Optimize the MultiplyMe and DivMe functions when operate the scalar tensors.

1. Fix the bug in DivMe function which cannot handle the scalar tensor and broadcast case.
2. Clean the codes.
3. Fix minor errors.

1. Fix the bug in SubMe function which cannot handle the scalar tensor and broadcast case.
2. Clean the codes.

Fix the bug in SumMe function which cannot handle the scalar tensor and broadcast case.

1. Fix the bug in MultiplyMe function which cannot handle the scalar tensor and broadcast case.
2. Add broadcast multiply unit test.

Fix the bugs in FlushToMem functions.

Fix the bugs in FlushToMem functions.

1. Fix the bugs in SetDevice functions and FlushToMem functions.
2. Fix the minor errors.

1. CPU Support for Gather function.
2. Fix the bugs in GPU Gather.
2. Minor error fixed.

Update the link in manual.

Update the manual.

Update the Transformer codes.

1. Clean the codes.
2. Fix minor errors.

Clean the codes.

1. Fix minor errors.
2. Add some annotations.

Clean the codes and fix some warning issues.

Clean the codes.

Clean the codes.

1. Supporting efficient propagate and gradient accumulation for backward functions.
2. Update the setData functions.
3. Clean the codes.

1. Add boundary check for Gather function.
2. Minor error fixed.

Fix the bugs in CUDA 10.

Minor error fixed.

Fix the dimension bugs in Stack functions.

Minor error fixed.

Minor error fixed.

1. Fix the bugs for MatrixMul functions which may cause nan in some cases. (IMPORTANT)
2. Fix the minor errors.

1. Offer global setting for enableGrad.
2. Update XList.
3. Minor error fixed.

Minor error fixed.

Fix the GPU bug in Clip function.

1. Support X_INT dataType for Clip and ScaleAndShift function.
2. Minor error fixed.

1. Support X_INT dataType for Sum function.
2. Minor error fixed.

1. Support to copy parts of source tensor to parts of target tensor.
2. New unit test for CopyIndex function.

Add a new parameter isSorted in TopK function to sort the items in the top-k pool.