leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 3.6.0 (#1850)

Browse Source 
* v3.6

* update changelog

* update readme

* fix typo

* fixing typos

* hopper gemm with weight prefetch

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Yujia Zhai
2024-10-09 12:33:27 -07:00
committed by GitHub
parent 0837a2a00a
commit cc3c29a81a
354 changed files with 105943 additions and 8203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
test/self_contained_includes/CMakeLists.txt
View File

@@ -30,12 +30,107 @@
# i.e. they can be included in a source file without needing to include other headers before it.
set(header_files_to_check
# cutlass
# cutlass/gemm/kernel
cutlass/gemm/kernel/default_gemm.h
cutlass/gemm/kernel/default_gemm_complex.h
cutlass/gemm/kernel/gemm_universal_decl.h
# cutlass/gemm/kernel/sm90_gemm_warpspecialized.hpp
# cute
cute/config.hpp
cute/int_tuple.hpp
cute/layout.hpp
cute/layout_composed.hpp
cute/pointer.hpp
cute/pointer_base.hpp
cute/pointer_flagged.hpp
cute/pointer_swizzle.hpp
cute/stride.hpp
cute/swizzle.hpp
cute/swizzle_layout.hpp
cute/tensor.hpp
cute/tensor_impl.hpp
cute/tensor_predicate.hpp
cute/underscore.hpp
# cute/algorithm
cute/algorithm/axpby.hpp
cute/algorithm/clear.hpp
# cute/algorithm/cooperative_copy.hpp
cute/algorithm/cooperative_gemm.hpp
# cute/algorithm/copy.hpp
cute/algorithm/fill.hpp
cute/algorithm/functional.hpp
# cute/algorithm/gemm.hpp
cute/algorithm/prefer.hpp
# cute/algorithm/prefetch.hpp
cute/algorithm/tensor_algorithms.hpp
cute/algorithm/tuple_algorithms.hpp
# cute/container
cute/container/alignment.hpp
cute/container/array.hpp
cute/container/array_aligned.hpp
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
# cute/numeric
cute/numeric/arithmetic_tuple.hpp
cute/numeric/complex.hpp
cute/numeric/int.hpp
cute/numeric/integer_sequence.hpp
cute/numeric/integral_ratio.hpp
cute/numeric/math.hpp
cute/numeric/numeric_types.hpp
cute/numeric/real.hpp
cute/numeric/integral_constant.hpp
# cute/util
cute/util/debug.hpp
cute/util/print.hpp
cute/util/type_traits.hpp
# cute/arch
cute/arch/cluster_sm90.hpp
cute/arch/copy.hpp
cute/arch/copy_sm50.hpp
cute/arch/copy_sm75.hpp
cute/arch/copy_sm80.hpp
cute/arch/copy_sm90.hpp
cute/arch/copy_sm90_desc.hpp
cute/arch/copy_sm90_tma.hpp
cute/arch/mma_sm61.hpp
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/atom
# cute/atom/copy_atom.hpp
# cute/atom/copy_traits.hpp
# cute/atom/copy_traits_sm50.hpp
# cute/atom/copy_traits_sm75.hpp
# cute/atom/copy_traits_sm80.hpp
# cute/atom/copy_traits_sm90.hpp
# cute/atom/copy_traits_sm90_im2col.hpp
# cute/atom/copy_traits_sm90_tma.hpp
# cute/atom/copy_traits_sm90_tma_swizzle.hpp
cute/atom/mma_atom.hpp
cute/atom/mma_traits.hpp
cute/atom/mma_traits_sm61.hpp
cute/atom/mma_traits_sm70.hpp
cute/atom/mma_traits_sm75.hpp
cute/atom/mma_traits_sm80.hpp
cute/atom/mma_traits_sm90.hpp
cute/atom/mma_traits_sm90_gmma.hpp
)
# for each header in _header_files: