Sparse matrix multiplication on a reconfigurable many-core architecture

Sparse matrix-vector multiplication (SMVM) is a fundamental operation in many scientific and engineering applications. In many cases sparse matrices have thousands of rows and columns where most of the entries are zero, while non-zero data is spread over the matrix. This sparsity of data locality reduces the effectiveness of data cache in general-purpose processors quite reducing their performance efficiency when compared to what is achieved with dense matrix multiplication. In this paper, we propose a parallel processing solution for SMVM in a many-core architecture. The architecture is tested with known benchmarks using a ZYNQ-7020 FPGA. The architecture is scalable in the number of core elements and limited only by the available memory bandwidth. It achieves performance efficiencies up to almost 70% and better performances than previous FPGA designs.

Algorithm-oriented design of efficient many-core architectures applied to dense matrix multiplication

Recent integrated circuit technologies have opened the possibility to design parallel architectures with hundreds of cores on a single chip. The design space of these parallel architectures is huge with many architectural options. Exploring the design space gets even more difficult if, beyond performance and area, we also consider extra metrics like performance and area efficiency, where the designer tries to design the architecture with the best performance per chip area and the best sustainable performance. In this paper we present an algorithm-oriented approach to design a many-core architecture. Instead of doing the design space exploration of the many core architecture based on the experimental execution results of a particular benchmark of algorithms, our approach is to make a formal analysis of the algorithms considering the main architectural aspects and to determine how each particular architectural aspect is related to the performance of the architecture when running an algorithm or set of algorithms. The architectural aspects considered include the number of cores, the local memory available in each core, the communication bandwidth between the many-core architecture and the external memory and the memory hierarchy. To exemplify the approach we did a theoretical analysis of a dense matrix multiplication algorithm and determined an equation that relates the number of execution cycles with the architectural parameters. Based on this equation a many-core architecture has been designed. The results obtained indicate that a 100 mm(2) integrated circuit design of the proposed architecture, using a 65 nm technology, is able to achieve 464 GFLOPs (double precision floating-point) for a memory bandwidth of 16 GB/s. This corresponds to a performance efficiency of 71 %. Considering a 45 nm technology, a 100 mm(2) chip attains 833 GFLOPs which corresponds to 84 % of peak performance These figures are better than those obtained by previous many-core architectures, except for the area efficiency which is limited by the lower memory bandwidth considered. The results achieved are also better than those of previous state-of-the-art many-cores architectures designed specifically to achieve high performance for matrix multiplication.

Genetic algorithms for discovery of matrix multiplication methods

We present a parallel genetic algorithm for nding matrix multiplication algo-rithms. For 3 x 3 matrices our genetic algorithm successfully discovered algo-rithms requiring 23 multiplications, which are equivalent to the currently best known human-developed algorithms. We also studied the cases with less mul-tiplications and evaluated the suitability of the methods discovered. Although our evolutionary method did not reach the theoretical lower bound it led to an approximate solution for 22 multiplications.

Matrix-vector multiplication and triangular linear solver using GPGPU for symmetric positive definite matrices derived from elliptic equations

The modern GPUs are well suited for intensive computational tasks and massive parallel computation. Sparse matrix multiplication and linear triangular solver are the most important and heavily used kernels in scientific computation, and several challenges in developing a high performance kernel with the two modules is investigated. The main interest it to solve linear systems derived from the elliptic equations with triangular elements. The resulting linear system has a symmetric positive definite matrix. The sparse matrix is stored in the compressed sparse row (CSR) format. It is proposed a CUDA algorithm to execute the matrix vector multiplication using directly the CSR format. A dependence tree algorithm is used to determine which variables the linear triangular solver can determine in parallel. To increase the number of the parallel threads, a coloring graph algorithm is implemented to reorder the mesh numbering in a pre-processing phase. The proposed method is compared with parallel and serial available libraries. The results show that the proposed method improves the computation cost of the matrix vector multiplication. The pre-processing associated with the triangular solver needs to be executed just once in the proposed method. The conjugate gradient method was implemented and showed similar convergence rate for all the compared methods. The proposed method showed significant smaller execution time.

Expokit: A software package for computing matrix exponentials

Expokit provides a set of routines aimed at computing matrix exponentials. More precisely, it computes either a small matrix exponential in full, the action of a large sparse matrix exponential on an operand vector, or the solution of a system of linear ODEs with constant inhomogeneity. The backbone of the sparse routines consists of matrix-free Krylov subspace projection methods (Arnoldi and Lanczos processes), and that is why the toolkit is capable of coping with sparse matrices of large dimension. The software handles real and complex matrices and provides specific routines for symmetric and Hermitian matrices. The computation of matrix exponentials is a numerical issue of critical importance in the area of Markov chains and furthermore, the computed solution is subject to probabilistic constraints. In addition to addressing general matrix exponentials, a distinct attention is assigned to the computation of transient states of Markov chains.

A matrix formula for the skewness of maximum likelihood estimators

We give a general matrix formula for computing the second-order skewness of maximum likelihood estimators. The formula was firstly presented in a tensorial version by Bowman and Shenton (1998). Our matrix formulation has numerical advantages, since it requires only simple operations on matrices and vectors. We apply the second-order skewness formula to a normal model with a generalized parametrization and to an ARMA model. (c) 2010 Elsevier B.V. All rights reserved.

A many-core co-processor for embedded parallel computing on FPGA

Single processor architectures are unable to provide the required performance of high performance embedded systems. Parallel processing based on general-purpose processors can achieve these performances with a considerable increase of required resources. However, in many cases, simplified optimized parallel cores can be used instead of general-purpose processors achieving better performance at lower resource utilization. In this paper, we propose a configurable many-core architecture to serve as a co-processor for high-performance embedded computing on Field-Programmable Gate Arrays. The architecture consists of an array of configurable simple cores with support for floating-point operations interconnected with a configurable interconnection network. For each core it is possible to configure the size of the internal memory, the supported operations and number of interfacing ports. The architecture was tested in a ZYNQ-7020 FPGA in the execution of several parallel algorithms. The results show that the proposed many-core architecture achieves better performance than that achieved with a parallel generalpurpose processor and that up to 32 floating-point cores can be implemented in a ZYNQ-7020 SoC FPGA.

TEA: Timing and Energy Aware compression architecture for Efficient Configuration in CGRAs

Coarse Grained Reconfigurable Architectures (CGRAs) are emerging as enabling platforms to meet the high performance demanded by modern applications (e.g. 4G, CDMA, etc.). Recently proposed CGRAs offer time-multiplexing and dynamic applications parallelism to enhance device utilization and reduce energy consumption at the cost of additional memory (up to 50% area of the overall platform). To reduce the memory overheads, novel CGRAs employ either statistical compression, intermediate compact representation, or multicasting. Each compaction technique has different properties (i.e. compression ratio, decompression time and decompression energy) and is best suited for a particular class of applications. However, existing research only deals with these methods separately. Moreover, they only analyze the compaction ratio and do not evaluate the associated energy overheads. To tackle these issues, we propose a polymorphic compression architecture that interleaves these techniques in a unique platform. The proposed architecture allows each application to take advantage of a separate compression/decompression hierarchy (consisting of various types and implementations of hardware/software decoders) tailored to its needs. Simulation results, using different applications (FFT, Matrix multiplication, and WLAN), reveal that the choice of compression hierarchy has a significant impact on compression ratio (up to 52%), decompression energy (up to 4 orders of magnitude), and configuration time (from 33 n to 1.5 s) for the tested applications. Synthesis results reveal that introducing adaptivity incurs negligible additional overheads (1%) compared to the overall platform area.

A linear algebra approach to OLAP

Inspired by the relational algebra of data processing, this paper addresses the foundations of data analytical processing from a linear algebra perspective. The paper investigates, in particular, how aggregation operations such as cross tabulations and data cubes essential to quantitative analysis of data can be expressed solely in terms of matrix multiplication, transposition and the Khatri–Rao variant of the Kronecker product. The approach offers a basis for deriving an algebraic theory of data consolidation, handling the quantitative as well as qualitative sides of data science in a natural, elegant and typed way. It also shows potential for parallel analytical processing, as the parallelization theory of such matrix operations is well acknowledged.

Análisis de prestaciones de procesadores multi-core y multi-thread

Los procesadores multi-core y el multi-threading por hardware permiten aumentar el rendimiento de las aplicaciones. Por un lado, los procesadores multi-core combinan 2 o más procesadores en un mismo chip. Por otro lado, el multi-threading por hardware es una técnica que incrementa la utilización de los recursos del procesador. Este trabajo presenta un análisis de rendimiento de los resultados obtenidos en dos aplicaciones, multiplicación de matrices densas y transformada rápida de Fourier. Ambas aplicaciones se han ejecutado en arquitecturas multi-core que explotan el paralelismo a nivel de thread pero con un modelo de multi-threading diferente. Los resultados obtenidos muestran la importancia de entender y saber analizar el efecto del multi-core y multi-threading en el rendimiento.

MA167exam01pdf

Exam questions and solutions in PDF

MA167exam01

Exam questions and solutions in LaTex. Diagrams for the questions are all together in the support.zip file, as .eps files