[GitHub] [incubator-tvm] cbalint13 commented on a change in pull request #6675: [QNN] Optimize requantize for power of 2 and bug in dequantize

[GitBox <gi...@apache.org>]

cbalint13 commented on a change in pull request #6675:
URL: https://github.com/apache/incubator-tvm/pull/6675#discussion_r503732613



##########
File path: src/relay/qnn/op/requantize.cc
##########
@@ -155,17 +155,20 @@ Expr RequantizeLower(const Expr& input_tensor, const Expr& input_scale,
     if (!IsEqualScalar(input_scale, output_scale)) {
       int32_t fixed_point_multiplier, shift;
       std::tie(fixed_point_multiplier, shift) = GetFixedPointMultiplierShift(double_multiplier);
-
       const bool is_upward_rounding = (param->rounding == "UPWARD");
 
-      // When using upward rounding (i.e., x.5 rounded to x+1), leverage
-      // the FixedPointMultiply operator
-      scaled_int32_t =
-          (is_upward_rounding
-               ? FixedPointMultiply(scaled_int32_t, fixed_point_multiplier, shift)
-               : FixedPointMultiplyToNearest(scaled_int32_t, double_multiplier, input_shape));
+      if (is_upward_rounding && fixed_point_multiplier == (1 << 30)) {

Review comment:
       @anijain2305 , can add a small one line comment regarding (1<<30) ? These days aside from ```float32``` many other types of ```float``` floats around. 




----------------------------------------------------------------
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:
users@infra.apache.org