[Offload][NFC] Remove all trailing whitespace from offload/ (#92578)

Summary:
This patch cleans up the training whitespace in a bunch of tests and
CMake files. Most just in preparation for other cleanups.

Author: jhuber6

offload/CMakeLists.txt

@@ -134,7 +134,7 @@ if (NOT LIBOMPTARGET_LLVM_INCLUDE_DIRS)
   message(FATAL_ERROR "Missing definition for LIBOMPTARGET_LLVM_INCLUDE_DIRS")
 endif()
 
-if(DEFINED LIBOMPTARGET_BUILD_CUDA_PLUGIN OR 
+if(DEFINED LIBOMPTARGET_BUILD_CUDA_PLUGIN OR
    DEFINED LIBOMPTARGET_BUILD_AMDGPU_PLUGIN)
   message(WARNING "Option removed, use 'LIBOMPTARGET_PLUGINS_TO_BUILD' instead")
 endif()

offload/DeviceRTL/CMakeLists.txt

@@ -104,7 +104,7 @@ set(src_files
 # vectorized accesses to the shared state. Generally, those are "good" but
 # the optimizer pipeline (esp. Attributor) does not fully support vectorized
 # instructions yet and we end up missing out on way more important constant
-# propagation. That said, we will run the vectorizer again after the runtime 
+# propagation. That said, we will run the vectorizer again after the runtime
 # has been linked into the user program.
 set(clang_opt_flags -O3 -mllvm -openmp-opt-disable -DSHARED_SCRATCHPAD_SIZE=512 -mllvm -vectorize-slp=false )
 set(link_opt_flags  -O3        -openmp-opt-disable -attributor-enable=module -vectorize-slp=false )

offload/plugins-nextgen/CMakeLists.txt

@@ -38,7 +38,7 @@ function(add_target_library target_name lib_name)
                         PluginCommon ${OPENMP_PTHREAD_LIB})
 
   target_compile_definitions(${target_name} PRIVATE TARGET_NAME=${lib_name})
-  target_compile_definitions(${target_name} PRIVATE 
+  target_compile_definitions(${target_name} PRIVATE
                              DEBUG_PREFIX="TARGET ${lib_name} RTL")
   set_target_properties(${target_name} PROPERTIES POSITION_INDEPENDENT_CODE ON)
 endfunction()

offload/plugins-nextgen/amdgpu/CMakeLists.txt

@@ -28,7 +28,7 @@ endif()
 option(LIBOMPTARGET_FORCE_AMDGPU_TESTS "Build AMDGPU libomptarget tests" OFF)
 if (LIBOMPTARGET_FOUND_AMDGPU_GPU OR LIBOMPTARGET_FORCE_AMDGPU_TESTS)
   # Report to the parent scope that we are building a plugin for amdgpu
-  set(LIBOMPTARGET_SYSTEM_TARGETS 
+  set(LIBOMPTARGET_SYSTEM_TARGETS
       "${LIBOMPTARGET_SYSTEM_TARGETS} amdgcn-amd-amdhsa" PARENT_SCOPE)
   list(APPEND LIBOMPTARGET_TESTED_PLUGINS "omptarget.rtl.amdgpu")
   set(LIBOMPTARGET_TESTED_PLUGINS "${LIBOMPTARGET_TESTED_PLUGINS}" PARENT_SCOPE)

offload/plugins-nextgen/common/CMakeLists.txt

@@ -51,7 +51,7 @@ target_compile_definitions(PluginCommon PRIVATE
 target_compile_options(PluginCommon PUBLIC ${offload_compile_flags})
 target_link_options(PluginCommon PUBLIC ${offload_link_flags})
 
-target_include_directories(PluginCommon PUBLIC 
+target_include_directories(PluginCommon PUBLIC
   ${CMAKE_CURRENT_SOURCE_DIR}/include
   ${LIBOMPTARGET_LLVM_INCLUDE_DIRS}
   ${LIBOMPTARGET_BINARY_INCLUDE_DIR}

offload/plugins-nextgen/cuda/CMakeLists.txt

@@ -25,7 +25,7 @@ endif()
 option(LIBOMPTARGET_FORCE_NVIDIA_TESTS "Build NVIDIA libomptarget tests" OFF)
 if (LIBOMPTARGET_FOUND_NVIDIA_GPU OR LIBOMPTARGET_FORCE_NVIDIA_TESTS)
   libomptarget_say("Enable tests using CUDA plugin")
-  set(LIBOMPTARGET_SYSTEM_TARGETS 
+  set(LIBOMPTARGET_SYSTEM_TARGETS
       "${LIBOMPTARGET_SYSTEM_TARGETS} nvptx64-nvidia-cuda nvptx64-nvidia-cuda-LTO" PARENT_SCOPE)
   list(APPEND LIBOMPTARGET_TESTED_PLUGINS "omptarget.rtl.cuda")
   set(LIBOMPTARGET_TESTED_PLUGINS "${LIBOMPTARGET_TESTED_PLUGINS}" PARENT_SCOPE)

offload/plugins-nextgen/host/CMakeLists.txt

@@ -44,23 +44,23 @@ endif()
 
 # Define the target specific triples and ELF machine values.
 if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le$")
-  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS 
+  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS
        "powerpc64le-ibm-linux-gnu" "powerpc64le-ibm-linux-gnu-LTO")
   set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
 elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64$")
-  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS 
+  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS
        "powerpc64-ibm-linux-gnu" "powerpc64-ibm-linux-gnu-LTO")
   set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
 elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64$")
-  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS 
+  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS
        "x86_64-pc-linux-gnu" "x86_64-pc-linux-gnu-LTO")
   set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
 elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64$")
-  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS 
+  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS
        "aarch64-unknown-linux-gnu" "aarch64-unknown-linux-gnu-LTO")
   set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
 elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "s390x$")
-  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS 
+  list(APPEND LIBOMPTARGET_SYSTEM_TARGETS
        "s390x-ibm-linux-gnu" "s390x-ibm-linux-gnu-LTO")
   set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
 endif()

offload/src/CMakeLists.txt

@@ -38,7 +38,7 @@ add_llvm_library(omptarget
   NO_INSTALL_RPATH
   BUILDTREE_ONLY
 )
-target_include_directories(omptarget PRIVATE 
+target_include_directories(omptarget PRIVATE
   ${LIBOMPTARGET_INCLUDE_DIR} ${LIBOMPTARGET_BINARY_INCLUDE_DIR}
 )
 

offload/test/mapping/array_section_implicit_capture.c

@@ -1,4 +1,4 @@
-// RUN: %libomptarget-compile-generic 
+// RUN: %libomptarget-compile-generic
 // RUN: %libomptarget-run-generic 2>&1 \
 // RUN: | %fcheck-generic
 

offload/test/offloading/default_thread_limit.c

@@ -33,7 +33,7 @@ int main() {
     optnone();
   }
 // DEFAULT: [[NT:(128|256)]] (MaxFlatWorkGroupSize: [[NT]]
-#pragma omp target 
+#pragma omp target
 #pragma omp teams distribute parallel for
   for (int i = 0; i < N; ++i) {
     optnone();

offload/test/offloading/fortran/basic-target-region-1D-array-section.f90

@@ -1,4 +1,4 @@
-! Basic offloading test of arrays with provided lower 
+! Basic offloading test of arrays with provided lower
 ! and upper bounds as specified by OpenMP's sectioning
 ! REQUIRES: flang
 ! UNSUPPORTED: nvptx64-nvidia-cuda-LTO
@@ -20,7 +20,7 @@ program main
             i = i + 1
         end do
     !$omp end target
-    
+
     print *, write_arr(:)
 end program
 

offload/test/offloading/fortran/basic-target-region-3D-array-section.f90

@@ -12,7 +12,7 @@ program main
     implicit none
     integer :: inArray(3,3,3)
     integer :: outArray(3,3,3)
-    integer :: i, j, k 
+    integer :: i, j, k
     integer :: j2 = 3, k2 = 3
 
     do i = 1, 3
@@ -25,7 +25,7 @@ program main
     end do
 
 j = 1
-k = 1 
+k = 1
 !$omp target map(tofrom:inArray(1:3, 1:3, 2:2), outArray(1:3, 1:3, 1:3), j, k, j2, k2)
     do while (j <= j2)
       k = 1

offload/test/offloading/fortran/double-target-call-with-declare-target.f90

@@ -1,6 +1,6 @@
 ! Offloading test with two target regions mapping the same
-! declare target Fortran array and writing some values to 
-! it before checking the host correctly receives the 
+! declare target Fortran array and writing some values to
+! it before checking the host correctly receives the
 ! correct updates made on the device.
 ! REQUIRES: flang
 ! UNSUPPORTED: nvptx64-nvidia-cuda
@@ -35,7 +35,7 @@ program main
         i = i + 1
     end do
 !$omp end target
-    
+
 print *, sp(:)
 
 end program

offload/test/offloading/fortran/target-map-allocatable-map-scopes.f90

@@ -11,55 +11,55 @@
 ! RUN: %libomptarget-compile-fortran-run-and-check-generic
 module test
     contains
-  subroutine func_arg(arg_alloc) 
+  subroutine func_arg(arg_alloc)
     integer,  allocatable, intent (inout) :: arg_alloc(:)
-  
-  !$omp target map(tofrom: arg_alloc) 
+
+  !$omp target map(tofrom: arg_alloc)
     do index = 1, 10
       arg_alloc(index) = arg_alloc(index) + index
     end do
   !$omp end target
-    
+
     print *, arg_alloc
   end subroutine func_arg
-end module 
-  
-subroutine func 
-    integer,  allocatable :: local_alloc(:) 
+end module
+
+subroutine func
+    integer,  allocatable :: local_alloc(:)
     allocate(local_alloc(10))
-  
-  !$omp target map(tofrom: local_alloc) 
+
+  !$omp target map(tofrom: local_alloc)
     do index = 1, 10
       local_alloc(index) = index
     end do
   !$omp end target
-  
+
     print *, local_alloc
-  
+
     deallocate(local_alloc)
-end subroutine func 
-  
-  
-program main 
-  use test 
-  integer,  allocatable :: map_ptr(:) 
-  
+end subroutine func
+
+
+program main
+  use test
+  integer,  allocatable :: map_ptr(:)
+
   allocate(map_ptr(10))
-  
-  !$omp target map(tofrom: map_ptr) 
+
+  !$omp target map(tofrom: map_ptr)
     do index = 1, 10
       map_ptr(index) = index
     end do
   !$omp end target
 
-   call func 
+   call func
 
    print *, map_ptr
 
    call func_arg(map_ptr)
 
    deallocate(map_ptr)
-end program 
+end program
 
 ! CHECK: 1 2 3 4 5 6 7 8 9 10
 ! CHECK: 1 2 3 4 5 6 7 8 9 10

offload/test/offloading/fortran/target-map-derived-type-full-1.f90

@@ -1,5 +1,5 @@
 ! Offloading test checking interaction of an
-! explicit derived type mapping when mapped 
+! explicit derived type mapping when mapped
 ! to target and assinging one derived type
 ! to another
 ! REQUIRES: flang, amdgcn-amd-amdhsa
@@ -16,22 +16,22 @@ program main
     integer(4) :: ix = 0
     real(4) :: rx = 0.0
     complex(4) :: zx = (0,0)
-    end type scalar  
-  
+    end type scalar
+
     type(scalar) :: in
     type(scalar) :: out
     in%ix = 10
     in%rx = 2.0
     in%zx = (2, 10)
-  
+
   !$omp target map(from:out) map(to:in)
-      out = in 
+      out = in
   !$omp end target
-  
+
     print*, in%ix
     print*, in%rx
     write (*,*) in%zx
-  
+
     print*, out%ix
     print*, out%rx
     write (*,*)  out%zx

offload/test/offloading/fortran/target-map-derived-type-full-2.f90

@@ -1,5 +1,5 @@
 ! Offloading test checking interaction of an
-! explicit derived type mapping when mapped to 
+! explicit derived type mapping when mapped to
 ! target and assigning to individual members
 ! REQUIRES: flang, amdgcn-amd-amdhsa
 ! UNSUPPORTED: nvptx64-nvidia-cuda
@@ -16,29 +16,29 @@ program main
     real(4) :: rx = 0.0
     complex(4) :: zx = (0,0)
     integer(4) :: array(5)
-    end type scalar 
-  
+    end type scalar
+
     type(scalar) :: out
     type(scalar) :: in
-  
+
     in%ix = 10
     in%rx = 2.0
     in%zx = (2, 10)
-  
+
     do i = 1, 5
       in%array(i) = i
-    end do 
-  
+    end do
+
   !$omp target map(from:out) map(to:in)
     out%ix = in%ix
     out%rx = in%rx
     out%zx = in%zx
-  
+
     do i = 1, 5
       out%array(i) = in%array(i)
-    end do 
+    end do
   !$omp end target
-  
+
     print*, in%ix
     print*, in%rx
     print*, in%array

offload/test/offloading/fortran/target-map-derived-type-full-implicit-1.f90

@@ -1,5 +1,5 @@
 ! Offloading test checking interaction of an
-! implicit derived type mapping when mapped 
+! implicit derived type mapping when mapped
 ! to target and assinging one derived type
 ! to another
 ! REQUIRES: flang, amdgcn-amd-amdhsa
@@ -16,18 +16,18 @@ program main
     integer(4) :: ix = 0
     real(4) :: rx = 0.0
     complex(4) :: zx = (0,0)
-    end type scalar  
-  
+    end type scalar
+
     type(scalar) :: in
     type(scalar) :: out
     in%ix = 10
     in%rx = 2.0
     in%zx = (2, 10)
-  
+
   !$omp target map(from:out)
-      out = in 
+      out = in
   !$omp end target
-  
+
     print*, in%ix
     print*, in%rx
     write (*,*) in%zx
@@ -43,4 +43,3 @@ end program main
 !CHECK: 10
 !CHECK: 2.
 !CHECK: (2.,10.)
-