Halfdocs reorg #13
Halfdocs reorg #13
Conversation
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
|
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. |
Yes, we shouldn't publish. We dont publish documentation for upstream LLVM either. |
| 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. |
There was a problem hiding this comment.
| 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. |
There was a problem hiding this comment.
And shouldn't there be a link to a github repository after the intro?
There was a problem hiding this comment.
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?
|
|
||
| # Installing Half | ||
|
|
||
| The library in its most recent version can be obtained from here, see the [Release Notes](changelog.html) for further information: |
There was a problem hiding this comment.
don't use "here" - it should be a link.
However, is the Changelog the right place
|
|
||
| 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. |
There was a problem hiding this comment.
| 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. |
| symbol. | ||
|
|
||
|
|
||
| IMPLEMENTATION |
| conceptually clean half-precision implementation, to which the standard | ||
| mathematical functions belong, even if usually not needed. | ||
|
|
||
| IEEE CONFORMANCE |
| 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 |
There was a problem hiding this comment.
| 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 |
| ----------- | ||
|
|
||
| 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: |
There was a problem hiding this comment.
| 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: |
No description provided.