Learn More
This paper presents a very efficient approach for algorithms developed based on conformal geometric algebra using reconfigurable hardware. We use the inverse kinematics of the arm of a virtual human as an example, but we are convinced that this approach can be used in a wide field of computer animation applications. We describe the original algorithm on a(More)
We describe the architecture and implementation of ffLink, a high-performance PCIe Gen3 interface for attaching reconfigurable accelerators on Xilinx Virtex 7 FPGA devices to Linux-based hosts. ffLink encompasses both hardware as well as flexible operating system components that allow a tailoring of the infrastructure to the specific data transfer needs of(More)
— The compiler COMRADE accepts full ANSI C and compiles it into hybrid hardware/software applications for execution on a reconfigurable adaptive computer system. After defining the model-of-computation underlying the flow, we describe the general compilation process as well as some specific techniques. These include path-based partitioning, module-generator(More)
—We propose an execution model that orchestrates the fine-grained interaction of a conventional general-purpose processor (GPP) and a high-speed reconfigurable hardware accelerator (HA), the latter having full master-mode access to memory. We then describe how the resulting requirements can actually be realized efficiently in a custom computer by hardware(More)
We introduce a new execution model for orchestrating the interaction between the conventional processor and the re-configurable compute unit in adaptive computer systems. We then characterize the architectural and OS-level requirements of implementing the model, and demonstrate how they can be achieved on a real hardware platform running under a full scale(More)
This study systematically investigated the symmetry of arm-swing kinematics in 16 normal subjects (8 right-handed, 8 left-handed) during treadmill locomotion, including forward walking (2-6 km/h), running (8 km/h), and backward walking (4 km/h). Kinematic data of both sides were compared. Significant differences between the left and right amplitudes of(More)
Rechenleistung wird klassisch durch schnellere oder zusätzliche Mikro-prozessoren gesteigert. Dagegen beschleunigen Adaptive Computersysteme (ACS) Applikationen durch eine teilweise Auslagerung in konfigurierbare Hardware. Der Compiler COMRADE übersetzt C-Quelltexte in Programme für ein ACS. Er bestimmt hierbei automatisch Regionen für eine(More)
We present experimental evidence that multiple compute-units, compiled from sequential high-level language input programs, can be merged into a reduced number of configurations for a reconfig-urable fabric (such as a modern FPGA), thus significantly reducing the reconfiguration overhead. For cases requiring multiple configurations , both heuristical and(More)
We present a low-level infrastructure for use by high-level language to hardware compiler back-ends. It consists of the highly parameterizable, technology-independent module library Modlib and the LMEM framework for localizing variables in fast on-chip memories. Modlib not only supports all high-level language operators (including memory accesses), but also(More)