tree c6a024cb0faa0562f44c2eab298bd5ff4f1cb017
parent 275280c2803f463b443b841eb78279dcac956ea6
author Guray Ozen <guray.ozen@gmail.com> 1669898058 +0100
committer Guray Ozen <guray.ozen@gmail.com> 1669898058 +0100

Set maximum number of threads in the thread block for CUDA target

PTX programming models provides some performance tuning directives; see https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#performance-tuning-directives The downstream compiler namely ptxas leverages these information for better register allocation or to handle other resource management that improves the performance.

As far as I understand, iree knows the number of threads for thread blocks. This PR sets `maxntid`.