GitLab

Add exclusive and reverse modes to gpu implementation of prefix_scan_sum, which completes support for ONNX op CumSum

change max number of groups in a kernel to 1B for greater performance

Update the base version of clang-format from 5.0 to 10.0

Changed the number of threads in a block from 256 to 128
Increased the max number of blocks in the kernel from 256 to 1M.
For the case that the axis is the last dimension, we removed the computation of index since it is not required.

With these change, we can get about 2x speedup compared to the develop branch for the softmax op used in the BertSquad model.