Abstract

We address the compiler correctness problem for many-core systems through novel applications of fuzz testing to OpenCL compilers. Focusing on two methods from prior work, random differential testing and testing via equivalence modulo inputs (EMI), we present several strategies for random generation of deterministic, communicating OpenCL kernels, and an injection mecha- nism that allows EMI testing to be applied to kernels that oth- erwise exhibit little or no dynamically-dead code. We use these methods to conduct a large, controlled testing campaign with re- spect to 21 OpenCL (device, compiler) configurations, covering a range of CPU, GPU, accelerator, FPGA and emulator implementa- tions. Our study provides independent validation of claims in prior work related to the effectiveness of random differential testing and EMI testing, proposes novel methods for lifting these techniques to the many-core setting and reveals a significant number of OpenCL compiler bugs in commercial implementations.