Index: test/GPGPU/invariant-load-hoisting-with-variable-lower-bound.ll
===================================================================
--- /dev/null
+++ test/GPGPU/invariant-load-hoisting-with-variable-lower-bound.ll
@@ -0,0 +1,51 @@
+; RUN: opt %loadPolly -analyze  -polly-scops < %s | FileCheck %s -check-prefix=SCOP
+; RUN: opt %loadPolly -S  -polly-codegen-ppcg -polly-invariant-load-hoisting < %s | FileCheck %s -check-prefix=HOST-IR
+
+; REQUIRES: pollyacc
+
+; Check that we detect a scop.
+; SCOP:       Function: checkScalarKill
+; SCOP-NEXT: Region: %XLoopInit---%for.end
+; SCOP-NEXT: Max Loop Depth:  1
+
+
+; Check that kernel launch is generated in host IR.
+; the declare would not be generated unless a call to a kernel exists.
+; HOST-IR: declare void @polly_launchKernel(i8*, i32, i32, i32, i32, i32, i8*)
+
+; Check if we generate GPU code for simple loop with variable lower bound
+;    void breakInvaritantLoadHoisting(int *idx, int *arr) {
+;      for (int i = *idx; i < 100; i++) {
+;        arr[i] = 0;
+;      }
+;    }
+;
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @breakInvaritantLoadHoisting(i32* %idx, i32* %arr) {
+entry:
+  br label %entry.split
+
+entry.split:                                      ; preds = %entry
+  %tmp1 = load i32, i32* %idx, align 4
+  %cmp1 = icmp slt i32 %tmp1, 100
+  br i1 %cmp1, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry.split
+  %0 = sext i32 %tmp1 to i64
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %indvars.iv = phi i64 [ %0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %indvars.iv
+  store i32 0, i32* %arrayidx, align 4
+  %indvars.iv.next = add nsw i64 %indvars.iv, 1
+  %cmp = icmp slt i64 %indvars.iv, 99
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry.split
+  ret void
+}
Index: test/GPGPU/invariant-load-hoisting-with-variable-upper-bound.ll
===================================================================
--- /dev/null
+++ test/GPGPU/invariant-load-hoisting-with-variable-upper-bound.ll
@@ -0,0 +1,52 @@
+; RUN: opt %loadPolly -analyze  -polly-scops < %s | FileCheck %s -check-prefix=SCOP
+; RUN: opt %loadPolly -S  -polly-codegen-ppcg -polly-invariant-load-hoisting < %s | FileCheck %s -check-prefix=HOST-IR
+
+; REQUIRES: pollyacc
+
+; Check that we detect a scop.
+; SCOP:       Function: checkScalarKill
+; SCOP-NEXT: Region: %XLoopInit---%for.end
+; SCOP-NEXT: Max Loop Depth:  1
+
+
+; Check that kernel launch is generated in host IR.
+; the declare would not be generated unless a call to a kernel exists.
+; HOST-IR: declare void @polly_launchKernel(i8*, i32, i32, i32, i32, i32, i8*)
+
+; Check if we generate GPU code for simple loop with variable upper bound
+;    void breakInvaritantLoadHoisting(int *idx, int *arr) {
+;      for (int i = 0; i < *idx; i++) {
+;        arr[i] = 0;
+;      }
+;    }
+;
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @breakInvaritantLoadHoisting(i32* %idx, i32* %arr) {
+entry:
+  br label %entry.split
+
+entry.split:                                      ; preds = %entry
+  %tmp21 = load i32, i32* %idx, align 4
+  %cmp2 = icmp sgt i32 %tmp21, 0
+  br i1 %cmp2, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry.split
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %indvars.iv
+  store i32 0, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %tmp2 = load i32, i32* %idx, align 4
+  %0 = sext i32 %tmp2 to i64
+  %cmp = icmp slt i64 %indvars.iv.next, %0
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry.split
+  ret void
+}