arch-arm: Add FP16 support and other primitives to fplib
This changeset:
- extends fplib to support emulation of half-precision floating-point
(FP16) operations;
- extends fplib to support additional primitives introduced by the Arm
Scalable Vector Extension (SVE) (fplibExpa, fplibScale,
fplibTrigMAdd, fplibTrigSMul, fplibTrigSSel);
- adds the FZ16 bit to FPSCR;
- cleans up fplib code by replacing constants with preprocessor macros
and by adding inline functions to recognise NaNs and infinities.
Change-Id: If8fdb2a5824b478c8310bbc126ec60cc1105f135
Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/13044
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>