Loading CMakeLists.txt +1 −1 Original line number Diff line number Diff line Loading @@ -255,7 +255,7 @@ if( ${WITH_CUDA} ) set( CMAKE_EXECUTABLE_SUFFIX "${executable_suffix_backup}" ) endif() if( NOT CUDA_SAMPLES_DIR STREQUAL "none" ) set( CUDA_SAMPLES_FLAGS "-I${CUDA_SAMPLES_DIR}/common/inc -DHAVE_CUDA_SAMPLES") set( CUDA_SAMPLES_FLAGS "-I${CUDA_SAMPLES_DIR} -DHAVE_CUDA_SAMPLES") endif() endif() Loading src/Benchmarks/Sorting/ReferenceAlgorithms/MancaQuicksort.h +5 −5 Original line number Diff line number Diff line Loading @@ -217,8 +217,8 @@ inline __device__ void compareInclusive(Type &idata, Type &idata2, volatile Type } #include <assert.h> #include <helper_cuda.h> #include <../../6_Advanced/scan/scan_common.h> #include <common/inc/helper_cuda.h> #include <6_Advanced/scan/scan_common.h> //All three kernels run 512 threads per workgroup //Must be a power of two Loading Loading @@ -654,9 +654,9 @@ size_t scanInclusiveLarge( #include <thrust/scan.h> #include <helper_cuda.h> #include <helper_timer.h> #include <../../6_Advanced/scan/scan_common.h> #include <common/inc/helper_cuda.h> #include <common/inc/helper_timer.h> #include <6_Advanced/scan/scan_common.h> extern __shared__ uint sMemory[]; Loading Loading
CMakeLists.txt +1 −1 Original line number Diff line number Diff line Loading @@ -255,7 +255,7 @@ if( ${WITH_CUDA} ) set( CMAKE_EXECUTABLE_SUFFIX "${executable_suffix_backup}" ) endif() if( NOT CUDA_SAMPLES_DIR STREQUAL "none" ) set( CUDA_SAMPLES_FLAGS "-I${CUDA_SAMPLES_DIR}/common/inc -DHAVE_CUDA_SAMPLES") set( CUDA_SAMPLES_FLAGS "-I${CUDA_SAMPLES_DIR} -DHAVE_CUDA_SAMPLES") endif() endif() Loading
src/Benchmarks/Sorting/ReferenceAlgorithms/MancaQuicksort.h +5 −5 Original line number Diff line number Diff line Loading @@ -217,8 +217,8 @@ inline __device__ void compareInclusive(Type &idata, Type &idata2, volatile Type } #include <assert.h> #include <helper_cuda.h> #include <../../6_Advanced/scan/scan_common.h> #include <common/inc/helper_cuda.h> #include <6_Advanced/scan/scan_common.h> //All three kernels run 512 threads per workgroup //Must be a power of two Loading Loading @@ -654,9 +654,9 @@ size_t scanInclusiveLarge( #include <thrust/scan.h> #include <helper_cuda.h> #include <helper_timer.h> #include <../../6_Advanced/scan/scan_common.h> #include <common/inc/helper_cuda.h> #include <common/inc/helper_timer.h> #include <6_Advanced/scan/scan_common.h> extern __shared__ uint sMemory[]; Loading