Improved High-Level Synthesis for Complex CellML Models

In this work, we present the use of a new high-level synthesis engine capable of generating resource-shared compute accelerators, even from very complex double-precision codes, for cell biology simulations. From the domain-specific CellML description, the compilation pipeline is able to generate hardware that is shown to achieve a performance similar to or exceeding current generation desktop CPUs, and has energy savings of up to 96% even for a single accelerator, which requires just 25–30% area on a mid-sized FPGA.

[1]  Florent de Dinechin,et al.  Parameterized floating-point logarithm and exponential functions for FPGAs , 2007, Microprocess. Microsystems.

[2]  Florent de Dinechin,et al.  Designing Custom Arithmetic Data Paths with FloPoCo , 2011, IEEE Design & Test of Computers.

[3]  Antonis A Armoundas,et al.  Mechanisms of Abnormal Calcium Homeostasis in Mutations Responsible for Catecholaminergic Polymorphic Ventricular Tachycardia , 2007, Circulation research.

[4]  Pingfan Meng,et al.  Hardware Accelerated Alignment Algorithm for Optical Labeled Genomes , 2016 .

[5]  Oliver Sinnen,et al.  Performance optimisation strategies for automatically generated FPGA accelerators for biomedical models , 2016, Concurr. Comput. Pract. Exp..

[6]  Yu Ting Chen,et al.  A Survey and Evaluation of FPGA High-Level Synthesis Tools , 2016, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[7]  Andreas Koch,et al.  Precore - A Token-Based Speculation Architecture for High-Level Language to Hardware Compilation , 2011, 2011 21st International Conference on Field Programmable Logic and Applications.

[8]  Vlad Mihai Sima,et al.  DWARV 2.0: A CoSy-based C-to-VHDL hardware compiler , 2012, 22nd International Conference on Field Programmable Logic and Applications (FPL).

[9]  R. Winslow,et al.  A computational model of the human left-ventricular epicardial myocyte. , 2004, Biophysical journal.

[10]  Andreas Koch,et al.  Hardware/software co-compilation with the Nymble system , 2013, 2013 8th International Workshop on Reconfigurable and Communication-Centric Systems-on-Chip (ReCoSoC).

[11]  Michael Fingeroff,et al.  High-Level Synthesis Blue Book , 2010 .

[12]  Peter Müller,et al.  Accelerating high-level engineering computations by automatic compilation of Geometric Algebra to hardware accelerators , 2010, 2010 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation.

[13]  Heye Zhang,et al.  OpenCMISS: a multi-physics & multi-scale computational infrastructure for the VPH/Physiome project. , 2011, Progress in biophysics and molecular biology.

[14]  Andreas Koch,et al.  Automatic high-level synthesis of multi-threaded hardware accelerators , 2014, 2014 24th International Conference on Field Programmable Logic and Applications (FPL).

[15]  Peter J. Hunter,et al.  An Overview of CellML 1.1, a Biological Model Description Language , 2003, Simul..

[16]  Ting Yu,et al.  ODoST: Automatic Hardware Acceleration for Biomedical Model Integration , 2016, ACM Trans. Reconfigurable Technol. Syst..

[17]  R. Heinrich,et al.  Control of MAPK signalling: from complexity to what really matters , 2005, Oncogene.

[18]  David P. Nickerson,et al.  An overview of the CellML API and its implementation , 2010, BMC Bioinformatics.

[19]  Jason Helge Anderson,et al.  LegUp: high-level synthesis for FPGA-based processor/accelerator systems , 2011, FPGA '11.

[20]  Peter J. Hunter,et al.  The CellML Model Repository , 2008, Bioinform..

[21]  Ting Yu,et al.  Domain-specific optimisation for the high-level synthesis of CellML-based simulation accelerators , 2015, 2015 25th International Conference on Field Programmable Logic and Applications (FPL).

[22]  D. Bers,et al.  A novel computational model of the human ventricular action potential and Ca transient. , 2010, Journal of Molecular and Cellular Cardiology.

[23]  A J Pullan,et al.  Biophysically based mathematical modeling of interstitial cells of Cajal slow wave activity generated from a discrete unitary potential basis. , 2009, Biophysical journal.

[24]  Andreas Koch,et al.  High-level synthesis of resource-shared microarchitectures from irregular complex C-code , 2016, 2016 International Conference on Field-Programmable Technology (FPT).

[25]  Fabrizio Ferrandi,et al.  Bambu: A modular framework for the high level synthesis of memory-intensive applications , 2013, 2013 23rd International Conference on Field programmable Logic and Applications.