Memory size estimation for multimedia applications

Grun, Peter; Balasa, Florin; Dutt, Nikil

doi:10.1109/hsc.1998.666252

Cited by 31 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that in contrast to other works [4], [9], [11], [12], [18] that require the loop bounds to be known constants, we derive closed-form expressions for the minimum memory size as a function of the loop bounds and dependence vectors. We consider the cases where the dimension of the array accessed within the loop is the same as the nest level and where the dimensionality is less than the loop nesting level.…”

Section: Example 1(a)mentioning

confidence: 99%

“…Some early approaches in high-level synthesis that dealt with minimum register allocation for scalars [8] can be extended to arrays by treating each array element as a separate scalar; such an approach is highly expensive. Researchers from IMEC [1], [4], [11], [12], Grun et al [9], and Zhao and Malik [18] present techniques that estimate the minimum amount of memory required. Of these [11], [12] allow the user to specify an arbitrary execution ordering, Balasa et al [1] ignores execution ordering, while the rest of the works assume a fixed sequential execution ordering.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, we present a technique that reduces the amount of memory required through the use of loop-level transformations. See the section on related work for a comparison of our approach to those in other works [4], [9], [11], [12], [18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimating and reducing the memory requirements of signal processing codes for embedded systems

Ramanujam

Hong

Kandemir³

et al. 2006

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Abstract-Most embedded systems have limited amount of memory. In contrast, the memory requirements of the DSP and video processing codes (in nested loops, in particular) running on embedded systems is significant. This paper addresses the problem of estimating and reducing the amount of memory needed for transfers of data in embedded systems. First, the problem of estimating the region associated with a statement or the set of elements referenced by a statement during the execution of nested loops is analyzed. For a fixed execution ordering, a quantitative analysis of the number of elements referenced is presented; exact expressions for uniformly generated references and a close upper and lower bound for non-uniformly generated references are derived. Second, in addition to presenting an algorithm that computes the total memory required, this paper also discusses the effect of transformations (that change the execution ordering) on the lifetimes of array variables, i.e., the time between the first and last accesses to a given array location. The term maximum window size is introduced and quantitative expressions are derived to compute the maximum window size. A detailed analysis of the effect of unimodular transformations on data locality including the calculation of the maximum window size is presented.

show abstract

Section: Example 1(a)mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Estimating and reducing the memory requirements of signal processing codes for embedded systems

Ramanujam

Hong

Kandemir³

et al. 2006

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Grun et al use the data-dependency relations between the array references in the code to find the number of array elements produced or consumed by each assignment [11]. The storage requirement at the end of a loop equals the storage requirement at the beginning of the loop, plus the number of elements produced within the loop, minus the number of elements consumed within the loop.…”

mentioning

confidence: 99%

“…The typical assumption int A [7][4], B [9][5], C [11][6], D [13] [7] ; for ( i=0; i<=6; i++ ) // 1st loop nest for ( j=0; j<=3; j++ )…”

mentioning

confidence: 99%

Computation of the minimum data storage and applications in memory management for multimedia signal processing

Luican

Zhu

Balasa

2008

ICA

View full text Add to dashboard Cite

Abstract. The amount of the data storage in signal processing systems, whose behavior is described by loop-organized algorithmic specifications, has an important impact on the overall energy consumption, chip area, as well as system performance. This paper presents a methodology based on lattices [25] which can be used to address several memory management tasks for applications with high-level specifications, where the main data structures are multidimensional arrays. This methodology was used in the past for the exact computation of the minimum data storage in applications with procedural, affine specifications [2]. The paper discusses two applications of that technique in the memory management of data-dominated signal processing systems: (1) the evaluation of the impact of loop transformations on the data storage, and (2) the assessment and efficient implementation of models of mapping multidimensional signals into the physical memory.

show abstract

Guidance of Loop Ordering for Reduced Memory Usage in Signal Processing Applications

Kjeldsberg

Catthoor

Verdoolaege

et al. 2008

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

Data dominated signal processing applications are typically described using large and multidimensional arrays and loop nests. The order of production and consumption of array elements in these loop nests has huge impact on the amount of memory required during execution. This is essential since the size and complexity of the memory hierarchy is the dominating factor for power, performance and chip size in these applications. This paper presents a number of guiding principles for the ordering of the dimensions in the loop nests. They enable the designer, or design tools, to find the optimal ordering of loop nest dimensions for individual data dependencies in the code. We prove the validity of the guiding principles when no prior restrictions are given regarding fixation of dimensions. If some dimensions are already fixed at given nest levels, this is taken into account when fixing the remaining dimensions. In most cases an optimal ordering is found for this situation as well. The guiding principles can be used in the early design phases in order to enable minimization of the memory requirement through in-place mapping. We use real life examples to show how they can be applied to reach a cost optimized end product. The results show orders of magnitude improvement in memory requirement compared to using the declared array sizes, and similar penalties for choosing the suboptimal ordering of loops when in-place mapping is exploited. AbbreviationsDP dependency part LR length ratio DV dependency vector ND nonspanning dimension DVP dependency vector polytope SD spanning dimension ID iteration domain UB upper bound LB lower bound 302 P.G. Kjeldsberg et al.

show abstract

Memory size estimation for multimedia applications

Cited by 31 publications

References 10 publications

Estimating and reducing the memory requirements of signal processing codes for embedded systems

Estimating and reducing the memory requirements of signal processing codes for embedded systems

Computation of the minimum data storage and applications in memory management for multimedia signal processing

Guidance of Loop Ordering for Reduced Memory Usage in Signal Processing Applications

Contact Info

Product

Resources

About