Bert Molenkamp

Streaming Reduction Circuit

Reduction circuits are used to reduce rows of floating point values to single values. Binary floating point operators often have deep pipelines, which may cause hazards when many consecutive rows have to be reduced. We present an algorithm by which any number of consecutive rows of arbitrary lengths can be reduced by a pipelined commutative and associative binary operator in an efficient manner. The algorithm is simple to implement, has a low latency, produces results in-order, and requires only small buffers. Besides, it uses only a single pipeline for the involved operation. The complexity of the algorithm depends on the depth of the pipeline, not on the length of the input rows. In this paper we discuss an implementation of this algorithm and we prove its correctness.

A transformational approach to VHDL and CDFG based high-level synthesis: a case study

In this paper, a novel multi-target design methodology based on the concepts of transformational design, and its application to the interlaced-to-progressive scan conversion (IPSC) problem, are discussed. Starting from a single high-level behavioral specification in VHDL a direction detector used in IPSC algorithms is mapped onto both a custom implementation and a programmable video signal processor. Results are compared with those previously obtained using different tools and methodologies.

Sabrewing: A lightweight architecture for combined floating-point and integer arithmetic

In spite of the fact that floating-point arithmetic is costly in terms of silicon area, the joint design of hardware for floating-point and integer arithmetic is seldom considered. While components like multipliers and adders can potentially be shared, floating-point and integer units in contemporary processors are practically disjoint. This work presents a new architecture which tightly integrates floating-point and integer arithmetic in a single datapath. It is mainly intended for use in low-power embedded digital signal processors and therefore the following design constraints were important: limited use of pipelining for the convenience of the compiler; maintaining compatibility with existing technology; minimal area and power consumption for applicability in embedded systems. The architecture is tailored to digital signal processing by combining floating-point fused multiply-add and integer multiply-accumulate. It could be deployed in a multi-core system-on-chip designed to support applications with and without dominance of floating-point calculations. The VHDL structural description of this architecture is available for download under BSD license. Besides being configurable at design time, it has been thoroughly checked for IEEE-754 compliance by means of a floating-point test suite originating from the IBM Research Labs. A proof-of-concept has also been implemented using STMicroelectronics 65nm technology. This prototype supports 32-bit signed twos complement integers and 41-bit (8-bit exponent and 32-bit significand) floating-point numbers. Our evaluations show that over 67% energy and 19% area can be saved compared to a reference design in which floating-point and integer arithmetic are implemented separately. The area overhead caused by combining floating-point and integer is less than 5%. Implemented in STs general-purpose CMOS technology, the design can operate at a frequency of 1.35GHz, while 667MHz can be achieved in low-power CMOS. Considering that the entire datapath is partitioned in just three pipeline stages, and the fact that the design is intended for use in the low-power domain, these frequencies are adequate. They are in fact competitive with current technology low-power floating-point units. Post-layout estimates indicate that the required area of a low-power implementation can be as small as 0.04mm2. Power consumption is on the order of several milliwatts. Strengthened by the fact that clock gating could reduce power consumption even further, we think that a shared floating-point and integer architecture is a good choice for signal processing in low-power embedded systems.

On hardware for generating routes in Kautz digraphs

In this paper we present a hardware implementation of an algorithm for generating node disjoint routes in a Kautz network. Kautz networks are based on a family of digraphs described by W.H. Kautz[Kautz 68]. A Kautz network with in-degree and out-degree d has N = dk + dk?1 nodes (for any cardinals d, k>0). The diameter is at most k, the degree is fixed and independent of the network size. Moreover, it is fault-tolerant, the connectivity is d and the mapping of standard computation graphs such as a linear array, a ring and a tree on a Kautz network is straightforward. The network has a simple routing mechanism, even when nodes or links are faulty. Imase et al. [Imase 86] showed the existence of d node disjoint paths between any pair of vertices. In Smit et al. [Smit 91] an algorithm is described that generates d node disjoint routes between two arbitrary nodes in the network. In this paper we present a simple and fast hardware implementation of this algorithm. It can be realized with standard components (Field Programmable Gate Arrays).

Tool Demonstration CLasH From Haskell to Hardware

C\ensuremath{\lambda}aSH is a functional hardware description language that borrows both its syntax and semantics from the functional programming language Haskell. Polymorphism and higher-order functions provide a level of abstraction and generality that allow a circuit designer to describe circuits in a more natural way than possible with the language elements found in the traditional hardware description languages.