Test strategies on functionally partitioned module-based programmable architecture for base-band processing

A specialised reconfigurable architecture for telecommunication base-band processing is augmented with testing resources. The routing network is linked via virtual wire hardware modules to reduce the area occupied by connecting buses. The number of switches within the routing matrices is also minimised, which increases throughput without sacrificing flexibility. The testing algorithm was developed to systematically search for faults in the processing modules and the flexible high-speed routing network within the architecture. The testing algorithm starts by scanning the externally addressable memory space and testing the master controller. The controller then tests every switch in the route-through switch matrix by making loops from the shared memory to each of the switches. The local switch matrix is also tested in the same way. Next the local memory is scanned. Finally, pre-defined test vectors are loaded into local memory to check the processing modules. This algorithm scans all possible paths within the interconnection network exhaustively and reports all faults. Strategies can be inserted to bypass minor faults

Modelling continuum mechanics phenomena using three dimensional unstructured meshes on massively parallel processors

The difficulties encountered in implementing large scale CM codes on multiprocessor systems are now fairly well understood. Despite the claims of shared memory architecture manufacturers to provide effective parallelizing compilers, these have not proved to be adequate for large or complex programs. Significant programmer effort is usually required to achieve reasonable parallel efficiencies on significant numbers of processors. The paradigm of Single Program Multi Data (SPMD) domain decomposition with message passing, where each processor runs the same code on a subdomain of the problem, communicating through exchange of messages, has for some time been demonstrated to provide the required level of efficiency, scalability, and portability across both shared and distributed memory systems, without the need to re-author the code into a new language or even to support differing message passing implementations. Extension of the methods into three dimensions has been enabled through the engineering of PHYSICA, a framework for supporting 3D, unstructured mesh and continuum mechanics modeling. In PHYSICA, six inspectors are used. Part of the challenge for automation of parallelization is being able to prove the equivalence of inspectors so that they can be merged into as few as possible.

The stochastic geometric machine model

This paper introduces the stochastic version of the Geometric Machine Model for the modelling of sequential, alternative, parallel (synchronous) and nondeterministic computations with stochastic numbers stored in a (possibly infinite) shared memory. The programming language L(D! 1), induced by the Coherence Space of Processes D! 1, can be applied to sequential and parallel products in order to provide recursive definitions for such processes, together with a domain-theoretic semantics of the Stochastic Arithmetic. We analyze both the spacial (ordinal) recursion, related to spacial modelling of the stochastic memory, and the temporal (structural) recursion, given by the inclusion relation modelling partial objects in the ordered structure of process construction.

GPRM: a high performance programming framework for manycore processors

Processors with large numbers of cores are becoming commonplace. In order to utilise the available resources in such systems, the programming paradigm has to move towards increased parallelism. However, increased parallelism does not necessarily lead to better performance. Parallel programming models have to provide not only flexible ways of defining parallel tasks, but also efficient methods to manage the created tasks. Moreover, in a general-purpose system, applications residing in the system compete for the shared resources. Thread and task scheduling in such a multiprogrammed multithreaded environment is a significant challenge. In this thesis, we introduce a new task-based parallel reduction model, called the Glasgow Parallel Reduction Machine (GPRM). Our main objective is to provide high performance while maintaining ease of programming. GPRM supports native parallelism; it provides a modular way of expressing parallel tasks and the communication patterns between them. Compiling a GPRM program results in an Intermediate Representation (IR) containing useful information about tasks, their dependencies, as well as the initial mapping information. This compile-time information helps reduce the overhead of runtime task scheduling and is key to high performance. Generally speaking, the granularity and the number of tasks are major factors in achieving high performance. These factors are even more important in the case of GPRM, as it is highly dependent on tasks, rather than threads. We use three basic benchmarks to provide a detailed comparison of GPRM with Intel OpenMP, Cilk Plus, and Threading Building Blocks (TBB) on the Intel Xeon Phi, and with GNU OpenMP on the Tilera TILEPro64. GPRM shows superior performance in almost all cases, only by controlling the number of tasks. GPRM also provides a low-overhead mechanism, called “Global Sharing”, which improves performance in multiprogramming situations. We use OpenMP, as the most popular model for shared-memory parallel programming as the main GPRM competitor for solving three well-known problems on both platforms: LU factorisation of Sparse Matrices, Image Convolution, and Linked List Processing. We focus on proposing solutions that best fit into the GPRM’s model of execution. GPRM outperforms OpenMP in all cases on the TILEPro64. On the Xeon Phi, our solution for the LU Factorisation results in notable performance improvement for sparse matrices with large numbers of small blocks. We investigate the overhead of GPRM’s task creation and distribution for very short computations using the Image Convolution benchmark. We show that this overhead can be mitigated by combining smaller tasks into larger ones. As a result, GPRM can outperform OpenMP for convolving large 2D matrices on the Xeon Phi. Finally, we demonstrate that our parallel worksharing construct provides an efficient solution for Linked List processing and performs better than OpenMP implementations on the Xeon Phi. The results are very promising, as they verify that our parallel programming framework for manycore processors is flexible and scalable, and can provide high performance without sacrificing productivity.

Guiding Monte Carlo tree searches with neural networks in the game of go

A dissertation submitted in fulfillment of the requirements to the degree of Master in Computer Science and Computer Engineering

A parallel numerical solver using hierarchically tiled arrays

Solving linear systems is an important problem for scientific computing. Exploiting parallelism is essential for solving complex systems, and this traditionally involves writing parallel algorithms on top of a library such as MPI. The SPIKE family of algorithms is one well-known example of a parallel solver for linear systems. The Hierarchically Tiled Array data type extends traditional data-parallel array operations with explicit tiling and allows programmers to directly manipulate tiles. The tiles of the HTA data type map naturally to the block nature of many numeric computations, including the SPIKE family of algorithms. The higher level of abstraction of the HTA enables the same program to be portable across different platforms. Current implementations target both shared-memory and distributed-memory models. In this thesis we present a proof-of-concept for portable linear solvers. We implement two algorithms from the SPIKE family using the HTA library. We show that our implementations of SPIKE exploit the abstractions provided by the HTA to produce a compact, clean code that can run on both shared-memory and distributed-memory models without modification. We discuss how we map the algorithms to HTA programs as well as examine their performance. We compare the performance of our HTA codes to comparable codes written in MPI as well as current state-of-the-art linear algebra routines.

Studio e implementazione di componenti software per piattaforma mobile Android

Studio, descrizione, analisi e implementazione di tecnologie Android: Mappe, Google Cloud Messaging, Sensori

One-step digit-set-restricted modified signed-digit adder using an incoherent correlator based on a shared content-addressable memory

An efficient one-step digit-set-restricted modified signed-digit (MSD) adder based on symbolic substitution is presented. In this technique, carry propagation is avoided by introducing reference digits to restrict the intermediate carry and sum digits to {1,0} and {0,1}, respectively. The proposed technique requires significantly fewer minterms and simplifies system complexity compared to the reported one-step MSD addition techniques. An incoherent correlator based on an optoelectronic shared content-addressable memory processor is suggested to perform the addition operation. In this technique, only one set of minterms needs to be stored, independent of the operand length. (C) 2002 society or Photo-Optical Instrumentation Engineers.

Efficient two-step digit-set-restricted modified signed-digit algorithm based on optoelectronic shared content-addressable memory

A two-step digit-set-restricted modified signed-digit (MSD) adder based on symbolic substitution is presented. In the proposed addition algorithm, carry propagation is avoided by using reference digits to restrict the intermediate MSD carry and sum digits into {(1) over bar ,0} and {0, 1}, respectively. The algorithm requires only 12 minterms to generate the final results, and no complementarity operations for nonzero outputs are involved, which simplifies the system complexity significantly. An optoelectronic shared content-addressable memory based on an incoherent correlator is used for experimental demonstration. (c) 2005 Society of Photo-Optical Instrumentation Engineers.

Efficient two-step digit-set-restricted modified signed-digit algorithm based on optoelectronic shared content-addressable memory

A two-step digit-set-restricted modified signed-digit (MSD) adder based on symbolic substitution is presented. In the proposed addition algorithm, carry propagation is avoided by using reference digits to restrict the intermediate MSD carry and sum digits into {(1) over bar ,0} and {0, 1}, respectively. The algorithm requires only 12 minterms to generate the final results, and no complementarity operations for nonzero outputs are involved, which simplifies the system complexity significantly. An optoelectronic shared content-addressable memory based on an incoherent correlator is used for experimental demonstration. (c) 2005 Society of Photo-Optical Instrumentation Engineers.

Sviluppo di applicazioni android basate sulla sensoristica

L'obiettivo di questa tesi è quello di fornire le informazioni di base che, un aspirante programmatore Android, deve sapere per scrivere applicazioni che facciano uso dei sensori presenti nei moderni telefoni cellulari (accelerometro, giroscopio, sensore di prossimità, ecc...). La tesi si apre citando qualche aneddoto storico sulla nascita del sistema operativo più famoso al mondo ed elencando tutte le releases ufficiali e le novità che hanno portato dalla 1.0 all'attuale 5.1.1 Lollipop. Verranno analizzate le componenti fondamentali per costruire un applicazione Android: Activities, Services, Content Providers e Broadcast Receivers. Verrà introdotto e approfondito il concetto di sensore, sia punto di vista fisico sia dal punto di vista informatico/logico, evidenziando le tre dimensioni più importanti ovvero struttura, interazione e comportamento. Si analizzeranno tutte i tipi di errori e problematiche reali che potrebbero influire negativamente sui valori delle misurazioni (disturbi, rumori, ecc...) e si propone la moderna soluzione del Sensor Fusion come caso particolare di studio, prendendo spunto dal lavoro di grandi aziende come la Invensense e la Kionix Inc. Infine, si conclude l'elaborato passando dalle parole al codice: verranno affrontate le fasi di analisi e d'implementazione di un'applicazione esemplificativa capace di determinare l'orientamento del dispositivo nello spazio, sfruttando diverse tecniche Sensor Fusion.

Modular transactional memory

Software transactional memory has the potential to greatly simplify development of concurrent software, by supporting safe composition of concurrent shared-state abstractions. However, STM semantics are defined in terms of low-level reads and writes on individual memory locations, so implementations are unable to take advantage of the properties of user-defined abstractions. Consequently, the performance of transactions over some structures can be disappointing. ----- ----- We present Modular Transactional Memory, our framework which allows programmers to extend STM with concurrency control algorithms tailored to the data structures they use in concurrent programs. We describe our implementation in Concurrent Haskell, and two example structures: a finite map which allows concurrent transactions to operate on disjoint sets of keys, and a non-deterministic channel which supports concurrent sources and sinks. ----- ----- Our approach is based on previous work by others on boosted and open-nested transactions, with one significant development: transactions are given types which denote the concurrency control algorithms they employ. Typed transactions offer a higher level of assurance for programmers reusing transactional code, and allow more flexible abstract concurrency control.