PPoPP 2016
Sat 12 - Wed 16 March 2016 Barcelona, Spain
Mon 14 Mar 2016 12:00 - 12:25 at Mallorca+Menorca - Language Implementation & DSL Chair(s): Michael D. Bond

Many image processing tasks are naturally expressed as a pipeline of small computational kernels known as stencils. Halide is a popular domain-specific language and compiler designed to implement image processing algorithms. Halide uses simple language constructs to express what to compute and a separate scheduling co-language for expressing when and where to perform the computation. This approach has demonstrated performance comparable to or better than hand-optimized code. Until now, however, Halide has been restricted to parallel shared memory execution, limiting its performance for memory-bandwidth-bound pipelines or large-scale image processing tasks.

We present an extension to Halide to support distributed-memory parallel execution of complex stencil pipelines. These extensions compose with the existing scheduling constructs in Halide, allowing expression of complex computation and communication strategies. Existing Halide applications can be distributed with minimal changes, allowing programmers to explore the tradeoff between recomputation and communication with little effort. Approximately 10 new of lines code are needed even for a 200 line, 99 stage application. On nine image processing benchmarks, our extensions give up to a 1.4× speedup on a single node over regular multithreaded execution with the same number of cores, by mitigating the effects of non-uniform memory access. The distributed benchmarks achieve up to 18× speedup on a 16 node testing machine and up to 57× speedup on 64 nodes of the NERSC Cori supercomputer.

Mon 14 Mar
Times are displayed in time zone: (GMT+01:00) Greenwich Mean Time : Belfast change

11:35 - 12:50: Main conference - Language Implementation & DSL at Mallorca+Menorca
Chair(s): Michael D. BondOhio State University
PPoPP-2016-papers11:35 - 12:00
Flavio Cruz, Ricardo RochaFCUP, Universidade do Porto, Portugal, Seth Copen GoldsteinCarnegie Mellon University
Link to publication DOI
PPoPP-2016-papers12:00 - 12:25
Link to publication DOI
PPoPP-2016-papers12:25 - 12:50
Ryan R. NewtonIndiana University, Omer S. AgacanIndiana University, Peter FoggedX, Sam Tobin-HochstadtIndiana University
Link to publication DOI