Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -3338,15 +3338,18 @@
     // Create a temporary array to hold the sizes of local pointer arguments
     // for the block. \p First is the position of the first size argument.
     auto CreateArrayForSizeVar = [=](unsigned First) {
-      auto *AT = llvm::ArrayType::get(SizeTy, NumArgs - First);
-      auto *Arr = Builder.CreateAlloca(AT);
+      llvm::APInt ArraySize(32, NumArgs - First);
+      QualType SizeArrayTy = getContext().getConstantArrayType(
+          getContext().getSizeType(), ArraySize, ArrayType::Normal,
+          /*IndexTypeQuals=*/0);
+      auto Tmp = CreateMemTemp(SizeArrayTy, "block_sizes");
       llvm::Value *Ptr;
       // Each of the following arguments specifies the size of the corresponding
       // argument passed to the enqueued block.
       auto *Zero = llvm::ConstantInt::get(IntTy, 0);
       for (unsigned I = First; I < NumArgs; ++I) {
         auto *Index = llvm::ConstantInt::get(IntTy, I - First);
-        auto *GEP = Builder.CreateGEP(Arr, {Zero, Index});
+        auto *GEP = Builder.CreateGEP(Tmp.getPointer(), {Zero, Index});
         if (I == First)
           Ptr = GEP;
         auto *V =
Index: test/CodeGenOpenCL/enqueue-kernel-non-entry-block.cl
===================================================================
--- /dev/null
+++ test/CodeGenOpenCL/enqueue-kernel-non-entry-block.cl
@@ -0,0 +1,31 @@
+// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -emit-llvm -o - -triple amdgcn < %s | FileCheck %s --check-prefixes=COMMON,AMDGPU
+// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -emit-llvm -o - -triple "spir-unknown-unknown" < %s | FileCheck %s --check-prefixes=COMMON,SPIR32
+// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -emit-llvm -o - -triple "spir64-unknown-unknown" < %s | FileCheck %s --check-prefixes=COMMON,SPIR64
+// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -debug-info-kind=limited -emit-llvm -o - -triple amdgcn < %s | FileCheck %s --check-prefixes=CHECK-DEBUG
+
+// Check that the enqueue_kernel array temporary is in the entry block to avoid
+// a dynamic alloca
+
+typedef struct {int a;} ndrange_t;
+
+kernel void test(int i) {
+// COMMON-LABEL: define {{.*}} void @test
+// COMMON-LABEL: entry:
+// AMDGPU: %block_sizes = alloca [1 x i64]
+// SPIR32: %block_sizes = alloca [1 x i32]
+// SPIR64: %block_sizes = alloca [1 x i64]
+// COMMON-LABEL: if.then:
+// COMMON-NOT: alloca
+// CHECK-DEBUG: getelementptr {{.*}} %block_sizes, {{.*}} !dbg !34
+// COMMON-LABEL: if.end
+  queue_t default_queue;
+  unsigned flags = 0;
+  ndrange_t ndrange;
+  if (i)
+    enqueue_kernel(default_queue, flags, ndrange, ^(local void *a) { }, 32);
+}
+
+// Check that the temporary is scoped to the `if`
+
+// CHECK-DEBUG: !32 = distinct !DILexicalBlock(scope: !7, file: !1, line: 24)
+// CHECK-DEBUG: !34 = !DILocation(line: 25, scope: !32)