jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r188510242
##########
File path: src/operator/quantization/requantize-inl.h
##########
@@ -68,6 +68,24 @@ inline bool RequantizeType(const nnvm::NodeAttrs& attrs,
return (*in_attrs)[0] != -1;
}
+bool RequantizeStorageType(const nnvm::NodeAttrs& attrs,
+ const int dev_mask,
+ DispatchMode* dispatch_mode,
+ std::vector<int> *in_attrs,
+ std::vector<int> *out_attrs) {
+#if MXNET_USE_MKLDNN == 1
+ *dispatch_mode = DispatchMode::kFComputeEx;
+ if (dev_mask == mshadow::cpu::kDevMask)
+ *dispatch_mode = DispatchMode::kFComputeEx;
+ else
+#endif
+ *dispatch_mode = DispatchMode::kFCompute;
Review comment:
Please simplify dispatch_mode set logic here to ease code readability, you
can refer to current quantize/dequantize implementation.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
