Vulkan-Docs/appendices/VK_KHR_shader_float16_int8.txt

54 lines
1.7 KiB
Plaintext

// Copyright (c) 2014-2019 Khronos Group. This work is licensed under a
// Creative Commons Attribution 4.0 International License; see
// http://creativecommons.org/licenses/by/4.0/
include::meta/VK_KHR_shader_float16_int8.txt[]
*Last Modified Date*::
2018-03-07
*IP Status*::
No known IP claims.
*Interactions and External Dependencies*::
- This extension interacts with `<<VK_KHR_8bit_storage>>`
- This extension interacts with `<<VK_KHR_16bit_storage>>`
- This extension interacts with `<<VK_KHR_shader_float_controls>>`
*Contributors*::
- Alexander Galazin, Arm
- Jan-Harald Fredriksen, Arm
- Jeff Bolz, NVIDIA
- Graeme Leese, Broadcom
- Daniel Rakos, AMD
=== Description
The `VK_KHR_shader_float16_int8` extension allows use of 16-bit
floating-point types and 8-bit integer types in shaders for arithmetic
operations.
It introduces two new optional features pname:shaderFloat16 and
pname:shaderInt8 which directly map to the code:Float16 and the code:Int8
SPIR-V capabilities.
The `VK_KHR_shader_float16_int8` extension also specifies precision
requirements for half-precision floating-point SPIR-V operations.
This extension doesn't enable use of 8-bit integer types or 16-bit
floating-point types in any <<interfaces-iointerfaces, shader input and
output interfaces>> and therefore doesn't supersede the
`<<VK_KHR_8bit_storage>>` or `<<VK_KHR_16bit_storage>>` extensions.
=== New Enum Constants
* Extending elink:VkStructureType:
** ename:VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FLOAT16_INT8_FEATURES_KHR
=== New Structures
* slink:VkPhysicalDeviceFloat16Int8FeaturesKHR
=== New Functions
* None
=== Version History
* Revision 1, 2018-03-07 (Alexander Galazin)
- Initial draft