Implement SPV_INTEL_bfloat16_arithmetic (#3290)
The extension relaxes rules for bf16 type allowing to use it in some
arithmetic operations.
Spec is available here:
https://github.com/intel/llvm/pull/18352
Co-authered by: Michael Aziz <michael.aziz@intel.com>
---------
Signed-off-by: Sidorov, Dmitry <dmitry.sidorov@intel.com>
Original commit:
https://github.com/KhronosGroup/SPIRV-LLVM-Translator/commit/8242eb7a4ab8204