The Polyhedral Benchmark Suite Targeting Multicore CPUs, GPUs, and Accelerators

PolyBench is a collection of benchmarks containing static control parts. The purpose is to uniformize the execution and monitoring of kernels, typically used in past and current publications.

We have modified the original PolyBench Suite to run on GPUs and accelerators by using different programming languages.

Features:

• A single file, tunable at compile-time, used for the kernel instrumentation.
• Non-null data initialization, and live-out data dump.
• Syntactic constructs to prevent any dead code elimination on the kernel.
• Parametric loop bounds in the kernels, for general-purpose implementation.
• Clear kernel marking, using #pragma scop and #pragma endscop delimiters.