DSP Specification Using the Silage Language

Genin, D.; Hilfinger, Paul; Rabaey, Jan M.; Scheers, C.; Man, H. De

doi:10.1007/978-1-4615-3570-6_15

Cited by 39 publications

(12 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CoWare hardware-software codesign environment [1] employs a data model that allows the user to specify, simulate and produce heterogeneous implementations from heterogeneous specification source models. The specific synchronous dataflow (SDF) type of DSP applications is implemented into hardware using languages such as SILAGE [2], DFL [3], and LUSTRE [4,5], The advantage of this type of designs is that they can be scheduled at compile time and the execution of the compiled code can be two orders of magnitude faster than eventdriven VHDL (e.g. RTL) simulations.…”

Section: Related Workmentioning

confidence: 99%

Seamless Signal Processing Block Implementation Using the Cubed-C Design Environment

Dossis¹

2017

IRATJ

View full text Add to dashboard Cite

Design environments and automated CAD systems are proliferated nowadays with various preferences and restrictions in their work environments. One serious problem of automated high-level synthesis tools is their inability of at least difficulty to use for low, bit level functions such as signal processing blocks. Here the Cubed-C environment is used for the rapid implementation of a number of low level functions and blocks such as UARTs without difficulty. Cubed-C is a full-strength high-level synthesis CAD system; nevertheless, its structure and properties make it particularly suitable for this type of fine-grained applications. The experiments in this paper prove that the Cubed-C synthesis tools are particularly suitable for both complex and for low, bit level signal coding functions.

show abstract

Section: Related Workmentioning

confidence: 99%

Seamless Signal Processing Block Implementation Using the Cubed-C Design Environment

Dossis¹

2017

IRATJ

View full text Add to dashboard Cite

show abstract

“…For instance, the polytope has the projection , but none of the points (0, 1, 2, 3) is the projection of a lattice point in the polytope. 10 These invalid projections are detected easily. It is sufficient to replace the coordinates of the projection point in the polytope and to check whether the resulting -dimensional integer polytope is empty or not.…”

Section: A) Ifmentioning

confidence: 99%

“…The computation of the scalars covered by the array reference , defined within the second loop nest 1 in the illustrative Silage [10] example of Fig. 1(a), requires as operands signals covered by the array references and , residing in the regions indicated in Fig.…”

mentioning

confidence: 99%

“…The size of the index space corresponding to the array reference is, however, 16, therefore, 12 times less than the approximation. The error is due both to the incorrect evaluation of the iterator space size, which contains 72 points rather than 192 and to the fact that the affine mapping is not injective [e.g., signal is addressed by several pairs of iterators : (8,4), (9,3), (10,2)]. Concluding, for the general affine case, the approximation mentioned above may be very crude, being improper to use for memory estimation/allocation as it can lead to an exaggerated number of storage locations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Practical solutions for counting scalars and dependences in ATOMIUM-a memory management system for multidimensional signal processing

Balasa

Catthoor

Man

1997

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

Abstract-Image and video processing applications involve large multidimensional signals which have to be stored in memory modules. In application-specific architectures for real-time multidimensional signal processing, a significant cost in terms of chip area and power consumption is due to these background memory units. The multidimensional signals are usually modeled in behavioral descriptions with array variables. In the algorithmic specifications of our target applications, many of the array references cover large amounts of scalars. Therefore, the efficient handling of array references in the specifications for image and video processing is crucial for obtaining low cost memory allocation solutions. This paper addresses a central problem which arises when handling the array variables in behavioral specifications: the computation of the number of scalars covered by an array reference. This problem is closely related to the computation of dependences in data-flow analysis. The novel algorithms proposed in this paper are embedded in the ATOMIUM environment-a memory management system for multidimensional signal processing.Index Terms-Data dependence, data-flow analysis, digital signal processing (DSP), linearly bounded lattice, polytope.

show abstract

“…This paper describes a new memory estimation technique for DSP applications written in the applicative language SILAGE, [1] [2]. SILAGE is a data flow language, which is a natural way to describe the flow of computations in DSP applications.…”

Section: Introductionmentioning

confidence: 99%

Memory estimation for high level synthesis

Verbauwhede

Scheers

Rabaey

1994

Proceedings of the 31st Annual Conference on Design Automation Conference - DAC '94

View full text Add to dashboard Cite

--This paper describes a new memory estimation technique for DSP applications written in an applicative language. Since no concept of storage is present in an applicative language, the compiler has to derive the memory needs. For each array, the number of storage locations is estimated by modelling both, the dependencies and the sequence of execution. For this, an arrayspecific production time axis is created and the current production date is compared with the production date of the consumed signal. It is formulated as an integer linear problem.

show abstract

DSP Specification Using the Silage Language

Cited by 39 publications

References 1 publication

Seamless Signal Processing Block Implementation Using the Cubed-C Design Environment

Seamless Signal Processing Block Implementation Using the Cubed-C Design Environment

Practical solutions for counting scalars and dependences in ATOMIUM-a memory management system for multidimensional signal processing

Memory estimation for high level synthesis

Contact Info

Product

Resources

About