ALMA project

ALgorithm parallelization for Multicore Architectures.

Simplifying programming for multi-cores

Why must a programmer care for the hardware architecture when programming embedded applications on a multiprocessor Systems-on-Chip?
The ALMA project intends to change that 'MUST' into a 'MAY'. We work to develop a programming tool chain that hides the complexity of applications and architectures from the programmer, and creates optimized code at the same time.

ALMA Spin-Off: emmtrix Technologies

Karlsruhe, Germany, August 1, 2015 - Dr. Timo Stripf together with colleagues of Karlsruhe Institute of Technology (KIT) acquired significant seed money from the German EXIST program to establish the spinoff "emmtrix Technologies" (www.emmtrix.com).

emmtrix (short for embedded matrix) Technologies commercializes the ALMA technology to simplify the software development process for multicore embedded systems in order to break down the barriers preventing the deployment of multicore processors. To this end, emmtrix will provide a development tool for programming multicore processors. The innovative interactive parallelization technology creates a parallel application directly from sequential MATLAB or Scilab code.

emmtrix Technologies

Press Package

Karlsruhe, Germany, July 15, 2015 - The ALMA consortium published a press material package. After the successful end of the ALMA EU project and its excellent evaluation, the press package presents the outstanding results achieved by consortium of the ALMA project. The package contains the latest posters, presentations, videos and reports.

Download the press package...

Press Release: ALMA project results

Programming multi-cores just got up to 58% cheaper while applications run 3 times faster

Brussels, - March 3, 2015 – Software development for embedded multi-core processors is considered to require a large expenditure and to be difficult. Under the ALMA EU project, researchers developed a new integrated tool chain to facilitate programming. According to tests, the ALMA tool chain reduces the time and, hence, cost expenditure of programming by up to 58%. Compared to single-core processors, applications are accelerated by about a factor of three. The project has now been completed and was coordinated by Karlsruhe Institute of Technology (KIT).

Download the press release...

ALMA at DATE2015

Grenoble, France, March 11, 2015 - Christakis Lezos, Grigoris Dimitroulakos and Konstantinos Masselos, University of Peloponnese, GR, talks on Reuse Distance Analysis for Locality Optimization in Loop-Dominated Applications at DATE 2015

Read more on DATE2015...

ALMA at HiPEAC 2015

Amsterdam, The Netherlands, January 19-21, 2015 - During the HiPEAC conference, the researchers in the ALMA consortium share their knowlegde in presentations and invited talks:

G. Rauwerda (Recore Systems) touches on many-core programming complexity and the need for an ALMA-like solution in his invited talk at the Workshop in Reconfigurable Computing (WRC'14) held together with the HiPEAC conference (Tuesday, Jan 20, 11:30).

Prof. J. Becker (Karlsruhe Institute of Technology) presents a poster titled ALgorithm parallelization for Multicore Architectures at the HiPEAC conference (Wednesday, Jan 21).

Read more on HiPEAC2015...
Read more on the WRC workshop @ HiPEAC2015...

ALMA at ICCAD2014

San Jose, USA, Nov 5th, 2014 - The ALMA consortium presents the paper Toward Scalable Source Level Accuracy Analysis for Floating-point to Fixed-point Conversion at the ICCAD 2014.

In this talk, we explain how polyhedral methods to build high-level, more scalable accuracy models extend the applicability of analytical approach to verify the accurate conversion of floating-point to fixed-point.

In an embedded systems context, many numerical algorithms must be converted from floating-point to fixed-point to meet cost and area constraints. While cheap and power-efficient, fixed-point arithmetic comes at the price of reduced accuracy and the designer must make sure that accuracy constraints are satisfied.

Usually, one resorts to (slow) simulations. Analytical approaches have been proposed in order to avoid costly simulations and allow more thorough design-space exploration. However, their applicability is limited by severe scalability issues. We explain how to overcome this issues using polyhedral methods.

Read more on ICCAD 2014...

ALMA at FPL'14

München, Germany, Sept 5th, 2014 - The ALMA consortium organises a full-day workshop on the ALMA project during FPL'14.

Alma at ISPA 2014

Milan, Italy, Aug 28th, 2014 The ALMA consortium presents a paper titled A Hierarchical Architecture Description for Flexible Multicore System Simulation at the ISPA 2014.

Read more on ISPA14...

Alma at PATAT'14

York, UK, Aug 28th, 2014 Panayiotis Alefragis on behalf of the ALMA consortium presented "Assigning and Scheduling Hierarchical Task Graphs to Heterogeneous Resources" during the 10th International Conference of the Practice and Theory of Automated Timetabling (PATAT2014).
In the talk, the hybrid Heuristic - Integer Linear Programming coarse grain toolset for solving Hierarchical Task Graphs was presented.

Read more on PATAT'14...

ALMA at SCOPES2014

St. Goar, Germany, June 10th, 2014 - The ALMA consortium presents From Scilab To High Performance Embedded Multicore Systems - The ALMA Approach during the session on Automatic parallelization for multicore systems on June 10th, 15:00 17th SCOPES Workshop.

Read more on SCOPES2014...

HiPEAC Newsletter 38

May 2014 - The HiPEAC newsletter 38 features a one-page article on the ALMA project titled Wondering how to program your next multi-core? Read it in the HiPEAC newsletter....

ALMA at RAW '14

Phoenix, Arizona, May 19th, 2014 - The ALMA consortium presents A hybrid ILP-CP model for mapping Directed Acyclic Task Graphs to multicore architectures during the 21st Reconfigurable Architectures Workshop at the 28th Annual International Parallel & Distributed Processing Symposium (IPDPS 2014).

In the talk, the ALMA consortium introduces a hybrid Integer Linear Programming - Constraint Programming method that uses the Benders decomposition to tackle the challenges of modern embedded multicore architectures with a large number of heterogeneous resources. Experiments show that the proposed hybrid method systematically outperforms a conventional ILP-based solution method.

Read more on RAW'14...

ALMA at ARC2014

Villamoura, Portugal, April 15, 2014 - The ALMA consortium organises the special session From Scilab to High Performance Embedded Multicore Systems: The ALMA Approach at the ARC conference on Tuesday April 15 from 15:50 to 17:10.

The special session will cover the following topics:
  • Introducing the ALMA Approach for Compiling Scilab to Multi-Core Architectures,
  • Multi-Core Architectures targeted by ALMA Flow,
  • ADL-based Fine-Grain Optimizations within the ALMA Flow,
  • Mapping and Scheduling Coarse Grain Hierarchical Task Graphs on Multi-core Architectures,
  • Demonstration of the Integrated ALMA Toolflow.

Read more on the special sessions at ARC...

ALMA at DATE2014

Dresden, Germany, March 25-27, 2014 - The ALMA consortium will demonstrate its tool flow in a European Project Booth at DATE 2014.
The demo first converts Scilab code to C in the front end. A GeCoS framework then parallelizes and optimizes the code, integrating fine and coarse-grained parallelism extraction and parallel code generation.

The demo will show automatic parallelization of scale-invariant feature transform (SIFT) code, a computer vision algorithm to detect and describe local features in images.

Read the press release in English ... or in German (as distributed by KIT) ...

Read more on DATE...

Contact us for an appointment and demo...

ALMA at HiPEAC 2014

Vienna, Austria, January 20, 2014 - During the HiPEAC conference, the researchers in the ALMA consortium share their knowlegde in presentations and keynotes:

G. Rauwerda (Recore Systems) touches on many-core programming complexity and the need for an ALMA-like solution in his keynote at the Workshop in Reconfigurable Computing (WRC'14) held together with the HiPEAC conference (Tuesday, Jan 21, 10:00) and in his talk on Many-core DSP architectures during the PEGPUM workshop (Monday, Jan 20, 10:35).

Prof. J. Becker (Karlsruhe Institute of Technology) presents a poster titled ALgorithm parallelization for Multicore Architectures at the HiPEAC conference (Wednesday, Jan 22).

Read more on HiPEAC2014...
Read more on the WRC workshop @ HiPEAC2014...
Read more on the PEGPUM workshop @ HiPEAC2014...

ALMA at Cyber-Physical Systems

Brussels, Belgium, October 30, 2013 - Gerard Rauwerda (Recore Systems ) presents Reliable and efficient data processing in next-generation multi-core DSPs for space during the workshop 'Mixed criticality systems – platforms for the future' at the conference "Cyber-Physical Systems: Uplifting Europe's innovation capacity", on Wednesday, 30th October 2013 between 10.30-12.00.

In his talk, Gerard explains various fault-tolerant hardware architectures and discusses ALMA's solution for easy programming of complex many-cores.

Read more on the conference Cyber-Physical Systems: Uplifting Europe's innovation capacity

ALMA at IEEE-SCAM2013

Eindhoven, the Netherlands, Sept 22, 2013 - Tomofumi Yuki (INRIA) presents a talk titled GeCoS: A Framework for Prototyping Custom Hardware Design Flows, during which he sheds light on an important part of the ALMA toolchain. He presents his talk in a session on 'Dynamic analysis' at the IEEE International Working Conference on Source Code Analysis and Manipulation in Eindhoven, The Netherlands on the 22nd September, between 13.45 and 15.00.

In his talk, Tomofumi Yuki presents the GeCoS framework for prototyping hardware design flows. He explains how the framework distinguishes itself from existing compiler framework by providing an environment for developing "design flows", rather than a compiler pass where interaction with the hardware designer is expected.
Read more on the IEEE-SCAM2013, IEEE International Working Conference on Source Code Analysis and Manipulation...

ALMA at DSD 2013

Santander, Spain, Sept 4-6, 2013 - Oliver Oey (Karlsruhe Institute of Technology) presents the ALMA project in a talk titled Coarse-grain Optimization and Code Generation for Embedded Multicore Systems at the Euromicro Conference on Digital System Design in Santander, Cantabria, Spain.

Parallel programming of multi-core and many-core SoCs remains a difficult, timeconsuming and complicated task. State of the art fourth generation of high programming languages like Scilab or MATLAB can help to make programming multi-cores easier for end users who are not parallel programming experts, provided that an additional tool chain translates these high programming languages to efficient parallel code. The ALMA toolset is being developed to receive Scilab code as input and produce parallel code for (generic) embedded multiprocessor systems on chip, using platform quasi-agnostic optimisations.
In his talk, Oliver Oey discusses hurdles in coarse grain parallelism extraction and optimization, as well as solutions for automatic parallel code generation for the ALMA toolset.
Read more on the DSD 2013, the Euromicro Conference on Digital System Design...

FPL2013

September 1, 2013 - Nikos Voros (Technological Educational Institute of Mesolonghi) presents the paper 'An advanced design framework for the efficient parallelization and evaluation of design alternatives for multicore embedded systems' on September 1, between 11:55 and 12:35, at the Workshop on Research Projects Focusing on High Performance Computing (in conjunction with FPL’2013).

The mapping process of high performance embedded applications to today’s multiprocessor system-on-chip devices users from a complex toolchain and programming process. The problem is the expression of parallelism with a pure imperative programming language which is commonly C. This traditional approach limits the mapping, partitioning and the generation of optimized parallel code, and consequently the achievable performance and power consumption of applications from different domains. The Architecture oriented paraLlelization for high performance embedded Multicore systems using scilAb (ALMA) European project aims to bridge these hurdles through the introduction and exploitation of a Scilab-based toolchain which enables the efficient mapping of applications on multiprocessor platforms from a high level of abstraction. The holistic solution of the ALMA toolchain allows the complexity of both the application and the architecture to be hidden, which leads to better acceptance, reduced development cost, and shorter time-to-market. Driven by the technology restrictions in chip design, the end of exponential growth of clock speeds, and an unavoidable increasing request of computing performance, ALMA is a fundamental step forward in the necessary introduction of novel computing paradigms and methodologies.
Read more on FPL2013...

MISTA 2013

Ghent, Belgium, August 27-30 2013- Panayiotis Alefragis (Technological Educational Institute of Mesolonghi) presents 'DAG Scheduling using Integer Programming in heterogeneous parallel execution environments' on the Multidisciplinary International Scheduling Conference: Theory & Applications (MISTA).

A computer program can be represented by a Directed Acyclic Graph (DAG) that captures the dependencies between the individual tasks in the program.
In his talk, Panayiotis Alefragis outlines a new mathematical model of Integer Programming for scheduling tasks over multiple processors serving as the execution environment. The multi-level approach called MATHL is benchmarked and consistently outperforms other DAG approaches with regards to the minimum overall execution time (a.k.a. schedule length or makespan), even for cases consisting over several hundreds of nodes.
Professor Alefragis will explain how MATHL partitions the DAG into levels and thus allows for breaking down complex programs into sub-problems with manageable sizes that can be solved in a timely manner. Consecutive optimal solutions for each level result in a high quality schedule for the overall problem, explaining the consistently favorable results.
Read more on MISTA 2013...

INDIN 2013

Bochum, Germany, July 29-31, 2013- Panayiotis Alefragis (Technological Educational Institute of Mesolonghi) presents 'Coarse grain parallelization using Integer Programming' on the 11th IEEE International Conference on Industrial Informatics (INDIN).

Automatic tools and techniques help programmers in developing complex parallel applications. The ALMA toolset automatically parallelizes programs written in Scilab to make them ready for execution on embedded multicore platforms.
In his talk, Panayiotis Alefragis presents key parts of ALMA's coarse grained parallelism optimization. He explains how the coarse grained parallelism optimization proces turns a program's hierarchical task graph into an optimized parallel schedule.
Read more on INDIN 2013...

IRIS Summer School 2013

IRIS2013 Greece, July 16, 2013 - Panayiotis Alefragis (TMES) presents ALMA technology in a course on Modeling, Heuristics and Evolutionary Algorithms in Network and Communication Systems during the ERASMUS IRIS summer school, on Tuesday July 16, 2013 from 13.00 to 16.00.

The course "Mathematical Modeling, Heuristics and Evolutionary Algorithms in Network and Communication Systems" will present the general principles of techniques and case studies of the application of the different optimization approaches in multi-core architectures, cellular and wireless networks.
Read more on the ERASMUS intensive program on "Cellular Technologies & Services" - IRIS 2013 Summer School...

ARC 2013

March 27, 2013 - Nikos Voros (Technological Educational Institute of Mesolonghi) presents the paper 'Coarse Grained Parallelism Optimization for Multicore Architectures: The ALMA Project Approach' in the special session on Research projects in Configurable and Embedded Computing on Wednesday March 27, between 8:00 an 10:00

Nikos will discuss the coarse grained parallelism optimization steps of the ALMA EU FP7 project. He will outline the possibilities of using Integer Programming, and the feasibility to provide optimal results to the problem model.
Read more on ARC2013...

ALMA goes Brazil (4)

Brazil, March 18, 2013 - Timo Stripf (Karlsruhe Institute of Technology) presents the ALMA project at the Universidade Federal do Rio Grande do Sul in Porto Alegre, in a presentation titled 'From Scilab To High Performance Embedded Multicore Systems – The ALMA Approach' on Tuesday, March 18, 14:00.
Read more on the ALMA presentation at UFRGS...

ALMA goes Brazil (3)

Brazil, March 12, 2013 - Timo Stripf (Karlsruhe Institute of Technology) presents the ALMA project at the University of Brasília in a presentation titled 'From Scilab To High Performance Embedded Multicore Systems – The ALMA Approach' on Tuesday, March 12, 14:00.

8th HiPEAC Conference

Berlin, Germany, Jan 23, 2013 - Inès Nijman (Recore Systems) and Timo Stripf (Karlsruhe Institute of Technology) present the poster 'ALgorithm parallelization for Multicore Architectures ' during the poster session on EU projects at the 8th HiPEAC Conference in Berlin, Germany, on Wednesday Jan 23.

During the conference, Timo Stripf (Karlsruhe Institute of Technology) is available to discuss high-level programming of multi-core SoCs. On Jan 22, Recore Systems will be available at the Industry Exhibit to discuss the same topic from an industry point of view.
Read more on the 8th HiPEAC Conference...

EUC 2012

Cyprus, Dec 5-7, 2012 - The ALMA consortium presents 'A Compilation- and Simulation-Oriented Architecture Description Language for Multicore Systems' at the EUC 2012 conference.
Read more on the IEEE/IFIP International Conference on Embedded and Ubiquitous Computing...

ALMA goes Brazil (2)

Brazil, November 28, 2012 - Oliver Oey (Karlsruhe Institute of Technology) presents the ALMA project at the University of Brasília in a presentation titled 'The Kahrisma Architecture within the ALMA Project' on Wednesday, November 28, 19:00 at the Computer Science Department . In his presentation, Oliver presents an overview of the goals of the ALMA project, gives insight in the ALMA tool-flow and concludes with the description of the Kahrisma architecture.

ALMA goes Brazil (1)

Brazil, November 13, 2012 - Oliver Oey (Karlsruhe Institute of Technology) presents the ALMA project at the University of Brasília in a presentation titled 'The Kahrisma Architecture within the ALMA Project' on Tuesday, November 13, 15:00 at the Mechatronics Department. In his presentation, Oliver presents an overview of the goals of the ALMA project, gives insight in the ALMA tool-flow and concludes with the description of the Kahrisma architecture.

2012 HiPEAC Computing Systems Week

Ghent, Belgium, Oct 17, 2012 - Kim Sunesen (Recore Systems) presents 'Towards reconfigurable tool chains for reconfigurable systems' during a sesssion on Reconfigurable Computing, at the 2012 HiPEAC Computing Systems Week in Ghent, Belgium, on Wednesday Oct 17 at 11:00. Read more on the 2012 HiPEAC Computing Systems Week...

Fall school

Lauterbad, Germany, Oct 2, 2012 - Timo Stripf (Karlsruhe Institute of Technology) presents the ALMA project during the Fall School on Programming Paradigms for Multi-core Embedded Systems in Lauterbad on Oct 2 at 10:15.
Read more on the Fall School on Programming Paradigms for Multi-core Embedded Systems...

DSD 2012

Çesme, Turkey, Sept 6, 2012 - Timo Stripf (Karlsruhe Institute of Technology) speaks on 'From Scilab To High Performance Embedded Multicore Systems – The ALMA Approach' during a session on European Projects in Digital Systems Design at the DSD 2012 conference in Çesme, Turkey, on Thursday Sept 6, at 16:00. Read more on DSD 2012, 15th Euromicro Conference on Digital System Design...

ISVLSI 2012

UMass, Amherst, USA, August 19, 2012 - Prof. Juergen Becker (Karlsruhe Institute of Technology) speaks on 'Architecture oriented paraLlelization for high performance embedded Multicore systems using scilAb' at the ISVLSI 2012 conference at the University of Massachusetts, Amherst, USA, on Sunday August 19, 2012, at 15:00. Read more on the IEEE Computer Society Annual Symposium on VLSI...

SAMOS XII

SAMOS - July 17, 2012 - Dr.-Ing. Diana Goehringer (Karlsruhe Institute of Technology), researcher in the ALMA consortium, speaks on 'From Scilab to Multicore Embedded Systems: Algorithms and Methodologies' during a special session on Programming Paradigms For Reconfigurable Multicore Embedded Systems during the SAMOS XII conference in Samos on Tuesday July 17, at 11:50. Read more on SAMOS2012...

ALMA in Liverpool

JLiverpool, UK, July 11, 2012 - Timo Stripf (Karlsruhe Institute of Technology) presents the ALMA project at the Computer Science Department of the Liverpool University on July 11 at 16:00.

Read more on the presentation at Liverpool University...

ReCoSoC'2012

York, UK - July 10, 2012 - Timo Stripf (Karlsruhe Institute of Technology) is to speak on A Flexible Approach for Compiling Scilab to Reconfigurable Multi-Core Embedded Systems during a Special Session on EU projects related to reconfigurable technology during the ReCoSoc'2012 Conference in York on Tuesday July 10, at 10:30. Read more on ReCoSoC'2012, 7th International Workshop on Reconfigurable Communication-centric Systems-on-Chip...

ASAP2012

Delft, the Netherlands - July 9, 2012 - Panayiotis Alefragis (TEIMES), researcher in the ALMA consortium, participates in the brainstorming dissussion on during a special session on Ongoing EU Projects during the ASAP 2012 conference in Delft, the Netherlands on Monday July 9, at 15:00. He will also present the ALMA project during the presentations session at 13:00. Read more on ASAP 2012, the 23rd IEEE International Conference on Application-specific Systems, Architectures and Processors...

PARMA 2012

MUNICH - February 29, 2012 - PD Dr.-Ing. Michael Huebner (Karlsruhe Institute of Technology), researcher in the ALMA consortium, delivers the keynote speech on ‘Application-aware multi-core hardware architectures and methods’ during the Parma2012 Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures in Munich. Read more on PARMA 2012 (co-located with ARCS 2012)...

Alma in the news

January 31, 2012 - The ALMA project has made the news! Read more in: Design& Reuse, EngineersOnline (Dutch), Display+, Elektronik Praxis (German), Compute Scotland, Silicon.de (German), Heise Developer (German), The H open, PhysOrg, KA news.

Press Release: ALMA project

Can programming of reconfigurable multi-cores be easier, please?

PARIS - January 24, 2012 – Why must a programmer care for the hardware architecture when writing embedded applications for multi-core? Today at HiPEAC 2012, Prof. Nikolaos Voros ex-plains how the ALMA Consortium intends to turn the 'MUST' into a 'MAY'. The ALMA Consortium proposes a tool chain that hides the complexity of hardware architectures from the programmer, and creates optimized code at the same time. More...

Press Release: Fast and Easy Programming

New EU Consortium ALMA Develops a Tool Chain for Embedded Multi-core Processors

KARLSRUHE - 31 January, 2012 - An increasing number of electronics products such as smartphones are equipped with fast, energy-efficient multi-core processors. As a matter of fact, however, programming of the respective applications is rather time-consuming and expensive. For fast and easy programming, partners from research and industry within the EU consortium ALMA are developing a novel tool chain based on the open-source software Scilab. ALMA is being coordinated by Professor Jürgen Becker and Dr. Michael Hübner from KIT’s Institute for Information Processing Technology (ITIV). More in English or in German...

HiPEAC2012

Nikolaos Voros, scientific coordinator of the project, speaks at the HiPEAC 2012 Workshop on Design Tools and Architectures for Multi-Core Embedded Computing Platforms on January 24 in Paris, France. Read more about the HiPEAC workshop...

Kick-off meeting

ATHENS - November 9, 2011 - The ALMA project officially started today in Athens with a kick-off meeting. The consortium aligned research tasks to be able to reach the goal of programmer-friendly, architecture-independent tooling for complex parallel multi-core systems in the next 36 months.

© 2012-2014 ALMA project | Disclaimer | Glossary