotope Beam Factory at RIKEN within the EURICA project. The new experimental information is compared to the results of a modern realistic shell-model calculation, the first one in this region very far from stability, focusing in particular on the π0g9/2−1⊗ν1f7/2 particle-hole multiplet in In83132. In addition, theoretical estimates based on a scaling of the two-body matrix elements for the πh11/2−1⊗νg9/2 analog multiplet in Tl127208, one major proton and one major neutron shell above, are presented.
For steganalysis of F5-like steganography with two types of widely used joint distribution statistical features: co-occurrence matrix and Markov transition probability matrix, a feature selection and fusion method bas...
详细信息
Double-layered STC (syndrome trellis code) is the most popular method for minimizing the distortion of ± 1 steganography. However, it is a probabilistic algorithm which may fail in the embedding process on some g...
详细信息
Double-layered STC (syndrome trellis code) is the most popular method for minimizing the distortion of ± 1 steganography. However, it is a probabilistic algorithm which may fail in the embedding process on some given profiles. Another characteristic of double-layered STC is the high computational complexity. Starting from these two points, we propose a dynamic distortion model defined in a pixel chain in this paper. The dynamic distortion model is working on a principle that the SLSB (second least significant bit) of current pixel is used to control the LSB (least significant bit) of the next pixel. So the distortion of some pixels may be adjusted to zero by this means. We apply STC to fit the dynamic distortion model and get a novel method for ± 1 steganography. Comparing with the double-layered STC, the experiment result shows that the proposed method has comparable ability for minimizing distortion with significantly improved embedding speed. And this novel method avoids failure in the embedding process. Considering the advantages together, the method is more suitable for steganography systems and software in practical environment.
At present,the research on reverse analysis of encrypting and decrypting process pays more attention to cryptographic algorithms *** is no mature theory or tools for the entire process analysis of encryption and *** o...
详细信息
At present,the research on reverse analysis of encrypting and decrypting process pays more attention to cryptographic algorithms *** is no mature theory or tools for the entire process analysis of encryption and *** order to solve the problem efficiently,this paper discusses encryption and decryption process dependency graphs,summarizes the existing research results about the cryptographic algorithms recognition technology,and explores a way to research the process analysis of encryption and decryption based on process dependency ***,the result on an example reveals the entire process analysis of encryption and decryption.
Instrumentation is an important mechanism to collect run-time information of applications for further analysis like bottleneck analysis, hotspot analysis and even bug detection and revision. Currently there are lots o...
详细信息
Aiming at the function disable Energy-saving hardware Trojan detection application requirements, has resarech the Energy-saving hardware Trojan generation principle and the trigger mechanism deeply, gives the function...
详细信息
暂无评论