mirror of
https://gitlab.kitware.com/vtk/vtk-m
synced 2024-09-08 13:23:51 +00:00
047d79672a
CUDA architecture has a limited amount of memory available for constants. The CUDA compiler uses this space to hold constants for some optimizations. However, for large kernels, the number of constants needed might be larger than the constant space available. For these conditions, you have to disable this form of optimization with the `- Xptxas --disable-optimizer-constants` flags. Currently, the only file that seems to have this issue is the test for the Lagrangian filter. Someone should take a closer look to see if this filter in particular is making unnecessarily large worklet/kernel. (In particular, why does the Lagrangian filter have a larger kernel than the streamline and stream surface filters?) If this occurance happens more often, we might need to add some ways to configure it in the build.
33 lines
1.6 KiB
CMake
33 lines
1.6 KiB
CMake
##============================================================================
|
|
## Copyright (c) Kitware, Inc.
|
|
## All rights reserved.
|
|
## See LICENSE.txt for details.
|
|
##
|
|
## This software is distributed WITHOUT ANY WARRANTY; without even
|
|
## the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
|
|
## PURPOSE. See the above copyright notice for more information.
|
|
##============================================================================
|
|
cmake_minimum_required(VERSION 3.12...3.15 FATAL_ERROR)
|
|
|
|
#Find the VTK-m package
|
|
find_package(VTKm REQUIRED QUIET)
|
|
|
|
if ((TARGET vtkm::cuda) OR (TARGET vtkm::kokkos_cuda))
|
|
# CUDA architecture has a limited amount of memory available for constants. The CUDA
|
|
# compiler uses this space to hold constants for some optimizations. However, for large
|
|
# kernels, the number of constants needed might be larger than the constant space
|
|
# available. For these conditions, you have to disable this form of optimization with
|
|
# the -Xptxas --disable-optimizer-constants flags.
|
|
# TODO: Find a more elegant way to do this. Either figure out a way around this problem
|
|
# or add more general flags to vtkm_library/vtkm_unit_tests for sources with "large" kernels.
|
|
set_source_files_properties(lagrangian.cxx PROPERTIES
|
|
COMPILE_OPTIONS "-Xptxas;--disable-optimizer-constants"
|
|
)
|
|
endif()
|
|
|
|
add_executable(Lagrangian lagrangian.cxx ABCfield.h)
|
|
target_link_libraries(Lagrangian PRIVATE vtkm_filter)
|
|
vtkm_add_target_information(Lagrangian
|
|
DROP_UNUSED_SYMBOLS MODIFY_CUDA_FLAGS
|
|
DEVICE_SOURCES lagrangian.cxx)
|