diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
index 97b8f79..21911c9 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -56,12 +56,12 @@
   /// Call to int64_t __kmpc_shuffle_int64(int64_t element,
   /// int16_t lane_offset, int16_t warp_size);
   OMPRTL_NVPTX__kmpc_shuffle_int64,
-  /// Call to __kmpc_nvptx_parallel_reduce_nowait(kmp_int32
+  /// Call to __kmpc_nvptx_parallel_reduce_nowait_v2(ident_t *loc, kmp_int32
   /// global_tid, kmp_int32 num_vars, size_t reduce_size, void* reduce_data,
   /// void (*kmp_ShuffleReductFctPtr)(void *rhsData, int16_t lane_id, int16_t
   /// lane_offset, int16_t shortCircuit),
   /// void (*kmp_InterWarpCopyFctPtr)(void* src, int32_t warp_num));
-  OMPRTL_NVPTX__kmpc_parallel_reduce_nowait,
+  OMPRTL_NVPTX__kmpc_parallel_reduce_nowait_v2,
   /// Call to __kmpc_nvptx_teams_reduce_nowait_simple(ident_t *loc, kmp_int32
   /// global_tid, kmp_critical_name *lck)
   OMPRTL_NVPTX__kmpc_nvptx_teams_reduce_nowait_simple,
@@ -91,10 +91,11 @@
   OMPRTL_NVPTX__kmpc_parallel_level,
   /// Call to int8_t __kmpc_is_spmd_exec_mode();
   OMPRTL_NVPTX__kmpc_is_spmd_exec_mode,
-  /// Call to void __kmpc_get_team_static_memory(const void *buf, size_t size,
-  /// int16_t is_shared, const void **res);
+  /// Call to void __kmpc_get_team_static_memory(int16_t isSPMDExecutionMode,
+  /// const void *buf, size_t size, int16_t is_shared, const void **res);
   OMPRTL_NVPTX__kmpc_get_team_static_memory,
-  /// Call to void __kmpc_restore_team_static_memory(int16_t is_shared);
+  /// Call to void __kmpc_restore_team_static_memory(int16_t
+  /// isSPMDExecutionMode, int16_t is_shared);
   OMPRTL_NVPTX__kmpc_restore_team_static_memory,
   /// Call to void __kmpc_barrier(ident_t *loc, kmp_int32 global_tid);
   OMPRTL__kmpc_barrier,
@@ -1646,12 +1647,12 @@
     RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_shuffle_int64");
     break;
   }
-  case OMPRTL_NVPTX__kmpc_parallel_reduce_nowait: {
-    // Build int32_t kmpc_nvptx_parallel_reduce_nowait(kmp_int32 global_tid,
-    // kmp_int32 num_vars, size_t reduce_size, void* reduce_data,
-    // void (*kmp_ShuffleReductFctPtr)(void *rhsData, int16_t lane_id, int16_t
-    // lane_offset, int16_t Algorithm Version),
-    // void (*kmp_InterWarpCopyFctPtr)(void* src, int warp_num));
+  case OMPRTL_NVPTX__kmpc_parallel_reduce_nowait_v2: {
+    // Build int32_t kmpc_nvptx_parallel_reduce_nowait_v2(ident_t *loc,
+    // kmp_int32 global_tid, kmp_int32 num_vars, size_t reduce_size, void*
+    // reduce_data, void (*kmp_ShuffleReductFctPtr)(void *rhsData, int16_t
+    // lane_id, int16_t lane_offset, int16_t Algorithm Version), void
+    // (*kmp_InterWarpCopyFctPtr)(void* src, int warp_num));
     llvm::Type *ShuffleReduceTypeParams[] = {CGM.VoidPtrTy, CGM.Int16Ty,
                                              CGM.Int16Ty, CGM.Int16Ty};
     auto *ShuffleReduceFnTy =
@@ -1661,7 +1662,8 @@
     auto *InterWarpCopyFnTy =
         llvm::FunctionType::get(CGM.VoidTy, InterWarpCopyTypeParams,
                                 /*isVarArg=*/false);
-    llvm::Type *TypeParams[] = {CGM.Int32Ty,
+    llvm::Type *TypeParams[] = {getIdentTyPointerTy(),
+                                CGM.Int32Ty,
                                 CGM.Int32Ty,
                                 CGM.SizeTy,
                                 CGM.VoidPtrTy,
@@ -1670,7 +1672,7 @@
     auto *FnTy =
         llvm::FunctionType::get(CGM.Int32Ty, TypeParams, /*isVarArg=*/false);
     RTLFn = CGM.CreateRuntimeFunction(
-        FnTy, /*Name=*/"__kmpc_nvptx_parallel_reduce_nowait");
+        FnTy, /*Name=*/"__kmpc_nvptx_parallel_reduce_nowait_v2");
     break;
   }
   case OMPRTL_NVPTX__kmpc_end_reduce_nowait: {
@@ -1779,19 +1781,21 @@
     break;
   }
   case OMPRTL_NVPTX__kmpc_get_team_static_memory: {
-    // Build void __kmpc_get_team_static_memory(const void *buf, size_t size,
-    // int16_t is_shared, const void **res);
-    llvm::Type *TypeParams[] = {CGM.VoidPtrTy, CGM.SizeTy, CGM.Int16Ty,
-                                CGM.VoidPtrPtrTy};
+    // Build void __kmpc_get_team_static_memory(int16_t isSPMDExecutionMode,
+    // const void *buf, size_t size, int16_t is_shared, const void **res);
+    llvm::Type *TypeParams[] = {CGM.Int16Ty, CGM.VoidPtrTy, CGM.SizeTy,
+                                CGM.Int16Ty, CGM.VoidPtrPtrTy};
     auto *FnTy =
         llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
     RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_get_team_static_memory");
     break;
   }
   case OMPRTL_NVPTX__kmpc_restore_team_static_memory: {
-    // Build void __kmpc_restore_team_static_memory(int16_t is_shared);
+    // Build void __kmpc_restore_team_static_memory(int16_t isSPMDExecutionMode,
+    // int16_t is_shared);
+    llvm::Type *TypeParams[] = {CGM.Int16Ty, CGM.Int16Ty};
     auto *FnTy =
-        llvm::FunctionType::get(CGM.VoidTy, CGM.Int16Ty, /*isVarArg=*/false);
+        llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg=*/false);
     RTLFn =
         CGM.CreateRuntimeFunction(FnTy, "__kmpc_restore_team_static_memory");
     break;
@@ -2211,8 +2215,11 @@
             CGM.getContext().getSizeType(), Loc);
         llvm::Value *ResAddr = Bld.CreatePointerBitCastOrAddrSpaceCast(
             KernelStaticGlobalized, CGM.VoidPtrPtrTy);
-        llvm::Value *GlobalRecordSizeArg[] = {StaticGlobalized, Ld,
-                                              IsInSharedMemory, ResAddr};
+        llvm::Value *GlobalRecordSizeArg[] = {
+            llvm::ConstantInt::get(
+                CGM.Int16Ty,
+                getExecutionMode() == CGOpenMPRuntimeNVPTX::EM_SPMD ? 1 : 0),
+            StaticGlobalized, Ld, IsInSharedMemory, ResAddr};
         CGF.EmitRuntimeCall(createNVPTXRuntimeFunction(
                                 OMPRTL_NVPTX__kmpc_get_team_static_memory),
                             GlobalRecordSizeArg);
@@ -2400,10 +2407,15 @@
               Address(GlobalizedRecords.back().UseSharedMemory,
                       CGM.getContext().getTypeAlignInChars(Int16Ty)),
               /*Volatile=*/false, Int16Ty, GlobalizedRecords.back().Loc);
+          llvm::Value *Args[] = {
+              llvm::ConstantInt::get(
+                  CGM.Int16Ty,
+                  getExecutionMode() == CGOpenMPRuntimeNVPTX::EM_SPMD ? 1 : 0),
+              IsInSharedMemory};
           CGF.EmitRuntimeCall(
               createNVPTXRuntimeFunction(
                   OMPRTL_NVPTX__kmpc_restore_team_static_memory),
-              IsInSharedMemory);
+              Args);
         }
       } else {
         CGF.EmitRuntimeCall(createNVPTXRuntimeFunction(
@@ -3608,7 +3620,7 @@
 /// 3. Call the OpenMP runtime on the GPU to reduce within a team
 ///    and store the result on the team master:
 ///
-///     __kmpc_nvptx_parallel_reduce_nowait(...,
+///     __kmpc_nvptx_parallel_reduce_nowait_v2(...,
 ///        reduceData, shuffleReduceFn, interWarpCpyFn)
 ///
 ///     where:
@@ -3779,7 +3791,7 @@
 /// Intra-Team Reduction
 ///
 /// This function, as implemented in the runtime call
-/// '__kmpc_nvptx_parallel_reduce_nowait', aggregates data across OpenMP
+/// '__kmpc_nvptx_parallel_reduce_nowait_v2', aggregates data across OpenMP
 /// threads in a team.  It first reduces within a warp using the
 /// aforementioned algorithms.  We then proceed to gather all such
 /// reduced values at the first warp.
@@ -3802,7 +3814,7 @@
 /// 'loadAndReduceDataFn' to load and reduce values from the array, i.e.,
 /// the k'th worker reduces every k'th element.
 ///
-/// Finally, a call is made to '__kmpc_nvptx_parallel_reduce_nowait' to
+/// Finally, a call is made to '__kmpc_nvptx_parallel_reduce_nowait_v2' to
 /// reduce across workers and compute a globally reduced value.
 ///
 void CGOpenMPRuntimeNVPTX::emitReduction(
@@ -3832,6 +3844,7 @@
   // RedList, shuffle_reduce_func, interwarp_copy_func);
   // or
   // Build res = __kmpc_reduce_teams_nowait_simple(<loc>, <gtid>, <lck>);
+  llvm::Value *RTLoc = emitUpdateLocation(CGF, Loc);
   llvm::Value *ThreadId = getThreadID(CGF, Loc);
 
   llvm::Value *Res;
@@ -3886,19 +3899,19 @@
     llvm::Value *InterWarpCopyFn =
         emitInterWarpCopyFunction(CGM, Privates, ReductionArrayTy, Loc);
 
-    llvm::Value *Args[] = {ThreadId,
+    llvm::Value *Args[] = {RTLoc,
+                           ThreadId,
                            CGF.Builder.getInt32(RHSExprs.size()),
                            ReductionArrayTySize,
                            RL,
                            ShuffleAndReduceFn,
                            InterWarpCopyFn};
 
-    Res = CGF.EmitRuntimeCall(
-        createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_parallel_reduce_nowait),
-        Args);
+    Res = CGF.EmitRuntimeCall(createNVPTXRuntimeFunction(
+                                  OMPRTL_NVPTX__kmpc_parallel_reduce_nowait_v2),
+                              Args);
   } else {
     assert(TeamsReduction && "expected teams reduction.");
-    llvm::Value *RTLoc = emitUpdateLocation(CGF, Loc);
     std::string Name = getName({"reduction"});
     llvm::Value *Lock = getCriticalRegionLock(Name);
     llvm::Value *Args[] = {RTLoc, ThreadId, Lock};