FHPC 2016- Proceedings of the 5th International Workshop on Functional High-Performance Computing

Full Citation in the ACM Digital Library

SESSION: Keynote

From identification of parallelizability to derivation of parallelizable codes

SESSION: Domain-Specific Languages

Icicle: write once, run once

Using fusion to enable late design decisions for pipelined computations

SESSION: Code Generation

Automatic generation of efficient codes from mathematical descriptions of stencil computation

JIT costing adaptive skeletons for performance portability


Low-level functional GPU programming for parallel algorithms

APL on GPUs: a TAIL from the past, scribbled in Futhark

SESSION: Streaming and Dataflow

Streaming nested data parallelism on multicores

Polarized data parallel data flow

SESSION: Graph Processing

s6raph: vertex-centric graph processing framework with functional interface