Deliverables

D9.6: Final plan to disseminate and use the foreground knowledge

In this deliverable, we examined the overall heterogeneous computing market, trends, and players in order to determine potential effective approaches and strategies that form good bases for exploitation and dissemination of results achieved during REPARA work. The heterogeneous processing and Continue reading D9.6: Final plan to disseminate and use the foreground knowledge

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.6: Final plan to disseminate and use the foreground knowledge

D9.7: Standardization report

This deliverable describes the interrelationship with the C++ language, and explicitly how this project has participated in getting new features proposed and included by the C++ standards committee. The deliverable is part of the dissemination and public awareness generation of Continue reading D9.7: Standardization report

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.7: Standardization report

D9.4: Project web site

This report describes the changes and the final deployment of the website design, including the public website (available at http://www.repara-project.eu ) and the project internal website, as well as other Internet based dissemination means. This deliverable summarizes the results obtained Continue reading D9.4: Project web site

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.4: Project web site

D9.2: Final Press Release

This deliverable reports activities and results of the final press release delivery. ICT-609666-D9-2

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.2: Final Press Release

D9.3: Report on Initial Project Web Site

This report describes the initial website design, including the public website (available at http://www.repara-project.eu) and the project internal website, as well as other internet based dissemination means. Results reported in this deliverable will influence the approach for dissemination and public Continue reading D9.3: Report on Initial Project Web Site

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.3: Report on Initial Project Web Site

D9.1: Initial Press Release

To maximize the press release dissemination we have combined a global (international delivery in English) and a local strategy (national delivery of localized press releases by beneficiaries in their countries). Results reported in this deliverable will influence the approach for Continue reading D9.1: Initial Press Release

Posted in deliverable, WP9: Dissemination, exploitation and public awareness | Comments Off on D9.1: Initial Press Release

D3.5: Dynamic Partitioning Techniques

In this deliverable we focus on the description of those mechanisms that support the implementation of the kernel execution migration across dierent target devices and the collection of runtime information metrics (such as energy consumption, memory consumption and execution time) that eventually Continue reading D3.5: Dynamic Partitioning Techniques

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.5: Dynamic Partitioning Techniques

D4.4: Source code transformations for fine grained parallelism

This document describes deliverable D4.4. Source code transformations for fine grained parallelism, which is part of task T4.3. The deliverable’s results specify the transformation of annotated REPARA C++ code to FastFlow pipeline and DSP/FPGA source code. Those transformations are realized as Continue reading D4.4: Source code transformations for fine grained parallelism

Posted in deliverable, WP4: Software Transformations | Comments Off on D4.4: Source code transformations for fine grained parallelism

D5.3: Optimized multi-threaded mapping to reconfigurable hardware

The ThreadPoolComposer (TPC) tool has been refined to support the automated insertion of custom-generated (non-Vivado HLS) IP cores into the thread-pool of hardware processing elements. This not only allows the use of highly optimized cores formulated in traditional hardware design Continue reading D5.3: Optimized multi-threaded mapping to reconfigurable hardware

Posted in deliverable, WP5: Reconfigurable hardware transformations | Comments Off on D5.3: Optimized multi-threaded mapping to reconfigurable hardware

D2.3: Enforcing techniques for the REPARA-C++ specication

This document presents deliverable D2.3 Reengineering of legacy code. The aim of this task was to process and transform legacy C++ code to REPARA-C++ conformance source code. For this we developed a static code analysis tool to nd the violations Continue reading D2.3: Enforcing techniques for the REPARA-C++ specication

Posted in deliverable, WP2: Source Code Analysis | Comments Off on D2.3: Enforcing techniques for the REPARA-C++ specication

D2.5: Semantic specication for libraries

This document describes the deliverable D2.5 named Semantic specication for libraries. In document we present dierent mechanisms for specifying the semantic properties of libraries in generic terms. We explore two dierent alternative specications: axiom based and compiletime contracts. First mechanism Continue reading D2.5: Semantic specication for libraries

Posted in deliverable, WP2: Source Code Analysis | Comments Off on D2.5: Semantic specication for libraries

D3.4: Automatic kernel identication and assessment

The aim of this deliverable is to describe the Automatic Kernel Identification Tool (AKI) that aims to identify potential kernels in C++ sequential applications. AKI looks for hotspots that can be oined on heterogeneous computing devices. Finally, AKI annotates the Continue reading D3.4: Automatic kernel identication and assessment

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.4: Automatic kernel identication and assessment

D7.3: System-level quantitative models

In this document, we describe a method for deriving detailed, system-level quantitative models for predicting performance, power, and energy consumption based on source code software metrics. The models are built by employing various statistical and machine learning methods where the Continue reading D7.3: System-level quantitative models

Posted in deliverable, WP7: Predicitive modelling | Comments Off on D7.3: System-level quantitative models

D6.3: Dynamic runtimes with auto-tuning capabilities

The REPARA Project aims to deploy software kernels of a sequential application written in C++ in a parallel heterogeneous platform by using static or dynamic scheduling and mapping techniques with the objective to improve both the performance and the energy Continue reading D6.3: Dynamic runtimes with auto-tuning capabilities

Posted in deliverable, WP6: Runtimes for parallel heterogeneous architectures | Comments Off on D6.3: Dynamic runtimes with auto-tuning capabilities

D5.4: Reconfigurable hardware integration into runtime engines

The REPARA Project aims to provide a uniform programming interface for applications on parallel heterogeneous platforms to improve both the performance, as well as the energy efficiency. Field-programmable gate arrays (FPGAs) are characterized by their potential for deep spatial parallelism Continue reading D5.4: Reconfigurable hardware integration into runtime engines

Posted in deliverable, WP5: Reconfigurable hardware transformations | Comments Off on D5.4: Reconfigurable hardware integration into runtime engines

D5.2: Target platform for stand-alone hw execution and library of optimized module

The Repara Project targets the utilization of parallel heterogeneous hardware platforms such as GPGPUs, DSPs or FPGAs within a common design flow. Enhancements in terms of energy efficiency as well as performance shall be achieved by executing individual parts of Continue reading D5.2: Target platform for stand-alone hw execution and library of optimized module

Posted in deliverable, WP5: Reconfigurable hardware transformations | Comments Off on D5.2: Target platform for stand-alone hw execution and library of optimized module

D6.2: Dynamic runtimes for heterogeneous platforms

The REPARA Project aims to deploy software kernels of a sequential application written in C++ in parallel heterogeneous platforms by using static or dynamic scheduling and mapping techniques in order to improve both the performance and the energy efficiency. The Continue reading D6.2: Dynamic runtimes for heterogeneous platforms

Posted in deliverable, WP6: Runtimes for parallel heterogeneous architectures | Comments Off on D6.2: Dynamic runtimes for heterogeneous platforms

D7.4: Maintainability models of heterogeneous programming models

So far we have examined how performance and energy consumption changed if a program was executed on dierent platforms. Although it is a very important aspect of a program, there are other factors that have to be taken into consideration. Continue reading D7.4: Maintainability models of heterogeneous programming models

Posted in deliverable, WP7: Predicitive modelling | Comments Off on D7.4: Maintainability models of heterogeneous programming models

D7.2: Detailed quantitative performance and energy models

In this document, we describe a method for deriving detailed quantitative models for predicting performance, power, and energy consumption based on source code software metrics, with a special focus on recongurable hardware. The models are built by employing various statistical and Continue reading D7.2: Detailed quantitative performance and energy models

Posted in deliverable, WP7: Predicitive modelling | Comments Off on D7.2: Detailed quantitative performance and energy models

D1.2: Second Periodic Report

This report is the second in a series of documents reporting progress in the REPARA project. It will be followed later in the project by the third project periodic report to be produced at the end of second reporting period. ICT-609666-D1.2

Posted in deliverable, WP1: Project Management | Comments Off on D1.2: Second Periodic Report

D1.1: First Periodic Report

This report is the first in a series of documents reporting progress in the REPARA project. It will be followed later in the project by the project periodic reports to be produced at the end of each reporting period. ICT-609666-D1.1

Posted in deliverable, WP1: Project Management | Comments Off on D1.1: First Periodic Report

D6.4: Performance and energy monitoring library

Work Package 6 is focusing on run-time engines that manage software running on parallel heterogeneous computing systems, which includes techniques for measuring performance and energy consumption of the managed software and the integration of these techniques into the run-time engine. Therefore, we designed Continue reading D6.4: Performance and energy monitoring library

Posted in deliverable, WP6: Runtimes for parallel heterogeneous architectures | Comments Off on D6.4: Performance and energy monitoring library

D7.1: High-level quantitative performance and energy models

In this report we describe a method for deriving high-level quantitative prediction models for making low-fidelity predictions on performance, power, and energy consumption when a software component is mapped to a specific processing element. These predictions are low-fidelity as the transformation specific Continue reading D7.1: High-level quantitative performance and energy models

Posted in deliverable, WP7: Predicitive modelling | Comments Off on D7.1: High-level quantitative performance and energy models

D6.1: Static run times for coordination in heterogeneous platforms

This report is introduces static run-times for coordination in heterogeneous platforms, which is a prototype deliverable. It describes the basic run-time engine supporting statically partitioned applications. FastFlow is an open-source, structured parallel programming framework written in C/C++ originally conceived to support highly efficient stream Continue reading D6.1: Static run times for coordination in heterogeneous platforms

Posted in deliverable, WP6: Runtimes for parallel heterogeneous architectures | Comments Off on D6.1: Static run times for coordination in heterogeneous platforms

D3.3: Static Partitioning Tool

The REPARA project aims to deploy software kernels of an application in parallel heterogeneous platforms using static and dynamic scheduling and mapping techniques to improve the performance and energy efficiency. With this aim, a static partitioning tool is a key element. Static Continue reading D3.3: Static Partitioning Tool

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.3: Static Partitioning Tool

D5.1: Compile flow for behavioral transformation to reconfigurable hardware

This report introduces the compile flow for behavioral transformation to reconfigurable hardware. It describes the automated compilation flow of isolated C/C++ kernels to hardware thread-pools and their integration into higher-level run-times on the software-side. In the context of the REPARA project, this prototype Continue reading D5.1: Compile flow for behavioral transformation to reconfigurable hardware

Posted in deliverable, WP5: Reconfigurable hardware transformations | Comments Off on D5.1: Compile flow for behavioral transformation to reconfigurable hardware

D4.3: Source Code Transformations for Coarse Grained Parallelism

The REPARA project aims to help the transformation and deployment of new and legacy applications in parallel heterogeneous computing architectures while maintaining a balance between application performance, energy efficiency and source code maintainability. This report describes, source code transformations for coarse grained parallelism. The Continue reading D4.3: Source Code Transformations for Coarse Grained Parallelism

Posted in deliverable, WP4: Software Transformations | Comments Off on D4.3: Source Code Transformations for Coarse Grained Parallelism

D2.4: Algorithm Constraining and Selection Techniques

This report describes algorithm constraining and selection techniques. The presented techniques allow generating multi-versioned kernels implementations for a selected kernel in a source code in order to choose the most promising one in runtime. The report introduces the workow and the algorithms used. The Continue reading D2.4: Algorithm Constraining and Selection Techniques

Posted in deliverable, WP2: Source Code Analysis | Comments Off on D2.4: Algorithm Constraining and Selection Techniques

D2.2: Static Analysis Techniques for AIR Generation

In this report we describe the developed techniques for static analysis of REPARA-C++ source code and for producing REPARA-AIR representations. This means that we developed a command line tool, called RCPP2AIR, whose input is a REPARA-C++ compilation unit. It analyses the input and builds Continue reading D2.2: Static Analysis Techniques for AIR Generation

Posted in deliverable, WP2: Source Code Analysis | Comments Off on D2.2: Static Analysis Techniques for AIR Generation

D3.6: Qualitative Models for Performance and Energy Efficiency

This document contains the detailed description of our concept of the qualitative partitioning model. Using source code metrics produced by static analysis, our model is able to predict the computing unit that allows the fastest or most energy efficient execution of a Continue reading D3.6: Qualitative Models for Performance and Energy Efficiency

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.6: Qualitative Models for Performance and Energy Efficiency

D4.2: AIR access library

The AIR abbreviation stands for Abstract Intermediate Representation, which is an abstract semantic graph (ASG) representing C++ source code as described in the D2.1: REPARA C++ Open Specification document. An ASG is based on an abstract syntax tree (AST), but it is extended Continue reading D4.2: AIR access library

Posted in deliverable, WP4: Software Transformations | Comments Off on D4.2: AIR access library

D3.2: Target Platform Description Extraction Tool

This report summarizes the target platform description extraction tool developed as part of  of the REPARA project. The REPARA report D3.1 (Target Platform Description Specification) introduces the target platform description language (HPP-DL) itself. The purpose of HPP-DL is to allow creating a standard description Continue reading D3.2: Target Platform Description Extraction Tool

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.2: Target Platform Description Extraction Tool

D4.1: Extensible infrastructure for source code transformation

This document describes the Extensible infrastructure for source code transformation. The deliverable’s results support the convenient implementation of plug-ins for interactive and non-interactive transformations. Those transformations form the basis for implementing REPARA’s refactorings towards parallel code supporting heterogeneous computing architectures and improving source code Continue reading D4.1: Extensible infrastructure for source code transformation

Posted in deliverable, WP4: Software Transformations | Comments Off on D4.1: Extensible infrastructure for source code transformation

D3.1: Target Platform Description Specification

Heterogeneous Parallel Platform Description Language (HPP-DL) is a specification of a description language to provide all the relevant details of heterogeneous parallel platform. These heterogeneous platforms could be formed by: multicore, GPGPU, FPGA or DSP, or combinations of all of them. HPP-DL enables Continue reading D3.1: Target Platform Description Specification

Posted in deliverable, WP3: Software Partitioning | Comments Off on D3.1: Target Platform Description Specification

D9.1: Initial Press Release

This deliverable reports activities and results of the initial press release delivery. To maximize the press release dissemination we have combined a global (internatnional delivery in English) and a local strategy (national delivery of localized press releases by beneficiaries in their countries). Continue reading D9.1: Initial Press Release

Posted in deliverable | Comments Off on D9.1: Initial Press Release

D9.3: Report on Initial Project Website

This reports describes the initial website design, including the public website (available at http://repara-project.eu) and the project internal website, as well as other internet based dissemination means. The website has been split in two different websites targeting different public: A public Continue reading D9.3: Report on Initial Project Website

Posted in deliverable | Comments Off on D9.3: Report on Initial Project Website

D8.1: Description of applications and use cases and requirements

This deliverable describes the applications and use cases which will be used for testing and evaluating the REPARA framework. It also introduces requirements which should be fulfilled by different components of the REPARA framework so that the applications can be effectively compiled to Continue reading D8.1: Description of applications and use cases and requirements

Posted in deliverable, WP8: Use cases definition and evaluation | Comments Off on D8.1: Description of applications and use cases and requirements

D2.1: REPARA C++ Open Specification

The REPARA project aims to help the transformation and deployment of new and legacy applications in parallel heterogeneous computing architectures while maintaining a balance between application performance, energy efficiency and source code maintainability. For achieving this ambitious goal a key element is Continue reading D2.1: REPARA C++ Open Specification

Posted in deliverable, WP2: Source Code Analysis | Comments Off on D2.1: REPARA C++ Open Specification