C Specification
The VkPhysicalDeviceFloatControlsProperties structure is defined as:
typedef struct VkPhysicalDeviceFloatControlsProperties {
VkStructureType sType;
void* pNext;
VkShaderFloatControlsIndependence denormBehaviorIndependence;
VkShaderFloatControlsIndependence roundingModeIndependence;
VkBool32 shaderSignedZeroInfNanPreserveFloat16;
VkBool32 shaderSignedZeroInfNanPreserveFloat32;
VkBool32 shaderSignedZeroInfNanPreserveFloat64;
VkBool32 shaderDenormPreserveFloat16;
VkBool32 shaderDenormPreserveFloat32;
VkBool32 shaderDenormPreserveFloat64;
VkBool32 shaderDenormFlushToZeroFloat16;
VkBool32 shaderDenormFlushToZeroFloat32;
VkBool32 shaderDenormFlushToZeroFloat64;
VkBool32 shaderRoundingModeRTEFloat16;
VkBool32 shaderRoundingModeRTEFloat32;
VkBool32 shaderRoundingModeRTEFloat64;
VkBool32 shaderRoundingModeRTZFloat16;
VkBool32 shaderRoundingModeRTZFloat32;
VkBool32 shaderRoundingModeRTZFloat64;
} VkPhysicalDeviceFloatControlsProperties;
or the equivalent
typedef VkPhysicalDeviceFloatControlsProperties VkPhysicalDeviceFloatControlsPropertiesKHR;
Members
The members of the VkPhysicalDeviceFloatControlsProperties structure
describe the following implementation-dependent limits:
Description
-
denormBehaviorIndependenceis a VkShaderFloatControlsIndependence value indicating whether, and how, denorm behavior can be set independently for different bit widths. -
roundingModeIndependenceis a VkShaderFloatControlsIndependence value indicating whether, and how, rounding modes can be set independently for different bit widths. -
shaderSignedZeroInfNanPreserveFloat16is a boolean value indicating whether sign of a zero, Nans and \(\pm\infty\) can be preserved in 16-bit floating-point computations. It also indicates whether theSignedZeroInfNanPreserveexecution mode can be used for 16-bit floating-point types. -
shaderSignedZeroInfNanPreserveFloat32is a boolean value indicating whether sign of a zero, Nans and \(\pm\infty\) can be preserved in 32-bit floating-point computations. It also indicates whether theSignedZeroInfNanPreserveexecution mode can be used for 32-bit floating-point types. -
shaderSignedZeroInfNanPreserveFloat64is a boolean value indicating whether sign of a zero, Nans and \(\pm\infty\) can be preserved in 64-bit floating-point computations. It also indicates whether theSignedZeroInfNanPreserveexecution mode can be used for 64-bit floating-point types. -
shaderDenormPreserveFloat16is a boolean value indicating whether denormals can be preserved in 16-bit floating-point computations. It also indicates whether theDenormPreserveexecution mode can be used for 16-bit floating-point types. -
shaderDenormPreserveFloat32is a boolean value indicating whether denormals can be preserved in 32-bit floating-point computations. It also indicates whether theDenormPreserveexecution mode can be used for 32-bit floating-point types. -
shaderDenormPreserveFloat64is a boolean value indicating whether denormals can be preserved in 64-bit floating-point computations. It also indicates whether theDenormPreserveexecution mode can be used for 64-bit floating-point types. -
shaderDenormFlushToZeroFloat16is a boolean value indicating whether denormals can be flushed to zero in 16-bit floating-point computations. It also indicates whether theDenormFlushToZeroexecution mode can be used for 16-bit floating-point types. -
shaderDenormFlushToZeroFloat32is a boolean value indicating whether denormals can be flushed to zero in 32-bit floating-point computations. It also indicates whether theDenormFlushToZeroexecution mode can be used for 32-bit floating-point types. -
shaderDenormFlushToZeroFloat64is a boolean value indicating whether denormals can be flushed to zero in 64-bit floating-point computations. It also indicates whether theDenormFlushToZeroexecution mode can be used for 64-bit floating-point types. -
shaderRoundingModeRTEFloat16is a boolean value indicating whether an implementation supports the round-to-nearest-even rounding mode for 16-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTEexecution mode can be used for 16-bit floating-point types. -
shaderRoundingModeRTEFloat32is a boolean value indicating whether an implementation supports the round-to-nearest-even rounding mode for 32-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTEexecution mode can be used for 32-bit floating-point types. -
shaderRoundingModeRTEFloat64is a boolean value indicating whether an implementation supports the round-to-nearest-even rounding mode for 64-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTEexecution mode can be used for 64-bit floating-point types. -
shaderRoundingModeRTZFloat16is a boolean value indicating whether an implementation supports the round-towards-zero rounding mode for 16-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTZexecution mode can be used for 16-bit floating-point types. -
shaderRoundingModeRTZFloat32is a boolean value indicating whether an implementation supports the round-towards-zero rounding mode for 32-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTZexecution mode can be used for 32-bit floating-point types. -
shaderRoundingModeRTZFloat64is a boolean value indicating whether an implementation supports the round-towards-zero rounding mode for 64-bit floating-point arithmetic and conversion instructions. It also indicates whether theRoundingModeRTZexecution mode can be used for 64-bit floating-point types.
|
editing-note
Implementations may not be able to control behavior of denorms for floating-point atomics. This needs to be taken into account when such atomics will be added to Vulkan. |
If the VkPhysicalDeviceFloatControlsProperties structure is included
in the pNext chain of VkPhysicalDeviceProperties2, it is filled
with the implementation-dependent limits.
See Also
VkBool32, VkShaderFloatControlsIndependence, VkStructureType
Document Notes
For more information, see the Vulkan Specification
This page is extracted from the Vulkan Specification. Fixes and changes should be made to the Specification, not directly.
Copyright
Copyright (c) 2014-2020 Khronos Group. This work is licensed under a Creative Commons Attribution 4.0 International License.