Add new coopmat2 functions: Reduce and Transpose (#7027)

This commit adds three new functions for CoopMat as described in the proposal document,

Cooperative matrix 2 proposal spec#12
The new functions are:

CoopMat<T,S,M,N,R>::Transpose
CoopMat<T,S,M,N,R>::ReduceRow
CoopMat<T,S,M,N,R>::ReduceColumn
CoopMat<T,S,M,N,R>::ReduceRowAndColumn
CoopMat<T,S,M,N,R>::Reduce2x2

1 files changed, 45 insertions, 0 deletions

diff --git a/docs/user-guide/a3-02-reference-capability-atoms.md b/docs/user-guide/a3-02-reference-capability-atoms.md
index 116701119..a504f6f41 100644
--- a/docs/user-guide/a3-02-reference-capability-atoms.md
+++ b/docs/user-guide/a3-02-reference-capability-atoms.md
@@ -453,6 +453,15 @@ Extensions
 `SPV_KHR_cooperative_matrix`
 > Represents the SPIR-V extension for SPV_KHR_cooperative_matrix.
 
+`SPV_NV_cooperative_matrix2`
+> Represents the SPIR-V extension for SPV_NV_cooperative_matrix2.
+
+`SPV_NV_tensor_addressing`
+> Represents the SPIR-V extension for SPV_NV_tensor_addressing.
+
+`SPV_KHR_vulkan_memory_model`
+> Represents the SPIR-V extension for SPV_KHR_vulkan_memory_model.
+
 `spvAtomicFloat32AddEXT`
 > Represents the SPIR-V capability for atomic float 32 add operations.
 
@@ -573,6 +582,24 @@ Extensions
 `spvCooperativeMatrixKHR`
 > Represents the SPIR-V capability for cooperative matrices
 
+`spvCooperativeMatrixReductionsNV`
+> Represents the SPIR-V capability for cooperative matrix 2
+
+`spvCooperativeMatrixConversionsNV`
+> Represents the SPIR-V capability for cooperative matrix 2
+
+`spvCooperativeMatrixPerElementOperationsNV`
+> Represents the SPIR-V capability for cooperative matrix 2
+
+`spvCooperativeMatrixTensorAddressingNV`
+> Represents the SPIR-V capability for cooperative matrix 2
+
+`spvCooperativeMatrixBlockLoadsNV`
+> Represents the SPIR-V capability for cooperative matrix 2
+
+`spvTensorAddressingNV`
+> Represents the SPIR-V capability for tensor addressing
+
 `spvMaximalReconvergenceKHR`
 > Represents the SPIR-V capability for maximal reconvergence.
 
@@ -945,6 +972,24 @@ Compound Capabilities
 `cooperative_vector_training`
 > Capabilities needed to train cooperative vectors
 
+`cooperative_matrix_reduction`
+> Capabilities needed to use reduction operations with cooperative matrix
+
+`cooperative_matrix_conversion`
+> Capabilities needed to convert cooperative matrices
+
+`cooperative_matrix_map_element`
+> Capabilities needed to use MapElement operation with cooperative matrix
+
+`cooperative_matrix_tensor_addressing`
+> Capabilities needed to load or store with tensor_addressing extension
+
+`cooperative_matrix_block_load`
+> Capabilities needed to use decodeFunc with cooperative matrix load
+
+`tensor_addressing`
+> Capabilities needed to use tensor addressing
+
 `any_stage`
 > Collection of all shader stages