[v1] Implement blfoat16 in softfloat

[RFC PATCH 0/8] Implement blfoat16 in softfloat

LIU Zhiwei posted 8 patches 3 years, 9 months ago

Diff against v1
Download series mbox

Test checkpatch passed

Test docker-mingw@fedora passed

Test FreeBSD passed

Test docker-quick@centos7 passed

Patches applied successfully (tree, apply log)
git fetch https://github.com/patchew-project/qemu tags/patchew/20200712234521.3972-1-zhiwei_liu@c-sky.com

Maintainers: Peter Maydell <peter.maydell@linaro.org>, "Alex Bennée" <alex.bennee@linaro.org>, Aurelien Jarno <aurelien@aurel32.net>

There is a newer version of this series

fpu/softfloat-specialize.inc.c |  50 ++++-
fpu/softfloat.c                | 393 ++++++++++++++++++++++++++++++++-
include/fpu/softfloat-types.h  |   8 +
include/fpu/softfloat.h        | 133 +++++++++++
4 files changed, 577 insertions(+), 7 deletions(-)

Expand all Fold all

[RFC PATCH 0/8] Implement blfoat16 in softfloat

Posted by LIU Zhiwei 3 years, 9 months ago

As bfloat16 is more and more popular in many archs, implement bfloat16
interfaces in softfloat, so that archs can add their bfloat16 insns
based on the blfoat16 interfaces here.

This patch set is more copy of float16 than really define new
interfaces or implementations.

Any thoughts are welcomed!

LIU Zhiwei (8):
  fpu/softfloat: fix up float16 nan recognition
  fpu/softfloat: use the similiar logic to recognize sNaN and qNaN
  fpu/softfloat: add FloatFmt for bfloat16
  fpu/softfloat: add pack and unpack interfaces for bfloat16
  fpu/softfloat: define brain floating-point types
  fpu/softfloat: define operation for bfloat16
  fpu/softfloat: define covert operation for bfloat16
  fpu/softfloat: define misc operation for bfloat16

 fpu/softfloat-specialize.inc.c |  50 ++++-
 fpu/softfloat.c                | 393 ++++++++++++++++++++++++++++++++-
 include/fpu/softfloat-types.h  |   8 +
 include/fpu/softfloat.h        | 133 +++++++++++
 4 files changed, 577 insertions(+), 7 deletions(-)

-- 
2.23.0