Analysis of quasi-static scheduling techniques in a virtualized reconfigurable machine

Abstract

The SCORE compute model uses fixed-size, virtual compute and memory pages connected by stream links to capture the definition of a computation abstracted from the detailed size of the physical hardware.When the number of physical compute pages is smaller than the number of virtual compute pages in the abstract computation graph, the design is time-multiplexed onto the available physical hardware. A key component of this strategy is an automatic scheduler that selects the temporal sequencing of virtual resources onto the physical device. We describe a quasistatic scheduling strategy that retains the full semantic power of the dynamic SCORE flow graph while taking advantage of static scheduling techniques at program load time to hoist most of the computational work out of the inner scheduling loops. This strategy reduces online scheduling work per reconfiguration epoch by an order of magnitude. In addition, a more global perspective available from offline-scheduling improves schedule quality, resulting in a net reduction of total execution time by 46-81%.

Design Patterns for Reconfigurable Computing

“…In the simplest case, each subgraph is run for a fixed length of time before being swapped. However, for dynamic tasks, it is often useful to monitor buffers and dynamically identify events which motivate reconfiguration [9].…”

“…QUEUES WITH BACK-PRESSURE are naturally employed between portions of the graph which are not co-resident on the platform, and they are often useful between co-resident portions to smooth out dynamic flow rate or delay effects. PARALLEL-PREFIX RE-DUCTIONS are natural for quickly determing when reconfiguration is appropriate[9].…”