2019-10-06 12:42:12 -07:00
|
|
|
include::{generated}/meta/VK_NV_cooperative_matrix.txt[]
|
Change log for February 17, 2019 Vulkan 1.1.101 spec update:
* Update release number to 101.
Public Issues:
* Make clear that memory types for imported host memory must be host
visible in slink:VkMemoryHostPointerPropertiesEXT.txt (public issue
897).
* Make <<interfaces-resources-layout, WARNING block>> into a NOTE block,
per the styleguide (public pull request 916).
Internal Issues:
* Make <<textures-output-format-conversion, computation of derivatives in
non-uniform flow control>> have undefined behavior (internal issue
1367).
* Make behavior, not just values, undefined for
<<textures-layout-validation, reads from inconsistent YCbCr layouts>>
(internal issue 1366).
* Consolidate version and extension behavior documentation in the
<<extended-functionality, Extended Functionality>> appendix, While a
great deal of text was moved from other parts of the Specification into
the appendix, this just serves to simplify and make consistent
discussions of versions and extensions (internal issue 1473).
* Add limits for slink:VkPhysicalDeviceRayTracingPropertiesNV in the
<<features-limits-types, Required Limit Types>> and
<<features-limits-required, Required Limits>> tables (internal issue
1511).
* Disallow <<memory-protected-memory, indirect calls within protected
command buffers>> by adding valid usage statements for the related
indirect dispatch and draw commands (internal issue 1513).
* Add valid usage stataements to slink:VkGraphicsPipelineCreateInfo,
slink:VkSubpassDescription, slink:VkSubpassDescription2KHR,
slink:VkSubpassDescriptionDepthStencilResolveKHR, and
slink:VkImageViewCreateInfo preventing the creation of a renderpass with
attachments in formats that are not supported for rendering (internal
issue 1552).
* Qualify valid usage statements for
slink:VkAttachmentReference::pname:layout parameter so restrictions only
apply if an attachment is ename:VK_ATTACHMENT_UNUSED (internal issue
1561).
* Add valid usage statement for flink:vkCmdDrawIndirectByteCountEXT
restricting pname:vertexStride to be positive (internal issue 1566).
* Make the `VK_EXT_sample_locations` extension depend on
`VK_KHR_get_physical_device_properties2` in `vk.xml`.
* Rearrange and simplify the <<interfaces-resources-layout, block layout
rules>>.
New Extensions:
* `VK_NV_cooperative_matrix`
* `VK_EXT_depth_clip_enable` (internal issue 1485).
2019-02-15 04:00:36 -08:00
|
|
|
|
|
|
|
|
*Last Modified Data*::
|
|
|
|
|
2019-02-05
|
|
|
|
|
*Contributors*::
|
|
|
|
|
- Jeff Bolz, NVIDIA
|
|
|
|
|
- Markus Tavenrath, NVIDIA
|
|
|
|
|
- Daniel Koch, NVIDIA
|
|
|
|
|
|
|
|
|
|
This extension adds support for using cooperative matrix types in SPIR-V.
|
|
|
|
|
Cooperative matrix types are medium-sized matrices that are primarily
|
|
|
|
|
supported in compute shaders, where the storage for the matrix is spread
|
|
|
|
|
across all invocations in some scope (usually a subgroup) and those
|
|
|
|
|
invocations cooperate to efficiently perform matrix multiplies.
|
|
|
|
|
|
|
|
|
|
Cooperative matrix types are defined by the
|
Change log for August 17, 2019 Vulkan 1.1.120 spec update:
* Update release number to 120.
Github Issues:
* Add slink:VkAccelerationStructureTypeNV explicitly to extension XML for
`<<VK_NV_ray_tracing>>` (public issue 848).
* Add missing valid usage statements for feature flags in
slink:VkCommandBufferInheritanceInfo (public pull request 1017).
Internal Issues:
* Clarify behavior of non-premultiplied destination colors for
`<<VK_EXT_blend_operation_advanced>>` prior to the definition of
slink:VkBlendOverlapEXT (internal issue 1766).
* Fix the confusing phrasing "`no other queue must: be (doing something)`"
for flink:vkQueuePresentKHR, flink:vkQueueSubmit, and
flink:vkQueueBindSparse (internal issue 1774).
* Add `<<VK_EXT_validation_features>>` flag to enable best practices
checks, which will soon be available in the validation layer (internal
issue 1779).
* Specify allowed characters for VUID tag name components in the style
guide (internal issue 1788).
* Update links to SPIR-V extension specifications, and parameterize their
markup in case the URLs change in the future (internal issue 1797).
* Fix an off-by-one error in the valid usage statement for
slink:VkPipelineExecutableInfoKHR (internal merge request 3303).
* Clean up markup indentation not matching the style guide (internal merge
request 3314).
* Minor script updates to allow refpage aliases, generate a dynamic TOC
for refpages, generate Apache rewrite rules for aliases, open external
links from refpages in a new window, and synchronize with the OpenCL
scripts. This will shortly enable a paned navigation setup for refpages,
similar to the OpenCL 2.2 refpages (internal merge request 3322).
* Script updates to add tests to the checker, refactor and reformat code,
generate better text for some valid usage statements, use more Pythonic
idioms, and synchronize with the OpenXR scripts (internal merge request
3239).
* Script updates and minor fixes in spec language to not raise checker
errors for refpage markup of pages not existing in the API, such as
VKAPI_NO_STDINT_H. Remove corresponding suppression of some
check_spec_links.py tests from .gitlab-ci.yml and 'allchecks' target
(internal merge request 3315).
2019-08-17 15:33:21 -07:00
|
|
|
{spirv}/NV/SPV_NV_cooperative_matrix.html[`SPV_NV_cooperative_matrix`]
|
Change log for February 17, 2019 Vulkan 1.1.101 spec update:
* Update release number to 101.
Public Issues:
* Make clear that memory types for imported host memory must be host
visible in slink:VkMemoryHostPointerPropertiesEXT.txt (public issue
897).
* Make <<interfaces-resources-layout, WARNING block>> into a NOTE block,
per the styleguide (public pull request 916).
Internal Issues:
* Make <<textures-output-format-conversion, computation of derivatives in
non-uniform flow control>> have undefined behavior (internal issue
1367).
* Make behavior, not just values, undefined for
<<textures-layout-validation, reads from inconsistent YCbCr layouts>>
(internal issue 1366).
* Consolidate version and extension behavior documentation in the
<<extended-functionality, Extended Functionality>> appendix, While a
great deal of text was moved from other parts of the Specification into
the appendix, this just serves to simplify and make consistent
discussions of versions and extensions (internal issue 1473).
* Add limits for slink:VkPhysicalDeviceRayTracingPropertiesNV in the
<<features-limits-types, Required Limit Types>> and
<<features-limits-required, Required Limits>> tables (internal issue
1511).
* Disallow <<memory-protected-memory, indirect calls within protected
command buffers>> by adding valid usage statements for the related
indirect dispatch and draw commands (internal issue 1513).
* Add valid usage stataements to slink:VkGraphicsPipelineCreateInfo,
slink:VkSubpassDescription, slink:VkSubpassDescription2KHR,
slink:VkSubpassDescriptionDepthStencilResolveKHR, and
slink:VkImageViewCreateInfo preventing the creation of a renderpass with
attachments in formats that are not supported for rendering (internal
issue 1552).
* Qualify valid usage statements for
slink:VkAttachmentReference::pname:layout parameter so restrictions only
apply if an attachment is ename:VK_ATTACHMENT_UNUSED (internal issue
1561).
* Add valid usage statement for flink:vkCmdDrawIndirectByteCountEXT
restricting pname:vertexStride to be positive (internal issue 1566).
* Make the `VK_EXT_sample_locations` extension depend on
`VK_KHR_get_physical_device_properties2` in `vk.xml`.
* Rearrange and simplify the <<interfaces-resources-layout, block layout
rules>>.
New Extensions:
* `VK_NV_cooperative_matrix`
* `VK_EXT_depth_clip_enable` (internal issue 1485).
2019-02-15 04:00:36 -08:00
|
|
|
SPIR-V extension and can be used with the
|
Change log for August 17, 2019 Vulkan 1.1.120 spec update:
* Update release number to 120.
Github Issues:
* Add slink:VkAccelerationStructureTypeNV explicitly to extension XML for
`<<VK_NV_ray_tracing>>` (public issue 848).
* Add missing valid usage statements for feature flags in
slink:VkCommandBufferInheritanceInfo (public pull request 1017).
Internal Issues:
* Clarify behavior of non-premultiplied destination colors for
`<<VK_EXT_blend_operation_advanced>>` prior to the definition of
slink:VkBlendOverlapEXT (internal issue 1766).
* Fix the confusing phrasing "`no other queue must: be (doing something)`"
for flink:vkQueuePresentKHR, flink:vkQueueSubmit, and
flink:vkQueueBindSparse (internal issue 1774).
* Add `<<VK_EXT_validation_features>>` flag to enable best practices
checks, which will soon be available in the validation layer (internal
issue 1779).
* Specify allowed characters for VUID tag name components in the style
guide (internal issue 1788).
* Update links to SPIR-V extension specifications, and parameterize their
markup in case the URLs change in the future (internal issue 1797).
* Fix an off-by-one error in the valid usage statement for
slink:VkPipelineExecutableInfoKHR (internal merge request 3303).
* Clean up markup indentation not matching the style guide (internal merge
request 3314).
* Minor script updates to allow refpage aliases, generate a dynamic TOC
for refpages, generate Apache rewrite rules for aliases, open external
links from refpages in a new window, and synchronize with the OpenCL
scripts. This will shortly enable a paned navigation setup for refpages,
similar to the OpenCL 2.2 refpages (internal merge request 3322).
* Script updates to add tests to the checker, refactor and reformat code,
generate better text for some valid usage statements, use more Pythonic
idioms, and synchronize with the OpenXR scripts (internal merge request
3239).
* Script updates and minor fixes in spec language to not raise checker
errors for refpage markup of pages not existing in the API, such as
VKAPI_NO_STDINT_H. Remove corresponding suppression of some
check_spec_links.py tests from .gitlab-ci.yml and 'allchecks' target
(internal merge request 3315).
2019-08-17 15:33:21 -07:00
|
|
|
https://github.com/KhronosGroup/GLSL/blob/master/extensions/nv/GLSL_NV_cooperative_matrix.txt[`GL_NV_cooperative_matrix`]
|
Change log for February 17, 2019 Vulkan 1.1.101 spec update:
* Update release number to 101.
Public Issues:
* Make clear that memory types for imported host memory must be host
visible in slink:VkMemoryHostPointerPropertiesEXT.txt (public issue
897).
* Make <<interfaces-resources-layout, WARNING block>> into a NOTE block,
per the styleguide (public pull request 916).
Internal Issues:
* Make <<textures-output-format-conversion, computation of derivatives in
non-uniform flow control>> have undefined behavior (internal issue
1367).
* Make behavior, not just values, undefined for
<<textures-layout-validation, reads from inconsistent YCbCr layouts>>
(internal issue 1366).
* Consolidate version and extension behavior documentation in the
<<extended-functionality, Extended Functionality>> appendix, While a
great deal of text was moved from other parts of the Specification into
the appendix, this just serves to simplify and make consistent
discussions of versions and extensions (internal issue 1473).
* Add limits for slink:VkPhysicalDeviceRayTracingPropertiesNV in the
<<features-limits-types, Required Limit Types>> and
<<features-limits-required, Required Limits>> tables (internal issue
1511).
* Disallow <<memory-protected-memory, indirect calls within protected
command buffers>> by adding valid usage statements for the related
indirect dispatch and draw commands (internal issue 1513).
* Add valid usage stataements to slink:VkGraphicsPipelineCreateInfo,
slink:VkSubpassDescription, slink:VkSubpassDescription2KHR,
slink:VkSubpassDescriptionDepthStencilResolveKHR, and
slink:VkImageViewCreateInfo preventing the creation of a renderpass with
attachments in formats that are not supported for rendering (internal
issue 1552).
* Qualify valid usage statements for
slink:VkAttachmentReference::pname:layout parameter so restrictions only
apply if an attachment is ename:VK_ATTACHMENT_UNUSED (internal issue
1561).
* Add valid usage statement for flink:vkCmdDrawIndirectByteCountEXT
restricting pname:vertexStride to be positive (internal issue 1566).
* Make the `VK_EXT_sample_locations` extension depend on
`VK_KHR_get_physical_device_properties2` in `vk.xml`.
* Rearrange and simplify the <<interfaces-resources-layout, block layout
rules>>.
New Extensions:
* `VK_NV_cooperative_matrix`
* `VK_EXT_depth_clip_enable` (internal issue 1485).
2019-02-15 04:00:36 -08:00
|
|
|
GLSL extension.
|
|
|
|
|
|
|
|
|
|
This extension includes support for enumerating the matrix types and
|
|
|
|
|
dimensions that are supported by the implementation.
|
|
|
|
|
|
|
|
|
|
=== New Object Types
|
|
|
|
|
|
|
|
|
|
None.
|
|
|
|
|
|
|
|
|
|
=== New Enum Constants
|
|
|
|
|
|
|
|
|
|
* Extending elink:VkStructureType:
|
|
|
|
|
|
|
|
|
|
** ename:VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_COOPERATIVE_MATRIX_FEATURES_NV
|
|
|
|
|
** ename:VK_STRUCTURE_TYPE_COOPERATIVE_MATRIX_PROPERTIES_NV
|
|
|
|
|
** ename:VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_COOPERATIVE_MATRIX_PROPERTIES_NV
|
|
|
|
|
|
|
|
|
|
=== New Enums
|
|
|
|
|
|
|
|
|
|
* elink:VkScopeNV
|
|
|
|
|
* elink:VkComponentTypeNV
|
|
|
|
|
|
|
|
|
|
=== New Structures
|
|
|
|
|
|
|
|
|
|
* Extending slink:VkPhysicalDeviceFeatures2:
|
|
|
|
|
** slink:VkPhysicalDeviceCooperativeMatrixFeaturesNV
|
|
|
|
|
|
|
|
|
|
* Extending slink:VkPhysicalDeviceProperties2:
|
|
|
|
|
** slink:VkPhysicalDeviceCooperativeMatrixPropertiesNV
|
|
|
|
|
|
|
|
|
|
* slink:VkCooperativeMatrixPropertiesNV
|
|
|
|
|
|
|
|
|
|
=== New Functions
|
|
|
|
|
|
|
|
|
|
* flink:vkGetPhysicalDeviceCooperativeMatrixPropertiesNV
|
|
|
|
|
|
|
|
|
|
=== New SPIR-V Capabilities
|
|
|
|
|
|
|
|
|
|
* <<spirvenv-capabilities-table-cooperativeMatrix,CooperativeMatrixNV>>
|
|
|
|
|
|
|
|
|
|
=== Issues
|
|
|
|
|
|
|
|
|
|
(1) What matrix properties will be supported in practice?
|
|
|
|
|
|
|
|
|
|
RESOLVED: In NVIDIA's initial implementation, we will support:
|
|
|
|
|
|
|
|
|
|
* AType = BType = fp16 CType = DType = fp16 MxNxK = 16x8x16 scope =
|
|
|
|
|
Subgroup
|
|
|
|
|
* AType = BType = fp16 CType = DType = fp16 MxNxK = 16x8x8 scope =
|
|
|
|
|
Subgroup
|
|
|
|
|
* AType = BType = fp16 CType = DType = fp32 MxNxK = 16x8x16 scope =
|
|
|
|
|
Subgroup
|
|
|
|
|
* AType = BType = fp16 CType = DType = fp32 MxNxK = 16x8x8 scope =
|
|
|
|
|
Subgroup
|
|
|
|
|
|
|
|
|
|
=== Version History
|
|
|
|
|
|
|
|
|
|
* Revision 1, 2019-02-05 (Jeff Bolz)
|
|
|
|
|
- Internal revisions
|