Typo

missing empty line (was affecting formatting)

Clarified emulation of BF16 arithmetic and conversion instructions.

Minor typo.

Fixed non-normative text in zvfbfmin - Vector BF16 converts - to specify how narrowing conversions to BF16 could be (exactly) emulated by leveraging the round-to-odd conversion instructions.
Added some clarifications to the introduction.
Clarified the vector converts by replacing "double-width float" with "2*SEW-width format" and "single-width floar" with "SEW-width format"

New date and rev number

Fixed dependencies for Zvfbfmin.
Clarified language on widening convert.
Fixed typos.

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>
Signed-off-by: Ken Dockser <kdockser@tenstorrent.com>
Co-authored-by: Ken Dockser <kdockser@tenstorrent.com>

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: Rafael Sene <rafael@riscv.org>

apply compression for adoc pdf outputs

Asciidoctor-mathematical requires mathematical but is looking for version .1.6.16 which does not exist.  This forces the version to 1.6.14.

Signed-off-by: Bill Traynor <wmat@riscv.org>

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: jnk0le <jnk0le@hotmail.com>

Zfhmin and Zfh are now ratified. Removed the "proposed" qualifier.

Explicitly listed which extensions depend on "F" and which depend on "V"/Zve32f.

Removed superfluous note.

Removed redundant information.

Made the instruction mnemonics lowercase to match the vector and bitmanip extensions.
Removed the instruction specifications that duplicated instructions in Zfh
In the instruction descriptions, removed the minimum version and made the "Included in" a single line.
Changed the "relies on" dependencies to be nested and removed duplication.

Bumped date and rev #
Partial fixes requested by ARC. Final fixes will be soon.

These changes partially address the requested changes by the AR. The complete changes will follow soon.
Removed the pages for the instructions that already exist in  the Zfh extension: flh, fmv_h_x. fmv_x_h, fsh.

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>

rename file to allow links to work on github interface

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

We only have commitment to generate the software collateral (e.g., SPIKE, Sail, butils etc.) for the vector and BF16 extensions. There are no resources allocated to produce the software collateral for Zfbfinxmin.

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>
Signed-off-by: Ken Dockser <kdockser@tenstorrent.com>
Co-authored-by: Ken Dockser <kdockser@tenstorrent.com>

* Fixing reported typo

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

* Fix reported typo

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

* Update vfncvtbf16_f_f_w.adoc

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

---------

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

Signed-off-by: Nicolas Brunie <82109999+nibrunieAtSi5@users.noreply.github.com>

With Zfinx, Zdinx, Zhinx, and Zhinxmin there's a clear precedent that
floating point extensions should have an analogous "inx" version. As
defining such a variant is straight-forward, I feel it would be most
sensible (and efficient) to define it as part of the bfloat16 definition
process rather than leaving a gap within the ISA to be filled at a later
date.

This drafts such a definition. As the bfloat16 extensions are defined in
new documentation rather than patches to the riscv-isa-manual, I've
duplicated some explanatory text from the Zfinx chapater of the manual
so that the zfbfinxmin definition makes sense standalone. If merging
into the ISA manual, it would of course take a different form.

Signed-off-by: Rafael Sene <rafael@riscv.org>