diff options
| author | Jay Kwak <82421531+jkwak-work@users.noreply.github.com> | 2025-05-15 07:02:38 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-15 00:02:38 -0700 |
| commit | 49de1e8f60c698e9d524befacc988fb06574b234 (patch) | |
| tree | cc1006b24532b0f98a2f8af49010925e9d992f66 /docs/user-guide | |
| parent | dd275dd952afc1b0d1a156d786c28620a48863e1 (diff) | |
Support tensor addressing (#7060)
This commit implements two new types and related Load/Store functions in CoopMat.
tensor_addrressing.TensorLayout
tensor_addressing.TensorView
CoopMat.Load(..., TensorLayout)
CoopMat.Load(..., TensorLayout, TensorView)
CoopMat.Store(..., TensorLayout)
CoopMat.Store(..., TensorLayout, TensorView)
CoopMat.Load(..., TensorLayout, TensorView)
Diffstat (limited to 'docs/user-guide')
| -rw-r--r-- | docs/user-guide/a3-02-reference-capability-atoms.md | 13 |
1 files changed, 8 insertions, 5 deletions
diff --git a/docs/user-guide/a3-02-reference-capability-atoms.md b/docs/user-guide/a3-02-reference-capability-atoms.md index a504f6f41..549d98ece 100644 --- a/docs/user-guide/a3-02-reference-capability-atoms.md +++ b/docs/user-guide/a3-02-reference-capability-atoms.md @@ -447,20 +447,20 @@ Extensions `SPV_EXT_replicated_composites` > Represents the SPIR-V extension for SPV_EXT_replicated_composites. +`SPV_KHR_vulkan_memory_model` +> Represents the SPIR-V extension for SPV_KHR_vulkan_memory_model. + `SPV_NV_cooperative_vector` > Represents the SPIR-V extension for SPV_NV_cooperative_vector. `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. +`SPV_NV_cooperative_matrix2` +> Represents the SPIR-V extension for SPV_NV_cooperative_matrix2. `spvAtomicFloat32AddEXT` > Represents the SPIR-V capability for atomic float 32 add operations. @@ -990,6 +990,9 @@ Compound Capabilities `tensor_addressing` > Capabilities needed to use tensor addressing +`cooperative_matrix_2` +> Capabilities needed to use tensor addressing + `any_stage` > Collection of all shader stages |