This is a patch release containing the following changes to v2.1:
- Improved performance of fp32 depthwise convolution with plain activations on CPU (762a9c7)
- Worked around internal compiler error in GCC 7.3.1 when building with
--std=c++14(f637501) - Fixed memory leaks in batchnorm and gemm implementations (2ea5385, 4f3a7cf)
- Addressed several issues in benchdnn and gtests (bb7bdb4, 0e04cc2, d7df8d2, a59354f)