Imperial College London > Talks@ee.imperial > CAS Talks > (FPT Preview) Co-optimisation of Datapath and Memory in Outer Loop Pipelining
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
(FPT Preview) Co-optimisation of Datapath and Memory in Outer Loop PipeliningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact George A Constantinides. When targeting algorithms to FPGA based systems both the array to memory assignment and the selection of data reuse structures must often be considered to maximise performance. In this work we present an Integer Linear Programming formulation for the combined problem of array to memory assignment and data reuse selection. We include a number of cost functions to minimise during memory optimisation and show how these optimisations can be integrated into a loop pipelining framework to iteratively update the memory subsystem during scheduling. By co-optimising the datapath (schedule) and memory subsystem we are able to produce near optimal (fastest) solutions, with an upper bound on the distance from the optimal solution. Our results show an average speedup of up to 4x over a non-optimised memory subsystem when integrated into an existing outer loop pipelining framework. This talk is part of the CAS Talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsisn_talks@ee.imperial Type the title of a new list here Type the title of a new list hereOther talksControlling Spatially Invariant Distributed Parameter Systems using Arrays of Actuators and Sensors Engineering Education at a Crossroads - How Changes in the Technology and in the Marketplace are Forcing a New Reform in Engineering Education |