ZhennanQin commented on a change in pull request #12530: Implement mkldnn convolution fusion and quantization. URL: https://github.com/apache/incubator-mxnet/pull/12530#discussion_r220032476
########## File path: src/executor/attach_op_execs_pass.cc ########## @@ -159,9 +159,13 @@ class StatefulComputeExExecutor : public OpExecutor { op_ctx.run_ctx = rctx; #if MXNET_USE_MKLDNN == 1 InvalidateOutputs(out_array, req); - CreateDefaultInputs(in_array, &in_array_fallback); - fcompute_(state_, op_ctx, in_array_fallback, req, out_array); - return; + // TODO(alex): (MXNET-847) Remove this fallback feature after subgraph implemented + const auto is_mkldnn = Op::GetAttr<bool>("TIsMKLDNN"); + if (!is_mkldnn.get(attrs_.op, false)) { + CreateDefaultInputs(in_array, &in_array_fallback); + fcompute_(state_, op_ctx, in_array_fallback, req, out_array); + return; + } Review comment: OK. I will move this part out. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services