1  // Copyright (c) 2014-2019 Khronos Group. This work is licensed under a
 2  // Creative Commons Attribution 4.0 International License; see
 3  // http://creativecommons.org/licenses/by/4.0/
 4  
 5  include::meta/VK_KHR_shader_float16_int8.txt[]
 6  
 7  *Last Modified Date*::
 8      2018-03-07
 9  *IP Status*::
10      No known IP claims.
11  *Interactions and External Dependencies*::
12    - This extension interacts with `<<VK_KHR_8bit_storage>>`
13    - This extension interacts with `<<VK_KHR_16bit_storage>>`
14    - This extension interacts with `<<VK_KHR_shader_float_controls>>`
15  *Contributors*::
16      - Alexander Galazin, Arm
17      - Jan-Harald Fredriksen, Arm
18      - Jeff Bolz, NVIDIA
19      - Graeme Leese, Broadcom
20      - Daniel Rakos, AMD
21  
22  === Description
23  
24  The `VK_KHR_shader_float16_int8` extension allows use of 16-bit
25  floating-point types and 8-bit integer types in shaders for arithmetic
26  operations.
27  
28  It introduces two new optional features pname:shaderFloat16 and
29  pname:shaderInt8 which directly map to the code:Float16 and the code:Int8
30  SPIR-V capabilities.
31  The `VK_KHR_shader_float16_int8` extension also specifies precision
32  requirements for half-precision floating-point SPIR-V operations.
33  This extension does not enable use of 8-bit integer types or 16-bit
34  floating-point types in any <<interfaces-iointerfaces, shader input and
35  output interfaces>> and therefore does not supersede the
36  `<<VK_KHR_8bit_storage>>` or `<<VK_KHR_16bit_storage>>` extensions.
37  
38  === New Enum Constants
39  
40    * Extending elink:VkStructureType:
41    ** ename:VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FLOAT16_INT8_FEATURES_KHR
42  
43  === New Structures
44  
45    * slink:VkPhysicalDeviceFloat16Int8FeaturesKHR
46  
47  === New Functions
48  
49    * None
50  
51  === Version History
52    * Revision 1, 2018-03-07 (Alexander Galazin)
53      - Initial draft