#### Filter Results:

- Full text PDF available (3)

#### Publication Year

2004

2017

- This year (1)
- Last 5 years (3)
- Last 10 years (6)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Maksims Abalenkovs, Ahmad Abdelfattah, +7 authors Asim YarKhan
- 2016

We present a review of the current best practices in parallel programming models for dense linear algebra (DLA) on heterogeneous architectures. We consider multicore CPUs, stand alone manycore coprocessors, GPUs, and combinations of these. Of interest is the evolution of the programming models for DLA libraries – in particular, the evolution from the… (More)

- A. Haidar
- Proceedings. 2004 International Conference on…
- 2004

This paper focuses upon the design of neural network to produce good solution to multiple-valued logic circuits. The theoretical basis for applying neural networks to multiple-valued logic algebra called neuro-algebra is proposed. This research also studies the design of a single artificial neural network model for half adders of binary, ternary, quaternary… (More)

- H.A. Osseily, A. Haidar, Ali Kassem
- 2008 3rd International Conference on Information…
- 2008

The purpose of this paper is to present new algorithms and circuits to convert from MVL (multiple valued logic) to MVL coded decimal (MVL-CD) and vice versa. We will introduce two conversion techniques: the first one is called "addition-subtraction technique" (AST) while the other method is called "division-multiplication technique" (DMT). Based on AST, we… (More)

- A. Haidar, A.S.A. Hoda, M. Hamad, Hirokatsu Shirahama
- Canadian Conference on Electrical and Computer…
- 2005

The VLSI/ULSI performance is expected to keep improving at the current rate indefinitely as feature size shrinks; however as chips are bursting with huge number of transistors, the interchip connections are increased and heat dissipation is becoming an enormous problem as more and more functions are gathered on the same chip. This will influence size and… (More)

- Ahmad Abdelfattah, Marc Baboulin, +6 authors Stan Tomov
- 2017

This technical report describes our findings regarding performance optimizations of the tensor contraction kernels used in BLAST – a high-order FE hydrodynamics research code developed at LLNL – on various modern architectures. Our approach considers and shows ways to organize the contractions, their vectorization, data storage formats, read/write patterns,… (More)

- A. Haidar, S. Ghabboura, Nawar El Ahdab
- 2006 2nd International Conference on Information…
- 2006

This paper proposes a novel ternary QAM (TQAM), which is new concept in communication. The proposed model minimizes the number of characters per symbol; hence results in a better signal-to-noise ratio (SNR) and bit error rate (BER). For this purpose a new generation of constellation diagrams is proposed leading to new methods of modulating transmitted and… (More)

- A. Haidar, R. Dernaika, F. Shibani
- 2006 2nd International Conference on Information…
- 2006

We propose TQAM (ternary quadrature-amplitude modulation) as a scheme of modulating analog signals to carry ternary digital data. We propose a model for the constellation diagram of the new scheme. Our motivation of thinking about this issue is the fact that the application of multi-value (non-binary) digital signals can provide considerable relief of… (More)

- H.A. Osseily, A. Haidar
- 2008 3rd International Conference on Information…
- 2008

The purpose of this paper is to present new algorithms and circuits to convert from MVL (Multiple Valued Logic) to MVL Coded Decimal (MVL-CD) and vice versa. We will introduce two conversion techniques: the first one is called "Addition-Subtraction technique" (AST) while the other method is called "Division-Multiplication Technique" (DMT). Based on AST, we… (More)

- A. Haidar, Stan Tomov, +4 authors JJ. Dongarra
- 2012

The Matrix Algebra on GPU and Multicore Architectures (MAGMA) project aims to develop the next generation of LAPACK/ScaLAPACK-compliant linear algebra libraries for heterogeneous multicore-GPU architectures. The functionality covered in LAPACK and ScaLAPACK is a fundamental building block for many scientific computing applications, underlining the… (More)

- A. Haidar, F. Al-Rifai, Ali Alaeldine, M Bernard
- 2008 3rd International Conference on Information…
- 2008

The aim of this paper is to present a new design for a controller unit using base 3, which will be named ternary controller unit. The ternary controller unit is planned to be the future brain of the ternary central processing unit. The ternary controller unit controls the fetch and execution cycles of instructions. To achieve this task, the ternary… (More)

- ‹
- 1
- ›