Fix the bugs in ReduceMax and its related functions.

Support fp16 data type for more operations and fix the minor errors.  (Don't use this! It's an incomplete version)

Support fp16 data type for more operations and fix the minor errors.  (Don't use this! It's an incomplete version)

Update the minimum version of CUDA from 9.0 to 9.2.

Support fp16 data type for more operations and fix the minor errors.  (Don't use this! It's an incomplete version)

Update the version number which is synchronized with the github version.

1. Support KB size for memory pool.
2. Clean the codes: 1000000 -> 1024 * 1024.

1. Fix the mistakes in manual.
2. Fix the minor errors in Stack and LogSoftmax functions.

1. Fix the mistakes in manual.
2. Fix the minor errors in Normalize and ScaleAndShift functions.

1. Fix the mistakes in manual.
2. Fix the bug in the link process of ConvertDataType function.

1. Fix the mistakes in manual. By the way, I have to say there are so many mistakes in the manual. I'm shocked it has been checked a lot of times, but why they are still be there. No one care about that? Really???
2. Clean the codes.

1. Offer CMakeLists.txt to compile the NiuTensor.
2. Update the manuals for CMake.

1. Call the Scale or Shift functions when the parameter shift is 0.0F or scale is 1.0F.
2. Add the unit test for ScaleAndShift for the cases which parameter shift is 0.0F or scale is 1.0F.

Use the _CheckData without tolerance in some unit test to speedup the test process.

1. Use the _CheckData with tolerance in unit test to avoid the bug in "0.0F != -0.0F" case.
2, Clean the codes.

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.