kawakami-k
The tests are already implemented in [test/mov.cpp](https://github.com/fujitsu/xbyak_aarch64/blob/fjdev/test/mov.cpp) and [test/mov_imm.cpp](https://github.com/fujitsu/xbyak_aarch64/blob/fjdev/test/mov_imm.cpp), but they are not built in CI.
Currently, there is no test patterns for instructions of the A64 system instruction class.
This PR enhances the CPU feature detection function so as to detect [Arm SVE architecture](https://developer.arm.com/Architectures/SVE). It also includes vectorized functions for SVE that is implemented similarly to AVX/AVX2/ASIMD. The regression...
Recent versions of Python, for example 3.9.0, seem to get an error during the building of XED incorporated by dnnl_aarch64. Fortunately, the latest version of the original XED can be...
using TF+DNNL with a simple imagenet/resnet50 benchmark fails , see the following error output: ``` Train on 32 samples bad err=17 in Xbyak::Error terminate called after throwing an instance of...
The method of acquiring cache size varies depending on OS. In some cases, there is no way to obtain cache size from application software running on a guest OS different...
# Description This PR fixes https://github.com/oneapi-src/oneDNN/issues/1806 # Checklist ## General - [x] Do all unit and benchdnn tests (`make test` and `make test_benchdnn_*`) pass locally for each commit? - [x]...