[OpenMP][NFC] Remove a no-op function

llvm · Nov 3, 2023 · d3e7a48 · d3e7a48
1 parent 6b29279
commit d3e7a48
Show file tree

Hide file tree

Showing 11 changed files with 0 additions and 58 deletions.
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3081,14 +3081,7 @@ void CGOpenMPRuntimeGPU::emitReduction(
       ++IRHS;
     }
   };
-  llvm::Value *EndArgs[] = {ThreadId};
   RegionCodeGenTy RCG(CodeGen);
-  NVPTXActionTy Action(
-      nullptr, std::nullopt,
-      OMPBuilder.getOrCreateRuntimeFunction(
-          CGM.getModule(), OMPRTL___kmpc_nvptx_end_reduce_nowait),
-      EndArgs);
-  RCG.setAction(Action);
   RCG(CGF);
   // There is no need to emit line number for unconditional branch.
   (void)ApplyDebugLocation::CreateEmpty(CGF);

diff --git a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
@@ -148,7 +148,6 @@ int bar(int n){
 // CHECK-64-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK-64-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK-64-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK-64-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK-64-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-64:       .omp.reduction.done:
 // CHECK-64-NEXT:    ret void
@@ -353,7 +352,6 @@ int bar(int n){
 // CHECK-64-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK-64-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK-64-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK-64-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK-64-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-64:       .omp.reduction.done:
 // CHECK-64-NEXT:    ret void
@@ -609,7 +607,6 @@ int bar(int n){
 // CHECK-64:       cond.end11:
 // CHECK-64-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK-64-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK-64-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK-64-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-64:       .omp.reduction.done:
 // CHECK-64-NEXT:    ret void
@@ -824,7 +821,6 @@ int bar(int n){
 // CHECK-32-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK-32-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK-32-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK-32-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK-32-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32:       .omp.reduction.done:
 // CHECK-32-NEXT:    ret void
@@ -1029,7 +1025,6 @@ int bar(int n){
 // CHECK-32-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK-32-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK-32-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK-32-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK-32-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32:       .omp.reduction.done:
 // CHECK-32-NEXT:    ret void
@@ -1285,7 +1280,6 @@ int bar(int n){
 // CHECK-32:       cond.end11:
 // CHECK-32-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK-32-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK-32-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK-32-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32:       .omp.reduction.done:
 // CHECK-32-NEXT:    ret void
@@ -1500,7 +1494,6 @@ int bar(int n){
 // CHECK-32-EX-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK-32-EX-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK-32-EX-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK-32-EX-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK-32-EX-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32-EX:       .omp.reduction.done:
 // CHECK-32-EX-NEXT:    ret void
@@ -1705,7 +1698,6 @@ int bar(int n){
 // CHECK-32-EX-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK-32-EX-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK-32-EX-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK-32-EX-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK-32-EX-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32-EX:       .omp.reduction.done:
 // CHECK-32-EX-NEXT:    ret void
@@ -1961,7 +1953,6 @@ int bar(int n){
 // CHECK-32-EX:       cond.end11:
 // CHECK-32-EX-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK-32-EX-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK-32-EX-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK-32-EX-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK-32-EX:       .omp.reduction.done:
 // CHECK-32-EX-NEXT:    ret void

diff --git a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
@@ -338,7 +338,6 @@ void test() {
 // CHECK1-NEXT:    br i1 [[TMP37]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
 // CHECK1:       .omp.reduction.then:
 // CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[TMP2]], ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]]) #[[ATTR12]]
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP34]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
@@ -832,7 +831,6 @@ void test() {
 // CHECK1-NEXT:    br i1 [[TMP37]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
 // CHECK1:       .omp.reduction.then:
 // CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[TMP2]], ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]]) #[[ATTR12]]
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP34]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]

diff --git a/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp b/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
@@ -106,7 +106,6 @@ int bar(int n){
 // CHECK1-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK1-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK1-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[E1]], i64 8)
@@ -402,7 +401,6 @@ int bar(int n){
 // CHECK1-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK1-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK1-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @__kmpc_free_shared(ptr [[D2]], i64 4)
@@ -751,7 +749,6 @@ int bar(int n){
 // CHECK1:       cond.end:
 // CHECK1-NEXT:    [[COND:%.*]] = phi i16 [ [[TMP14]], [[COND_TRUE]] ], [ [[TMP15]], [[COND_FALSE]] ]
 // CHECK1-NEXT:    store i16 [[COND]], ptr [[TMP1]], align 2
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    ret void
@@ -821,7 +818,6 @@ int bar(int n){
 // CHECK1:       cond.end11:
 // CHECK1-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK1-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK1-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    ret void
@@ -1303,7 +1299,6 @@ int bar(int n){
 // CHECK2-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK2-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK2-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK2-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK2-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK2:       .omp.reduction.done:
 // CHECK2-NEXT:    call void @__kmpc_free_shared(ptr [[E1]], i32 8)
@@ -1599,7 +1594,6 @@ int bar(int n){
 // CHECK2-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK2-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK2-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK2-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK2-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK2:       .omp.reduction.done:
 // CHECK2-NEXT:    call void @__kmpc_free_shared(ptr [[D2]], i32 4)
@@ -1948,7 +1942,6 @@ int bar(int n){
 // CHECK2:       cond.end:
 // CHECK2-NEXT:    [[COND:%.*]] = phi i16 [ [[TMP14]], [[COND_TRUE]] ], [ [[TMP15]], [[COND_FALSE]] ]
 // CHECK2-NEXT:    store i16 [[COND]], ptr [[TMP1]], align 2
-// CHECK2-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK2-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK2:       .omp.reduction.done:
 // CHECK2-NEXT:    ret void
@@ -2018,7 +2011,6 @@ int bar(int n){
 // CHECK2:       cond.end11:
 // CHECK2-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK2-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK2-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK2-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK2:       .omp.reduction.done:
 // CHECK2-NEXT:    ret void
@@ -2500,7 +2492,6 @@ int bar(int n){
 // CHECK3-NEXT:    [[TMP8:%.*]] = load double, ptr [[E1]], align 8
 // CHECK3-NEXT:    [[ADD2:%.*]] = fadd double [[TMP7]], [[TMP8]]
 // CHECK3-NEXT:    store double [[ADD2]], ptr [[TMP0]], align 8
-// CHECK3-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP3]])
 // CHECK3-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK3:       .omp.reduction.done:
 // CHECK3-NEXT:    call void @__kmpc_free_shared(ptr [[E1]], i32 8)
@@ -2796,7 +2787,6 @@ int bar(int n){
 // CHECK3-NEXT:    [[TMP13:%.*]] = load float, ptr [[D2]], align 4
 // CHECK3-NEXT:    [[MUL8:%.*]] = fmul float [[TMP12]], [[TMP13]]
 // CHECK3-NEXT:    store float [[MUL8]], ptr [[TMP1]], align 4
-// CHECK3-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK3-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK3:       .omp.reduction.done:
 // CHECK3-NEXT:    call void @__kmpc_free_shared(ptr [[D2]], i32 4)
@@ -3145,7 +3135,6 @@ int bar(int n){
 // CHECK3:       cond.end:
 // CHECK3-NEXT:    [[COND:%.*]] = phi i16 [ [[TMP14]], [[COND_TRUE]] ], [ [[TMP15]], [[COND_FALSE]] ]
 // CHECK3-NEXT:    store i16 [[COND]], ptr [[TMP1]], align 2
-// CHECK3-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP5]])
 // CHECK3-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK3:       .omp.reduction.done:
 // CHECK3-NEXT:    ret void
@@ -3215,7 +3204,6 @@ int bar(int n){
 // CHECK3:       cond.end11:
 // CHECK3-NEXT:    [[COND12:%.*]] = phi i16 [ [[TMP15]], [[COND_TRUE9]] ], [ [[TMP16]], [[COND_FALSE10]] ]
 // CHECK3-NEXT:    store i16 [[COND12]], ptr [[TMP1]], align 2
-// CHECK3-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP6]])
 // CHECK3-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK3:       .omp.reduction.done:
 // CHECK3-NEXT:    ret void

diff --git a/clang/test/OpenMP/reduction_implicit_map.cpp b/clang/test/OpenMP/reduction_implicit_map.cpp
@@ -158,7 +158,6 @@ int main()
 // CHECK-NEXT:    [[TMP15:%.*]] = load double, ptr [[E2]], align 8
 // CHECK-NEXT:    [[ADD:%.*]] = fadd double [[TMP14]], [[TMP15]]
 // CHECK-NEXT:    store double [[ADD]], ptr [[ARRAYIDX]], align 8
-// CHECK-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP10]])
 // CHECK-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK:       .omp.reduction.done:
 // CHECK-NEXT:    ret void

diff --git a/clang/test/OpenMP/target_teams_generic_loop_codegen.cpp b/clang/test/OpenMP/target_teams_generic_loop_codegen.cpp
@@ -614,7 +614,6 @@ int foo() {
 // CHECK-NEXT:    [[OMP_ARRAYCPY_DONE16:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT15]], [[TMP43]]
 // CHECK-NEXT:    br i1 [[OMP_ARRAYCPY_DONE16]], label [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_BODY]]
 // CHECK:       omp.arraycpy.done17:
-// CHECK-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP38]])
 // CHECK-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK:       .omp.reduction.done:
 // CHECK-NEXT:    ret void
@@ -759,7 +758,6 @@ int foo() {
 // CHECK-NEXT:    [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP25]]
 // CHECK-NEXT:    br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY]]
 // CHECK:       omp.arraycpy.done19:
-// CHECK-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP21]])
 // CHECK-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK:       .omp.reduction.done:
 // CHECK-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_IS_LAST_ASCAST]], align 4
@@ -1348,7 +1346,6 @@ int foo() {
 // IR-GPU-NEXT:    [[OMP_ARRAYCPY_DONE16:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT15]], [[TMP42]]
 // IR-GPU-NEXT:    br i1 [[OMP_ARRAYCPY_DONE16]], label [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_BODY]]
 // IR-GPU:       omp.arraycpy.done17:
-// IR-GPU-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP38]])
 // IR-GPU-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // IR-GPU:       .omp.reduction.done:
 // IR-GPU-NEXT:    ret void
@@ -1495,7 +1492,6 @@ int foo() {
 // IR-GPU-NEXT:    [[OMP_ARRAYCPY_DONE18:%.*]] = icmp eq ptr [[OMP_ARRAYCPY_DEST_ELEMENT17]], [[TMP25]]
 // IR-GPU-NEXT:    br i1 [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_DONE19]], label [[OMP_ARRAYCPY_BODY]]
 // IR-GPU:       omp.arraycpy.done19:
-// IR-GPU-NEXT:    call void @__kmpc_nvptx_end_reduce_nowait(i32 [[TMP21]])
 // IR-GPU-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // IR-GPU:       .omp.reduction.done:
 // IR-GPU-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_IS_LAST_ASCAST]], align 4

diff --git a/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def b/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
@@ -471,7 +471,6 @@ __OMP_RTL(__kmpc_end_serialized_parallel, false, Void, IdentPtr, Int32)
 __OMP_RTL(__kmpc_shuffle_int32, false, Int32, Int32, Int16, Int16)
 __OMP_RTL(__kmpc_nvptx_parallel_reduce_nowait_v2, false, Int32, IdentPtr, Int32,
           Int32, SizeTy, VoidPtr, ShuffleReducePtr, InterWarpCopyPtr)
-__OMP_RTL(__kmpc_nvptx_end_reduce_nowait, false, Void, Int32)
 __OMP_RTL(__kmpc_nvptx_teams_reduce_nowait_v2, false, Int32, IdentPtr, Int32,
           VoidPtr, Int32, VoidPtr, ShuffleReducePtr, InterWarpCopyPtr,
           GlobalListPtr, GlobalListPtr, GlobalListPtr, GlobalListPtr)
@@ -1042,8 +1041,6 @@ __OMP_RTL_ATTRS(__kmpc_shuffle_int32, AttributeSet(), SExt,
                 ParamAttrs(SExt, SExt, SExt))
 __OMP_RTL_ATTRS(__kmpc_nvptx_parallel_reduce_nowait_v2, AttributeSet(), SExt,
                 ParamAttrs(AttributeSet(), SExt, SExt, SizeTyExt))
-__OMP_RTL_ATTRS(__kmpc_nvptx_end_reduce_nowait, AttributeSet(), AttributeSet(),
-                ParamAttrs(SExt))
 __OMP_RTL_ATTRS(__kmpc_nvptx_teams_reduce_nowait_v2, AttributeSet(), SExt,
                 ParamAttrs(AttributeSet(), SExt, AttributeSet(), ZExt))
 __OMP_RTL_ATTRS(__kmpc_reduction_get_fixed_buffer, GetterAttrs, AttributeSet(), ParamAttrs())

diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -4940,7 +4940,6 @@ struct AAKernelInfoCallSite : AAKernelInfo {
       case OMPRTL___kmpc_barrier:
       case OMPRTL___kmpc_nvptx_parallel_reduce_nowait_v2:
       case OMPRTL___kmpc_nvptx_teams_reduce_nowait_v2:
-      case OMPRTL___kmpc_nvptx_end_reduce_nowait:
       case OMPRTL___kmpc_error:
       case OMPRTL___kmpc_flush:
       case OMPRTL___kmpc_get_hardware_thread_id_in_block:

diff --git a/llvm/test/Transforms/OpenMP/add_attributes.ll b/llvm/test/Transforms/OpenMP/add_attributes.ll
@@ -722,8 +722,6 @@ declare void @__kmpc_kernel_prepare_parallel(ptr);
 
 declare i32 @__kmpc_masked(ptr, i32, i32);
 
-declare void @__kmpc_nvptx_end_reduce_nowait(i32);
-
 declare i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr, i32, i32, i64, ptr, ptr, ptr);
 
 declare i32 @__kmpc_nvptx_teams_reduce_nowait_v2(ptr, i32, ptr, i32, ptr, ptr, ptr, ptr, ptr, ptr, ptr);
@@ -1367,9 +1365,6 @@ declare i32 @__tgt_target_kernel_nowait(ptr, i64, i32, i32, ptr, ptr, i32, ptr,
 ; CHECK: ; Function Attrs: nounwind
 ; CHECK: declare i32 @__kmpc_masked(ptr, i32, i32)
 
-; CHECK-NOT: Function Attrs
-; CHECK: declare void @__kmpc_nvptx_end_reduce_nowait(i32)
-
 ; CHECK-NOT: Function Attrs
 ; CHECK: declare i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr, i32, i32, i64, ptr, ptr, ptr)
 
@@ -2015,9 +2010,6 @@ declare i32 @__tgt_target_kernel_nowait(ptr, i64, i32, i32, ptr, ptr, i32, ptr,
 ; OPTIMISTIC: ; Function Attrs: nofree nosync nounwind willreturn memory(argmem: readwrite, inaccessiblemem: readwrite)
 ; OPTIMISTIC: declare i32 @__kmpc_masked(ptr nocapture nofree readonly, i32, i32)
 
-; OPTIMISTIC-NOT: Function Attrs
-; OPTIMISTIC: declare void @__kmpc_nvptx_end_reduce_nowait(i32)
-
 ; OPTIMISTIC-NOT: Function Attrs
 ; OPTIMISTIC: declare i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr, i32, i32, i64, ptr, ptr, ptr)
 
@@ -2676,9 +2668,6 @@ declare i32 @__tgt_target_kernel_nowait(ptr, i64, i32, i32, ptr, ptr, i32, ptr,
 ; EXT: ; Function Attrs: nounwind
 ; EXT: declare signext i32 @__kmpc_masked(ptr, i32 signext, i32 signext)
 
-; EXT-NOT: Function Attrs
-; EXT: declare void @__kmpc_nvptx_end_reduce_nowait(i32 signext)
-
 ; EXT-NOT: Function Attrs
 ; EXT: declare signext i32 @__kmpc_nvptx_parallel_reduce_nowait_v2(ptr, i32 signext, i32 signext, i64, ptr, ptr, ptr)
 

diff --git a/openmp/libomptarget/DeviceRTL/include/Interface.h b/openmp/libomptarget/DeviceRTL/include/Interface.h
@@ -230,10 +230,6 @@ void __kmpc_target_deinit();
 /// Reduction
 ///
 ///{
-void __kmpc_nvptx_end_reduce(int32_t TId);
-
-void __kmpc_nvptx_end_reduce_nowait(int32_t TId);
-
 void *__kmpc_reduction_get_fixed_buffer();
 
 int32_t __kmpc_nvptx_parallel_reduce_nowait_v2(

diff --git a/openmp/libomptarget/DeviceRTL/src/Reduction.cpp b/openmp/libomptarget/DeviceRTL/src/Reduction.cpp
@@ -335,10 +335,6 @@ int32_t __kmpc_nvptx_teams_reduce_nowait_v2(
 
   return 0;
 }
-
-void __kmpc_nvptx_end_reduce(int32_t TId) {}
-
-void __kmpc_nvptx_end_reduce_nowait(int32_t TId) {}
 }
 
 void *__kmpc_reduction_get_fixed_buffer() {