diff --git a/python/dune/perftool/logging.conf b/python/dune/perftool/logging.conf index 95297e7d7129e4846b9848c152a4b4a6c21d55c2..e89555eddae02f3e5ea251e42ad2b70ded41e7a6 100644 --- a/python/dune/perftool/logging.conf +++ b/python/dune/perftool/logging.conf @@ -1,5 +1,5 @@ [loggers] -keys=root,dune.perftool.pdelab.localoperator +keys=root,dune.perftool.pdelab.localoperator,dune.perftool.sumfact.vectorization [handlers] keys=consoleHandler @@ -16,6 +16,12 @@ handlers=consoleHandler qualname=dune.perftool.pdelab.localoperator propagate=0 +[logger_dune.perftool.sumfact.vectorization] +level=INFO +handlers=consoleHandler +qualname=dune.perftool.sumfact.vectorization +propagate=0 + [handler_consoleHandler] class=StreamHandler formatter=simpleFormatter diff --git a/python/dune/perftool/sumfact/vectorization.py b/python/dune/perftool/sumfact/vectorization.py index d5e855291816e27cc6627591a54bfa32b43bc1a6..08e07782c41e9a9928e9d06854ea7ef80a4a3414 100644 --- a/python/dune/perftool/sumfact/vectorization.py +++ b/python/dune/perftool/sumfact/vectorization.py @@ -1,5 +1,7 @@ """ Sum factorization vectorization """ +import logging + from dune.perftool.loopy.vcl import get_vcl_type_size from dune.perftool.loopy.symbolic import SumfactKernel, VectorizedSumfactKernel from dune.perftool.generation import (generator_factory, @@ -136,10 +138,14 @@ def decide_vectorization_strategy(): Note that the vectorization of the quadrature loop is independent of this, as it is implemented through a post-processing (== loopy transformation) step. """ + logger = logging.getLogger(__name__) + from dune.perftool.generation import retrieve_cache_items sumfacts = [i for i in retrieve_cache_items("kernel_default and sumfactnodes")] sfdict = {} + logger.debug("decide_vectorization_strategy: Found {} sum factorization nodes".format(len(sumfacts))) + if get_option("vectorize_grads"): # Currently we base our idea here on the fact that we only group sum # factorization kernels with the same input.