update 3.8 v2 (#2112)

* update 3.8 v2

* update 3.8

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-19 19:03:14 -08:00
committed by GitHub
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions

View File

@@ -75,7 +75,6 @@ set(header_files_to_check
cute/container/array_subbyte.hpp
cute/container/bit_field.hpp
cute/container/cuda_types.hpp
cute/container/packed_tuple.hpp
cute/container/tuple.hpp
cute/container/type_list.hpp
@@ -107,13 +106,12 @@ set(header_files_to_check
cute/arch/mma_sm70.hpp
cute/arch/mma_sm75.hpp
cute/arch/mma_sm80.hpp
cute/arch/mma_sm80_sparse.hpp
cute/arch/mma_sm90.hpp
cute/arch/mma_sm90_desc.hpp
cute/arch/mma_sm90_gmma.hpp
cute/arch/mma.hpp
cute/arch/util.hpp
cute/arch/cluster_sm100.hpp
cute/arch/copy_sm100.hpp
cute/arch/copy_sm100_tma.hpp
@@ -121,7 +119,7 @@ set(header_files_to_check
cute/arch/mma_sm100_desc.hpp
cute/arch/mma_sm100_umma.hpp
# cute/arch/tmem_allocator_sm100.hpp
# cute/atom
# cute/atom/copy_atom.hpp
# cute/atom/copy_traits.hpp
@@ -140,10 +138,10 @@ set(header_files_to_check
cute/atom/mma_traits_sm80.hpp
cute/atom/mma_traits_sm90.hpp
cute/atom/mma_traits_sm90_gmma.hpp
cute/atom/mma_traits_sm100.hpp
cute/atom/mma_traits_sm100.hpp
cute/atom/partitioner.hpp
# cutlass
cutlass/aligned_buffer.h
cutlass/array.h
@@ -180,7 +178,6 @@ set(header_files_to_check
cutlass/numeric_size.h
cutlass/numeric_types.h
cutlass/pitch_linear_coord.h
cutlass/predicate.h
cutlass/predicate_vector.h
cutlass/quaternion.h
cutlass/real.h
@@ -200,16 +197,16 @@ set(header_files_to_check
cutlass/workspace.h
cutlass/exmy_base.h
cutlass/float_subbyte.h
# cutlass/platform
cutlass/platform/platform.h
# cutlass/pipeline
cutlass/pipeline/pipeline.hpp
cutlass/pipeline/sm90_pipeline.hpp
cutlass/pipeline/sm100_pipeline.hpp
# cutlass/detail
cutlass/detail/cluster.hpp
@@ -217,18 +214,16 @@ set(header_files_to_check
cutlass/detail/dependent_false.hpp
cutlass/detail/helper_macros.hpp
cutlass/detail/layout.hpp
cutlass/detail/mainloop_fusion_helper_bgrada.hpp
cutlass/detail/mma.hpp
cutlass/detail/sm100_blockscaled_layout.hpp
# cutlass/arch
cutlass/arch/arch.h
cutlass/arch/barrier.h
cutlass/arch/cache_operation.h
cutlass/arch/config.h
cutlass/arch/custom_abi.h
cutlass/arch/grid_dependency_control.h
cutlass/arch/memory.h
# cutlass/arch/memory_sm75.h
@@ -248,7 +243,6 @@ set(header_files_to_check
# cutlass/arch/simd_sm60.h
# cutlass/arch/simd_sm61.h
cutlass/arch/reg_reconfig.h
cutlass/arch/tma_operation.h
cutlass/arch/wmma.h
# cutlass/arch/wmma_sm70.h
# cutlass/arch/wmma_sm72.h