Add support for AMD GPUs using HIP/ROCm

[sfantao]

Add support in KALDI for AMD GPUs by hipifying the existing CUDA implementation.

The implementation comprises the following:

• Add the option --use-rocm and --rocm-targets= to the configuration script.
• Add hip_64bit.mk build file to add the relevant HIP/ROCm build flags. IS_GPU_BUILD, CUDA and ROCM variables guard sections meant to any GPU build, CUDA only and ROCm only, respectively.
• Include hipify.h header to control the "hipification" of the code allowing to keep existing CUDA implementation largely untouched by mapping different APIs and variables to its HIP counterparts.
• The source code uses __IS_HIP_COMPILE__ to guard HIP specific sessions.
• The AMD GPUs arch is being feature-mapped to CUDA 8.0 compute capability which is largely true and sufficient for the code.
• Replace hardcoded warp/wavefront sizes and thread block limits so they can be configured properly to the target GPU.

ROCm builds can be completed with (assuming existing python environment with requirements), e.g.:

cd <kaldi source>/src
./configure \
    --shared \
    --debug-level=0 \
    --use-cuda=no \
    --with-cudadecoder \
    --use-rocm \
    --rocm-targets="gfx90a" \
    --mkl-root="$MKL_ROOT"

make -j clean depend
make V=1 VERBOSE=1 \
  EXTRA_CXXFLAGS="-g -ggdb -O3 -DNDEBUG -Wno-unused-variable -Wno-unused-but-set-variable" \
  EXTRA_ROCM_FLAGS="-g -ggdb -O3 -DDEBUG -Wno-unused-variable -Wno-unused-but-set-variable" \
  EXTRA_LDFLAGS="" -j 

This PR was tested successfully on AMD MI250x and NVIDIA A100 hardware.

[danpovey]

Thanks a lot for this! Sicne the tests run, I'll merge and if users have problems we can address them at that time.