echuraev commented on a change in pull request #7299: URL: https://github.com/apache/tvm/pull/7299#discussion_r588836309
########## File path: python/tvm/relay/op/contrib/bnns.py ########## @@ -0,0 +1,327 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# pylint: disable=invalid-name, unused-argument +"""BNNS library supported operators. +Is a part of Accelerate framework on macOS/iOS platforms. Apple provide several APIs +to handle tensor processing. Particularly: + * BNNS (basic neural ) + * vDSP (1D and 2D tensor processing) +""" +import math +import tvm.ir + +from tvm.relay import transform +from tvm.relay.expr import const +from tvm.relay.build_module import bind_params_by_name + +from .register import register_pattern_table, get_pattern_table +from ...dataflow_pattern import wildcard, is_op, is_expr + + +def partition_for_bnns(mod, params=None): + """Partition the graph greedily offloading supported + operators to BNNS. + + Parameters + ---------- + mod : Module + The module to run passes on. + params : Optional[Dict[str, NDArray]] + Constant input parameters. + + Returns + ------- + ret : annotated and partitioned module. + """ + if params: + mod["main"] = bind_params_by_name(mod["main"], params) + + seq = tvm.transform.Sequential( + [ + transform.InferType(), + transform.FoldConstant(), + transform.FoldScaleAxis(), + transform.DynamicToStatic(), + transform.AlterOpLayout(), + # TODO(apeskov): WA. AlterOpLayout call lead to constants shape transformation + # Some expand_dims op may appears after constants. It breaks BNNS fusing. + # So we have to call FoldConstant right before bnns composite passes. + transform.FoldConstant(), + transform.MergeComposite(get_pattern_table("bnns")), + transform.AnnotateTarget("bnns"), + # If you no need in per layer performance statistic you can + # uncomment next line + # transform.MergeCompilerRegions(), Review comment: No, it doesn't have effect on performance. But if we use this transformation, then it will be more difficult to compare per layer statistic with initial topology due to some kernels will be merged. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
