Learn More About SequenceL
Explore further how the breakthrough SequenceL Multicore Programming Solution can overcome your challenges of system performance, faster time to market, innovation, and improving software quality while unleashing full multicore performance on your next project.
PhD dissertation by TMT developer Bryant Nelson on extending the SequenceL compiler to automatically generate C++ which uses
a combination of MPI and Intel’s TBB to achieve scalable hybrid (shared memory + distributed/cluster) parallelizations.
Computational performance of SequenceL coding of the lattice Boltzmann method for multi-particle flow simulations (12/19/16)
This paper reports, for the first time, the computational performance of SequenceL for mesoscale simulations of large numbers of particles in a microfluidic device via the lattice-Boltzmann method. The performance of SequenceL simulations was assessed against the optimized serial and parallelized (via OpenMP directives) FORTRAN90 simulations.
Compilation of performance results of TMT optimizing the auto-parallelizing SequenceL multicore programming tool set to the IBM POWER8 platform. After completing the optimization work on IBM POWER8, TMT ran its suite of heatmap programs on two POWER8 configurations and three Intel x86 Xeon “Haswell” configurations for comparison and verification purposes.
The Best of Both Worlds. This paper, published in 08/20/14 Embedded Computing Design, shows how C++ programmers (as well as C and C#) can easily add the powerful SequenceL language and tool set to best tackle the multicore programming job. It is the classic hammer and nail problem, choosing the appropriate tool for the job.
Paper presented at the 2014 World Congress in Computer Science: In response to a growing interest in functional programming and its use in game development, a framework for developing real-time games using SequenceL was designed and implemented at Texas Tech University. This paper describes the framework and methods for writing games using the purely functional language, SequenceL.
Paper presented at the 2014 World Congress in Computer Science. A framework for developing real-time games using the SequenceL functional language was designed and implemented at Texas Tech University.After it was created, a study was conducted to determine the advantages of using SequenceL to develop games over Python.
Paper presented at the 2013 World Congress in Computer Science reports the results of experiments on the performance of parallel programs automatically generated by the SequenceL compiler. In particular we examine the parallel speedups obtained in running SequenceL programs on multicore hardware.
The Basic Linear Algebra Subprograms (BLAS) Library is a collection of functions to perform standard linear algebra operations on single processor computers.This paper shows how the extreme ease of use of the SequenceL compiler and interpreter, combined with a very impressive scalability of representative level 1 BLAS library routines, created a significantcant step forward in modern parallelization of linear algebra operations.
NASA Tech Brief - SequenceL: Automated Parallel Algorithms Derived from CSP-NT Computational Laws (03/01/13)
SequenceL has been found to discover all potential parallelisms automatically in relatively complex algorithms (involving multiple threads), and thus shows the potential to relieve more of the programmer’s cognitive load as the problem grows in complexity.
Optimizing Parallel Processing Performance and Coding Efficiency with AMD APUs and Texas Multicore Technologies’ SequenceL Auto-parallelizing Programming Solution. The combination of these advanced technologies ultimately yields ultra-responsive, parallel processing-driven embedded systems and liberates developers from conventional sequential coding processes.
Emerson and TMT: Utilizing Parallelization and Multicore Architectures for Scheduling Large-Scale Wireless Mesh Networks (04/23/12)
Award winning white paper presented at 2012 IECON describing how TMT’s SequenceL technology was used to prototype and deliver fast performance of Emerson Research’s SRDR WirelessHART (IEC 62591) Gateway algorithm on an embedded multicore SOC.
Paper explains some of the implementation details of the Emerson Process Managment Research WirelessHART SRDR algorithms under SequenceL. This allowed a quick and easy way to accurately express the algorithms in code and to generate parallelized C++ code that effectively utilized the multi-core and GPU processors automatically.
Technical presentation by Dr. Daniel Cooke for the SHPCP (Society of High Performance Computing Professionals) at their annual 2010 Fall technology meeting. Includes an introduction to SequenceL, the problems it solves and how it achieves its performance speed-ups, concluding with example codes and performance results in SequenceL compared to other languages including Haskell, Erlang, Matlab, OpenMP.
Mastering the Multicore Challenge: An Elegant and Efficient Approach to Exploiting the Power of Parallelism (08/27/10)
A new software development language and environment, named SequenceL, is specifically targeted at writing software that runs efficiently on parallel hardware. This white paper examines the technology, describing in outline how it works, why there is a need for it and how well it performs in parallel environments.
This white paper, published in IEEE Computer Magazine, is a good overview of SequenceL. It begins with a review of abstractions in procedural, object oriented, and functional programming to introduce the SequenceL abstraction that shields the user from the need to know how the parallel programming is implemented. It includes many examples and reviews work done with NASA and other customers.
SequenceL is a concise, high-level language with a simple semantics that provides for the automatic derivation of many iterative and parallel control structures. The semantics repeatedly applies a “Normalize-Transpose-Distribute” operation to functions and operators until base cases are discovered. This article introduces the results of a 24-month effort to reduce the language to a very small set of primitives. Included are comparisons with other languages, the formal syntax and semantics, and the traces of several example problems run with a prototype interpreter developed in 2006.
The seminal white paper introducing SequenceL, a compact, Turing-complete, high-level language, in which algorithms for implementing a solution are automatically derived from a high level description of that solution. In this paper we introduce how the language can be exploited in the design of iterative and parallel algorithms.
SequenceL is a concise, high-level language with a simple semantic that provides for the automatic derivation of many iterative and parallel control structures. This paper introduces the language from an intuitive point of view, indicating the scalability of the normalize-transpose operation, the different forms of recursion supported by the language and its abstraction, and new shorthand methods for specifying additional iterative/recursive problem solutions.