[all-commits] [llvm/llvm-project] 99f527: [APFloat] Add APFloat support for E8M0 type (#107127)

[Durgadoss R via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 99f527d2807b5a14dc7ee64d15405f09e95ee9f2
      https://github.com/llvm/llvm-project/commit/99f527d2807b5a14dc7ee64d15405f09e95ee9f2
  Author: Durgadoss R <durgadossr at nvidia.com>
  Date:   2024-10-02 (Wed, 02 Oct 2024)

  Changed paths:
    M llvm/include/llvm/ADT/APFloat.h
    M llvm/lib/Support/APFloat.cpp
    M llvm/unittests/ADT/APFloatTest.cpp

  Log Message:
  -----------
  [APFloat] Add APFloat support for E8M0 type (#107127)

This patch adds an APFloat type for unsigned E8M0 format. This format is
used for representing the "scale-format" in the MX specification:
(section 5.4)

https://www.opencompute.org/documents/ocp-microscaling-formats-mx-v1-0-spec-final-pdf

This format does not support {Inf, denorms, zeroes}. Like FP32, this
format's exponents are 8-bits (all bits here) and the bias value is 127.
However, it differs from IEEE-FP32 in that the minExponent is -127
(instead of -126). There are updates done in the APFloat utility
functions to handle these constraints for this format.

* The bias calculation is different and convertIEEE* APIs are updated to
handle this.
* Since there are no significand bits, the isSignificandAll{Zeroes/Ones}
methods are updated accordingly.
* Although the format does not have any precision, the precision bit in
the fltSemantics is set to 1 for consistency with APFloat's internal
representation.
* Many utility functions are updated to handle the fact that this format
does not support Zero.
* Provide a separate initFromAPInt() implementation to handle the quirks
of the format.
* Add specific tests to verify the range of values for this format.

Signed-off-by: Durgadoss R <durgadossr at nvidia.com>



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications