Streaming FFT on REDEFINE-v2: An Application-Architecture Design Space Exploration

In this paper we explore an implementation of a high-throughput, streaming application on REDEFINE-v2, which is an enhancement of REDEFINE. REDEFINE is a polymorphic ASIC combining the flexibility of a programmable solution with the execution speed of an ASIC. In REDEFINE Compute Elements are arranged in an 8x8 grid connected via a Network on Chip (NoC) called RECONNECT, to realize the various macrofunctional blocks of an equivalent ASIC. For a 1024-FFT we carry out an application-architecture design space exploration by examining the various characterizations of Compute Elements in terms of the size of the instruction store. We further study the impact by using application specific, vectorized FUs. By setting up different partitions of the FFT algorithm for persistent execution on REDEFINE-v2, we derive the benefits of setting up pipelined execution for higher performance. The impact of the REDEFINE-v2 micro-architecture for any arbitrary N-point FFT (N > 4096) FFT is also analyzed. We report the various algorithm-architecture tradeoffs in terms of area and execution speed with that of an ASIC implementation. In addition we compare the performance gain with respect to a GPP.

TeV scale implications of non commutative space time in laboratory frame with polarized beams

We analyze e(+)e(-) -> gamma gamma, e(-)gamma -> e(-)gamma and gamma gamma -> e(+)e(-) processes within the Seiberg-Witten expanded noncommutative scenario using polarized beams. With unpolarized beams the leading order effects of non commutativity starts from second order in non commutative(NC) parameter i.e. O(Theta(2)), while with polarized beams these corrections appear at first order (O(Theta')) in cross section. The corrections in Compton case can probe the magnetic component(Theta(B)) while in Pair production and Pair annihilation probe the electric component((Theta) over right arrow (E)) of NC parameter. We include the effects of earth rotation in our analysis. This study is done by investigating the effects of non commutativity on different time averaged cross section observables. The results which also depends on the position of the collider, can provide clear and distinct signatures of the model testable at the International Linear Collider(ILC).

Co-ordinate interleaved distributed space-time coding for two-antenna relay networks

Distributed space time coding for wireless relay networks where the source, the destination and the relays have multiple antennas have been studied by Jing and Hassibi. In this set up, the transmit and the receive signals at different antennas of the same relay are processed and designed independently, even though the antennas are colocated. In this paper, a wireless relay network with single antenna at the source and the destination and two antennas at each of the R relays is considered. In the first phase of the two-phase transmission model, a T -length complex vector is transmitted from the source to all the relays. At each relay, the inphase and quadrature component vectors of the received complex vectors at the two antennas are interleaved before processing them. After processing, in the second phase, a T x 2R matrix codeword is transmitted to the destination. The collection of all such codewords is called Co-ordinate interleaved distributed space-time code (CIDSTC). Compared to the scheme proposed by Jing-Hassibi, for T ges AR, it is shown that while both the schemes give the same asymptotic diversity gain, the CIDSTC scheme gives additional asymptotic coding gain as well and that too at the cost of negligible increase in the processing complexity at the relays.

On four-group ML decodable distributed space time codes for cooperative communication

A construction of a new family of distributed space time codes (DSTCs) having full diversity and low Maximum Likelihood (ML) decoding complexity is provided for the two phase based cooperative diversity protocols of Jing-Hassibi and the recently proposed Generalized Non-orthogonal Amplify and Forward (GNAF) protocol of Rajan et al. The salient feature of the proposed DSTCs is that they satisfy the extra constraints imposed by the protocols and are also four-group ML decodable which leads to significant reduction in ML decoding complexity compared to all existing DSTC constructions. Moreover these codes have uniform distribution of power among the relays as well as in time. Also, simulations results indicate that these codes perform better in comparison with the only known DSTC with the same rate and decoding complexity, namely the Coordinate Interleaved Orthogonal Design (CIOD). Furthermore, they perform very close to DSTCs from field extensions which have same rate but higher decoding complexity.

A Predictive Perfomance Model for Superscalar Processors

Designing and optimizing high performance microprocessors is an increasingly difficult task due to the size and complexity of the processor design space, high cost of detailed simulation and several constraints that a processor design must satisfy. In this paper, we propose the use of empirical non-linear modeling techniques to assist processor architects in making design decisions and resolving complex trade-offs. We propose a procedure for building accurate non-linear models that consists of the following steps: (i) selection of a small set of representative design points spread across processor design space using latin hypercube sampling, (ii) obtaining performance measures at the selected design points using detailed simulation, (iii) building non-linear models for performance using the function approximation capabilities of radial basis function networks, and (iv) validating the models using an independently and randomly generated set of design points. We evaluate our model building procedure by constructing non-linear performance models for programs from the SPEC CPU2000 benchmark suite with a microarchitectural design space that consists of 9 key parameters. Our results show that the models, built using a relatively small number of simulations, achieve high prediction accuracy (only 2.8% error in CPI estimates on average) across a large processor design space. Our models can potentially replace detailed simulation for common tasks such as the analysis of key microarchitectural trends or searches for optimal processor design points.

Efficient space-time codes from cyclic division algebras

An overview of space-time code construction based on cyclic division algebras (CDA) is presented. Applications of such space-time codes to the construction of codes optimal under the diversity-multiplexing gain (D-MG) tradeoff, to the construction of the so-called perfect space-time codes, to the construction of optimal space-time codes for the ARQ channel as well as to the construction of codes optimal for the cooperative relay network channel are discussed. We also present a construction of optimal codes based on CDA for a class of orthogonal amplify and forward (OAF) protocols for the cooperative relay network

Novel Switching Sequences for a Space-Vector-Modulated Three-Level Inverter

A three-level inverter produces six active vectors, each of normalized magnitudes 1, 0.866, and 0.5, besides a zero vector. The vectors of relative length 0.5 are termed pivot vectors.The three nearest voltage vectors are usually used to synthesize the reference vector. In most continuous pulsewidth-modulation(PWM) schemes, the switching sequence begins from a pivot vector and ends with the same pivot vector. Thus, the pivot vector is applied twice in a subcycle or half-carrier cycle. This paper proposes and investigates alternative switching sequences, which use the pivot vector only once but employ one of the other two vectors twice within the subcycle. The total harmonic distortion(THD) in the fundamental line current pertaining to these novel sequences is studied theoretically as well as experimentally over the whole range of modulation. Compared with centered space vector PWM, two of the proposed sequences lead to reduced THD at high modulation indices at a given average switching frequency.

On the cut‐on frequencies of a large round duct with azimuthal as well as radial partitions

This letter deals with a three‐dimensional analysis of circular sectors and annular segments resulting from the partitioning of a round (cylindrical) duct for use in an active noise control system. The relevant frequency equations are derived for stationary medium and solved numerically to arrive at the cut‐on frequencies of the first few modes. The resultant table indicates among other things that azimuthal partitioning does not raise the cutoff frequency (the smallest cut‐on frequency) beyond a particular value, and that radial partitioning is counterproductive in that respect.

Specification Based Regression Testing Using Explicit State Space Enumeration

This paper presents a method of partial automation of specification based regression testing, which we call ESSE (Explicit State Space Enumeration). The first step in ESSE method is the extraction of a finite state model of the system making use of an already tested version of the system under test (SUT). Thereafter, the finite state model thus obtained is used to compute good test sequences that can be used to regression test subsequent versions of the system. We present two new algorithms for test sequence computation - both based on our finite state model generated by the above method. We also provide the details and results of the experimental evaluation of ESSE method. Comparison with a practically used random-testing algorithm has shown substantial improvements.

A general construction of space-time trellis codes for PSK signal sets

The diversity order and coding gain are crucial for the performance of a multiple antenna communication system. It is known that space-time trellis codes (STTC) can be used to achieve these objectives. In particular, we can use STTCs to obtain large coding gains. Many attempts have been made to construct STTCs which achieve full-diversity and good coding gains, though a general method of construction does not exist. Delay diversity code (rate-1) is known to achieve full-diversity, for any number of transmit antennas and any signal set, but does not give a good coding gain. A product distance code based delay diversity scheme (Tarokh, V. et al., IEEE Trans. Inform. Theory, vol.44, p.744-65, 1998) enables one to improve the coding gain and construct STTCs for any given number of states using coding in conjunction with delay diversity; it was stated as an open problem. We achieve such a construction. We assume a shift register based model to construct an STTC for any state complexity. We derive a sufficient condition for this STTC to achieve full-diversity, based on the delay diversity scheme. This condition provides a framework to do coding in conjunction with delay diversity for any signal constellation. Using this condition, we provide a formal rate-1 STTC construction scheme for PSK signal sets, for any number of transmit antennas and any given number of states, which achieves full-diversity and gives a good coding gain.

Design space exploration of systolic realization of QR factorization on a runtime reconfigurable platform

In the world of high performance computing huge efforts have been put to accelerate Numerical Linear Algebra (NLA) kernels like QR Decomposition (QRD) with the added advantage of reconfigurability and scalability. While popular custom hardware solution in form of systolic arrays can deliver high performance, they are not scalable, and hence not commercially viable. In this paper, we show how systolic solutions of QRD can be realized efficiently on REDEFINE, a scalable runtime reconfigurable hardware platform. We propose various enhancements to REDEFINE to meet the custom need of accelerating NLA kernels. We further do the design space exploration of the proposed solution for any arbitrary application of size n × n. We determine the right size of the sub-array in accordance with the optimal pipeline depth of the core execution units and the number of such units to be used per sub-array.