P4
- Add a new HalffloatVector type in addition to existing primitive vector types, maintaining operation parity with the FloatVector type.
- Add necessary inline expander support.
- Enable intrinsification for a few vector operations, namely ADD/SUB/MUL/DIV/MAX/MIN/FMA.
- Use existing Float16 vector IR and backend support.
The idea here is to first be on par with Float16 auto-vectorization support.
- Add necessary inline expander support.
- Enable intrinsification for a few vector operations, namely ADD/SUB/MUL/DIV/MAX/MIN/FMA.
- Use existing Float16 vector IR and backend support.
The idea here is to first be on par with Float16 auto-vectorization support.