HPVM v1.0 released

HPVM ("heterogeneous parallel virtual machine") is a compiler for targets like GPUs and FPGAs based on LLVM; the 1.0 release is available now. "This release is a major addition to our first release (version 0.5), adding support for linear algebra tensor operations, Pytorch and Keras frontends, approximations for convolution operators, and an efficient and flexible framework for approximation tuning. Our novel approximation-tuner automatically selects approximation knobs for individual tensor operations and selects configurations that maximize a (configurable) performance objective."

Full Story (comments: 5)