148 lines
4.4 KiB
CMake
148 lines
4.4 KiB
CMake
|
|
# Copyright (c) 2017 - 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: BSD-3-Clause
|
|
#
|
|
# Redistribution and use in source and binary forms, with or without
|
|
# modification, are permitted provided that the following conditions are met:
|
|
#
|
|
# 1. Redistributions of source code must retain the above copyright notice, this
|
|
# list of conditions and the following disclaimer.
|
|
#
|
|
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
|
# this list of conditions and the following disclaimer in the documentation
|
|
# and/or other materials provided with the distribution.
|
|
#
|
|
# 3. Neither the name of the copyright holder nor the names of its
|
|
# contributors may be used to endorse or promote products derived from
|
|
# this software without specific prior written permission.
|
|
#
|
|
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
|
|
set(CUTLASS_EXAMPLES_COMMON_SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/common)
|
|
|
|
add_custom_target(cutlass_examples)
|
|
add_custom_target(test_examples)
|
|
|
|
function(cutlass_example_add_executable NAME)
|
|
|
|
set(options)
|
|
set(oneValueArgs DISABLE_TESTS)
|
|
set(multiValueArgs DEPENDS DEPENDEES TEST_COMMAND_OPTIONS)
|
|
cmake_parse_arguments(_ "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
|
|
|
|
if (NOT DEFINED __DISABLE_TESTS)
|
|
set(__DISABLE_TESTS OFF)
|
|
endif()
|
|
|
|
cutlass_add_executable(${NAME} ${__UNPARSED_ARGUMENTS} BATCH_SOURCES OFF)
|
|
|
|
add_dependencies(cutlass_examples ${NAME})
|
|
|
|
target_link_libraries(
|
|
${NAME}
|
|
PRIVATE
|
|
CUTLASS
|
|
cutlass_tools_util_includes
|
|
$<$<BOOL:${CUTLASS_ENABLE_CUBLAS}>:nvidia::cublas>
|
|
cuda
|
|
)
|
|
|
|
target_include_directories(
|
|
${NAME}
|
|
PRIVATE
|
|
${CUTLASS_EXAMPLES_COMMON_SOURCE_DIR}
|
|
${CUTLASS_EXAMPLES_UTILS_DIR}
|
|
)
|
|
|
|
install(
|
|
TARGETS ${NAME}
|
|
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
|
|
)
|
|
|
|
cutlass_add_executable_tests(
|
|
test_examples_${NAME} ${NAME}
|
|
DEPENDS ${__DEPENDS}
|
|
DEPENDEES test_examples ${__DEPENDEES}
|
|
TEST_COMMAND_OPTIONS ${__TEST_COMMAND_OPTIONS}
|
|
DISABLE_EXECUTABLE_INSTALL_RULE
|
|
DISABLE_TESTS ${__DISABLE_TESTS}
|
|
)
|
|
|
|
endfunction()
|
|
|
|
foreach(EXAMPLE
|
|
00_basic_gemm
|
|
01_cutlass_utilities
|
|
02_dump_reg_shmem
|
|
03_visualize_layout
|
|
04_tile_iterator
|
|
05_batched_gemm
|
|
06_splitK_gemm
|
|
07_volta_tensorop_gemm
|
|
08_turing_tensorop_gemm
|
|
09_turing_tensorop_conv2dfprop
|
|
10_planar_complex
|
|
11_planar_complex_array
|
|
12_gemm_bias_relu
|
|
13_two_tensor_op_fusion
|
|
14_ampere_tf32_tensorop_gemm
|
|
15_ampere_sparse_tensorop_gemm
|
|
16_ampere_tensorop_conv2dfprop
|
|
17_fprop_per_channel_bias
|
|
18_ampere_fp64_tensorop_affine2_gemm
|
|
19_tensorop_canonical
|
|
20_simt_canonical
|
|
21_quaternion_gemm
|
|
22_quaternion_conv
|
|
23_ampere_gemm_operand_reduction_fusion
|
|
24_gemm_grouped
|
|
25_ampere_fprop_mainloop_fusion
|
|
26_ampere_wgrad_mainloop_fusion
|
|
27_ampere_3xtf32_fast_accurate_tensorop_gemm
|
|
28_ampere_3xtf32_fast_accurate_tensorop_fprop
|
|
29_ampere_3xtf32_fast_accurate_tensorop_complex_gemm
|
|
30_wgrad_split_k
|
|
31_basic_syrk
|
|
32_basic_trmm
|
|
33_ampere_3xtf32_tensorop_symm
|
|
34_transposed_conv2d
|
|
35_gemm_softmax
|
|
36_gather_scatter_fusion
|
|
37_gemm_layernorm_gemm_fusion
|
|
38_syr2k_grouped
|
|
cute
|
|
39_gemm_permute
|
|
41_fused_multi_head_attention
|
|
42_ampere_tensorop_group_conv
|
|
43_ell_block_sparse_gemm
|
|
45_dual_gemm
|
|
46_depthwise_simt_conv2dfprop
|
|
47_ampere_gemm_universal_streamk
|
|
48_hopper_warp_specialized_gemm
|
|
49_hopper_gemm_with_collective_builder
|
|
50_hopper_gemm_with_epilogue_swizzle
|
|
51_hopper_gett
|
|
52_hopper_gather_scatter_fusion
|
|
53_hopper_gemm_permute
|
|
54_hopper_fp8_warp_specialized_gemm
|
|
55_hopper_mixed_dtype_gemm
|
|
56_hopper_ptr_array_batched_gemm
|
|
57_hopper_grouped_gemm
|
|
58_ada_fp8_gemm
|
|
59_ampere_gather_scatter_conv
|
|
)
|
|
|
|
add_subdirectory(${EXAMPLE})
|
|
|
|
endforeach()
|