Halfdocs reorg by Rmalavally · Pull Request #13 · ROCm/half

Rmalavally · 2024-05-02T18:44:12Z

No description provided.

creating docs and install folders/file

Using Half

how to convert and round half

Adding index.rst

Add conceptual

Adding examples

Updated index.rst

added tutorials

Updated TOC.yml

Added API

added metadata

pfultz2 · 2024-05-02T20:50:59Z

No documentation should be added to this repo. This is not an AMD/ROCM-maintained component. This repo is here only so we package the component as part of a rocm distribution. As such any documentation should be submitted upstream to the SVN repo here: https://sourceforge.net/p/half/code/HEAD/tree/

Rmalavally · 2024-05-02T21:30:26Z

No documentation should be added to this repo. This is not an AMD/ROCM-maintained component. This repo is here only so we package the component as part of a rocm distribution. As such any documentation should be submitted upstream to the SVN repo here: https://sourceforge.net/p/half/code/HEAD/tree/

Thanks so much, Paul. Appreciate your feedback. Do you recommend we don't publish the Half documentation on the ROCm documentation portal? I believe we have Half listed in the list of ROCm components at https://rocm.docs.amd.com/en/latest/what-is-rocm.html. Please advise.

pfultz2 · 2024-05-08T14:14:17Z

Do you recommend we don't publish the Half documentation on the ROCm documentation portal?

Yes, we shouldn't publish. We dont publish documentation for upstream LLVM either.

Rmalavally · 2024-05-08T14:19:41Z

Do you recommend we don't publish the Half documentation on the ROCm documentation portal?

Yes, we shouldn't publish. We dont publish documentation for upstream LLVM either.

Noted, @pfultz2. Thanks for clarifying.
@yhuiYH FYI

lpaoletti · 2024-05-08T19:21:34Z

docs/index.rst

+Half-Precision Floating Point library (Version 1.12.0)
+------------------------------------------------------
+
+Half is a C++ header-only library to provide an IEEE 754 conformant 16-bit half-precision floating point type along with corresponding arithmetic operators, type conversions and common mathematical functions. It aims for both efficiency and ease of use, trying to accurately mimic the behaviour of the builtin floating point types at the best performance possible.


Suggested change

Half is a C++ header-only library to provide an IEEE 754 conformant 16-bit half-precision floating point type along with corresponding arithmetic operators, type conversions and common mathematical functions. It aims for both efficiency and ease of use, trying to accurately mimic the behaviour of the builtin floating point types at the best performance possible.

Half is a C++ header-only library that provides an IEEE 754 conformant 16-bit half-precision floating point type along with corresponding arithmetic operators, type conversions, and common mathematical functions. It aims for both efficiency and ease of use, trying to accurately mimic the behavior of the built-in floating point types at the best performance possible.

And shouldn't there be a link to a github repository after the intro?

And shouldn't there be a link to a github repository after the intro?

Thanks so much, Leo. I think the decision is to not publish Half API documentation on the portal. @yhuiYH Could you please confirm?

lpaoletti · 2024-05-08T19:25:15Z

docs/install/install.md

+
+# Installing Half
+
+The library in its most recent version can be obtained from here, see the [Release Notes](changelog.html) for further information:


don't use "here" - it should be a link.
However, is the Changelog the right place

lpaoletti · 2024-05-08T19:25:54Z

docs/install/install.md

+
+The library in its most recent version can be obtained from here, see the [Release Notes](changelog.html) for further information:
+
+<ul class="tablist"><li>[Download half 1.12.0 (.zip)](http://sourceforge.net/projects/half/files/latest/download)</li></ul>


This formatting looks messed up.

lpaoletti · 2024-05-08T19:26:30Z

docs/install/install.md

+
+If you are interested in previous versions of the library, see the [SourceForge download page](http://sourceforge.net/projects/half/files/half).
+
+Comfortably enough, the library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the neccessity to build anything or link to anything.


Suggested change

Comfortably enough, the library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the neccessity to build anything or link to anything.

The library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the necessity to build anything or link to anything.

lpaoletti · 2024-05-08T19:27:58Z

docs/how-to/use-half.rst

+symbol.
+
+
+IMPLEMENTATION


This should be a heading style

lpaoletti · 2024-05-08T19:28:05Z

docs/how-to/use-half.rst

+conceptually clean half-precision implementation, to which the standard 
+mathematical functions belong, even if usually not needed.
+
+IEEE CONFORMANCE


This should be a heading style

lpaoletti · 2024-05-08T19:30:13Z

docs/how-to/use-half.rst

+Using Half
+-----------
+
+To make use of the library just include its only header file half.hpp, which defines all half-precision functionality inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This 


Suggested change

To make use of the library just include its only header file half.hpp, which defines all half-precision functionality inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This

To use the library, include its only header file half.hpp, which defines all half-precision functionality, inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This

lpaoletti · 2024-05-08T19:30:49Z

docs/how-to/use-half.rst

+-----------
+
+To make use of the library just include its only header file half.hpp, which defines all half-precision functionality inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This 
+type behaves like the builtin floating point types as much as possible, supporting the usual arithmetic, comparison and streaming operators, which makes its use pretty straight-forward:


Suggested change

type behaves like the builtin floating point types as much as possible, supporting the usual arithmetic, comparison and streaming operators, which makes its use pretty straight-forward:

type behaves like the builtin floating point types as much as possible, supporting the usual arithmetic, comparison and streaming operators, which makes its use pretty straightforward:

Rmalavally added 30 commits May 1, 2024 10:10

Create install.rst

8a7968c

creating docs and install folders/file

Update install.rst

d258400

Create use-half.rst

c8920ec

Using Half

Create convert-round.rst

337890e

how to convert and round half

Create implement.rst

3b5427b

Update implement.rst

e31e97b

Update convert-round.rst

d81b75c

Create index.rst

0297d47

Adding index.rst

Update and rename install.rst to install.md

d103640

Create understand-half.rst

4368d36

Add conceptual

Create half.hpp

a85907c

Adding examples

Add files via upload

bb3f2b0

Add files via upload

cfbd274

Merge branch 'ROCm:rocm' into halfdocs_reorg

61931da

Update index.rst

286232a

Updated index.rst

Update index.rst

35c0299

added tutorials

Update _toc.yml.in

b24a41d

Updated TOC.yml

Update implement.rst

440dfeb

Update index.rst

3fce1c4

Update index.rst

8163249

Update _toc.yml.in

f2b321b

Added API

Update _toc.yml.in

c8d94b9

Update index.rst

3e2a4da

Update index.rst

d182521

Update understand-half.rst

24e1b22

added metadata

Update convert-round.rst

29f2564

Update implement.rst

45cfa89

Update use-half.rst

0ff5f85

Update _toc.yml.in

b0a2852

Update _toc.yml.in

58eba51

Rmalavally added 10 commits May 2, 2024 11:18

Update index.rst

33c432f

Create half-api.rst

52d49fc

Update index.rst

0fd13ab

Update index.rst

c4fcccc

Update index.rst

08f7c2a

Update index.rst

b1936db

Update half-api.rst

7013630

Update index.rst

89dc011

Update _toc.yml.in

6b29e1a

Update half-api.rst

a8587a1

lpaoletti reviewed May 8, 2024

View reviewed changes

docs/how-to/use-half.rst

symbol.

IMPLEMENTATION

Copy link

lpaoletti May 8, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should be a heading style

lpaoletti reviewed May 8, 2024

View reviewed changes

	Half is a C++ header-only library to provide an IEEE 754 conformant 16-bit half-precision floating point type along with corresponding arithmetic operators, type conversions and common mathematical functions. It aims for both efficiency and ease of use, trying to accurately mimic the behaviour of the builtin floating point types at the best performance possible.
	Half is a C++ header-only library that provides an IEEE 754 conformant 16-bit half-precision floating point type along with corresponding arithmetic operators, type conversions, and common mathematical functions. It aims for both efficiency and ease of use, trying to accurately mimic the behavior of the built-in floating point types at the best performance possible.


		# Installing Half

		The library in its most recent version can be obtained from here, see the [Release Notes](changelog.html) for further information:


		The library in its most recent version can be obtained from here, see the [Release Notes](changelog.html) for further information:

		<ul class="tablist"><li>[Download half 1.12.0 (.zip)](http://sourceforge.net/projects/half/files/latest/download)</li></ul>


		If you are interested in previous versions of the library, see the [SourceForge download page](http://sourceforge.net/projects/half/files/half).

		Comfortably enough, the library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the neccessity to build anything or link to anything.

	Comfortably enough, the library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the neccessity to build anything or link to anything.
	The library consists of just a single header file containing all the functionality, which can be directly included by your projects, without the necessity to build anything or link to anything.

	To make use of the library just include its only header file half.hpp, which defines all half-precision functionality inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This
	To use the library, include its only header file half.hpp, which defines all half-precision functionality, inside the 'half_float' namespace. The actual 16-bit half-precision data type is represented by the 'half' type. This

	type behaves like the builtin floating point types as much as possible, supporting the usual arithmetic, comparison and streaming operators, which makes its use pretty straight-forward:
	type behaves like the builtin floating point types as much as possible, supporting the usual arithmetic, comparison and streaming operators, which makes its use pretty straightforward:

Conversation

Rmalavally commented May 2, 2024

Uh oh!

pfultz2 commented May 2, 2024

Uh oh!

Rmalavally commented May 2, 2024

Uh oh!

pfultz2 commented May 8, 2024

Uh oh!

Rmalavally commented May 8, 2024

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants