Systolic implementation of multiplication over GF(2m) is usually very efficient in area-time complexity,but its latency is usually very large.Thus,two low latency systolic multipliers over GF(2m) based on general irre...Systolic implementation of multiplication over GF(2m) is usually very efficient in area-time complexity,but its latency is usually very large.Thus,two low latency systolic multipliers over GF(2m) based on general irreducible polynomials and irreducible pentanomials are presented.First,a signal flow graph(SFG) is used to represent the algorithm for multiplication over GF(2m).Then,the two low latency systolic structures for multiplications over GF(2m) based on general irreducible polynomials and pentanomials are presented from the SFG by suitable cut-set retiming,respectively.Analysis indicates that the proposed two low latency designs involve at least one-third less area-delay product when compared with the existing designs,To the authors' knowledge,the time-complexity of the structures is the lowest found in literature for systolic GF(2m) multipliers based on general irreducible polynomials and pentanomials.The proposed low latency designs are regular and modular,and therefore they are suitable for many time critical applications.展开更多
In this paper,the discontinuous Galerkin(DG)method combined with localized artificial diffusivity is investigated in the context of numerical simulation of broadband compressible turbulent flows with shocks for under-...In this paper,the discontinuous Galerkin(DG)method combined with localized artificial diffusivity is investigated in the context of numerical simulation of broadband compressible turbulent flows with shocks for under-resolved cases.Firstly,the spectral property of the DG method is analyzed using the approximate dispersion relation(ADR)method and compared with typical finite difference methods,which reveals quantitatively that significantly less grid points can be used with DG for comparable numerical error.Then several typical test cases relevant to problems of compressible turbulence are simulated,including one-dimensional shock/entropy wave interaction,two-dimensional decaying isotropic turbulence,and two-dimensional temporal mixing layers.Numerical results indicate that higher numerical accuracy can be achieved on the same number of degrees of freedom with DG than high order finite difference schemes.Furthermore,shocks are also well captured using the localized artificial diffusivity method.The results in this work can provide useful guidance for further applications of DG to direct and large eddy simulation of compressible turbulent flows.展开更多
基金Project(61174132) supported by the National Natural Science Foundation of ChinaProject(09JJ6098) supported by the Natural Science Foundation of Hunan Province,China
文摘Systolic implementation of multiplication over GF(2m) is usually very efficient in area-time complexity,but its latency is usually very large.Thus,two low latency systolic multipliers over GF(2m) based on general irreducible polynomials and irreducible pentanomials are presented.First,a signal flow graph(SFG) is used to represent the algorithm for multiplication over GF(2m).Then,the two low latency systolic structures for multiplications over GF(2m) based on general irreducible polynomials and pentanomials are presented from the SFG by suitable cut-set retiming,respectively.Analysis indicates that the proposed two low latency designs involve at least one-third less area-delay product when compared with the existing designs,To the authors' knowledge,the time-complexity of the structures is the lowest found in literature for systolic GF(2m) multipliers based on general irreducible polynomials and pentanomials.The proposed low latency designs are regular and modular,and therefore they are suitable for many time critical applications.
基金supported by the National Basic Research Program of China(Grant No.2009CB724104)
文摘In this paper,the discontinuous Galerkin(DG)method combined with localized artificial diffusivity is investigated in the context of numerical simulation of broadband compressible turbulent flows with shocks for under-resolved cases.Firstly,the spectral property of the DG method is analyzed using the approximate dispersion relation(ADR)method and compared with typical finite difference methods,which reveals quantitatively that significantly less grid points can be used with DG for comparable numerical error.Then several typical test cases relevant to problems of compressible turbulence are simulated,including one-dimensional shock/entropy wave interaction,two-dimensional decaying isotropic turbulence,and two-dimensional temporal mixing layers.Numerical results indicate that higher numerical accuracy can be achieved on the same number of degrees of freedom with DG than high order finite difference schemes.Furthermore,shocks are also well captured using the localized artificial diffusivity method.The results in this work can provide useful guidance for further applications of DG to direct and large eddy simulation of compressible turbulent flows.
