IEEE Micro · 2014 · 19 citations · 20 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureField-programmable Gate ArraysParallel ComputingControl Unit DesignField-programmable Gate Array ArchitectureHardware AccelerationInterprocess CommunicationParallel ArchitecturesParallel Computer ArchitectureBranch InstructionsDynamic Instruction SchedulingExecution Unit OrganizationHardware Isolation MechanismsParallel Spatial ProcessingProcessing Element DesignReactivity
In this article, the authors present triggered instructions, a novel control paradigm for arrays of processing elements (PEs) aimed at exploiting spatial parallelism. Triggered instructions completely eliminate the program counter and allow programs to transition concisely between states without explicit branch instructions. They also allow efficient reactivity to inter-PE communication traffic. The approach provides a unified mechanism to avoid overserialized execution, essentially achieving the effect of techniques such as dynamic instruction reordering and multithreading, which each require distinct hardware mechanisms in a traditional sequential architecture.
20
The Landscape of Parallel Computing Research: A View from Berkeley
Krste Asanović, Ras Bodik, Bryan Catanzaro et al. · 2006 · 2K citations
Engineering, Computer Science, High-performance Computing +17
Parallel program design: a foundation
Chris Jesshope · Microprocessors and Microsystems · 1989 · 845 citations
Garp: a MIPS processor with a reconfigurable coprocessor
John R. Hauser, John Wawrzynek · 2002 · 794 citations