Index: llvm/trunk/lib/Target/AMDGPU/SILowerI1Copies.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SILowerI1Copies.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SILowerI1Copies.cpp
@@ -17,6 +17,7 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "SIInstrInfo.h"
+#include "Utils/AMDGPULaneDominator.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
@@ -141,7 +142,8 @@
               DefInst->getOperand(3).getReg()) &&
             TRI->getCommonSubClass(
               MRI.getRegClass(DefInst->getOperand(3).getReg()),
-              &AMDGPU::SGPR_64RegClass)) {
+              &AMDGPU::SGPR_64RegClass) &&
+            AMDGPU::laneDominates(DefInst->getParent(), &MBB)) {
           BuildMI(MBB, &MI, DL, TII->get(AMDGPU::S_AND_B64))
               .add(Dst)
               .addReg(AMDGPU::EXEC)
Index: llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.h
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.h
+++ llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.h
@@ -0,0 +1,24 @@
+//===- AMDGPULaneDominator.h ------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPULANEDOMINATOR_H
+#define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPULANEDOMINATOR_H
+
+namespace llvm {
+
+class MachineBasicBlock;
+
+namespace AMDGPU {
+
+bool laneDominates(MachineBasicBlock *MBBA, MachineBasicBlock *MBBB);
+
+} // end namespace AMDGPU
+} // end namespace llvm
+
+#endif // LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPULANEDOMINATOR_H
Index: llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.cpp
+++ llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPULaneDominator.cpp
@@ -0,0 +1,75 @@
+//===-- AMDGPULaneDominator.cpp - Determine Lane Dominators ---------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// MBB A lane-dominates MBB B if
+// 1. A dominates B in the usual sense, i.e. every path from the entry to B
+//    goes through A, and
+// 2. whenever B executes, every active lane during that execution of B was
+//    also active during the most recent execution of A.
+//
+// The simplest example where A dominates B but does not lane-dominate it is
+// where A is a loop:
+//
+//     |
+//     +--+
+//     A  |
+//     +--+
+//     |
+//     B
+//
+// Unfortunately, the second condition is not fully captured by the control
+// flow graph when it is unstructured (as may happen when branch conditions are
+// uniform).
+//
+// The following replacement of the second condition is a conservative
+// approximation. It is an equivalent condition when the CFG is fully
+// structured:
+//
+// 2'. every cycle in the CFG that contains A also contains B.
+//
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPULaneDominator.h"
+
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+
+namespace llvm {
+
+namespace AMDGPU {
+
+// Given machine basic blocks A and B where A dominates B, check whether
+// A lane-dominates B.
+//
+// The check is conservative, i.e. there can be false-negatives.
+bool laneDominates(MachineBasicBlock *A, MachineBasicBlock *B) {
+  // Check whether A is reachable from itself without going through B.
+  DenseSet<MachineBasicBlock *> Reachable;
+  SmallVector<MachineBasicBlock *, 8> Stack;
+
+  Stack.push_back(A);
+  do {
+    MachineBasicBlock *MBB = Stack.back();
+    Stack.pop_back();
+
+    for (MachineBasicBlock *Succ : MBB->successors()) {
+      if (Succ == A)
+        return false;
+      if (Succ != B && Reachable.insert(Succ).second)
+        Stack.push_back(Succ);
+    }
+  } while (!Stack.empty());
+
+  return true;
+}
+
+} // namespace AMDGPU
+
+} // namespace llvm
Index: llvm/trunk/lib/Target/AMDGPU/Utils/CMakeLists.txt
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/Utils/CMakeLists.txt
+++ llvm/trunk/lib/Target/AMDGPU/Utils/CMakeLists.txt
@@ -2,4 +2,5 @@
   AMDGPUBaseInfo.cpp
   AMDKernelCodeTUtils.cpp
   AMDGPUAsmUtils.cpp
+  AMDGPULaneDominator.cpp
   )
Index: llvm/trunk/test/CodeGen/AMDGPU/i1-copy-from-loop.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/i1-copy-from-loop.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/i1-copy-from-loop.ll
@@ -0,0 +1,48 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
+
+; SI-LABEL: {{^}}i1_copy_from_loop:
+;
+; Cannot use an SGPR mask to copy %cc out of the loop, since the mask would
+; only contain the lanes that were active during the last loop iteration.
+;
+; SI: ; %for.body
+; SI: v_cmp_gt_u32_e64 [[SREG:s\[[0-9]+:[0-9]+\]]], 4,
+; SI: v_cndmask_b32_e64 [[VREG:v[0-9]+]], 0, -1, [[SREG]]
+; SI-NOT: [[VREG]]
+; SI: ; %for.end
+; SI: v_cmp_ne_u32_e32 vcc, 0, [[VREG]]
+define amdgpu_ps void @i1_copy_from_loop(<4 x i32> inreg %rsrc, i32 %tid) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i32 [0, %entry], [%i.inc, %end.loop]
+  %cc = icmp ult i32 %i, 4
+  br i1 %cc, label %mid.loop, label %for.end
+
+mid.loop:
+  %v = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 %tid, i32 %i, i1 false, i1 false)
+  %cc2 = fcmp oge float %v, 0.0
+  br i1 %cc2, label %end.loop, label %for.end
+
+end.loop:
+  %i.inc = add i32 %i, 1
+  br label %for.body
+
+for.end:
+  br i1 %cc, label %if, label %end
+
+if:
+  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float undef, float undef, float undef, float undef, i1 true, i1 true)
+  br label %end
+
+end:
+  ret void
+}
+
+declare float @llvm.amdgcn.buffer.load.f32(<4 x i32>, i32, i32, i1, i1) #0
+declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #1
+
+attributes #0 = { nounwind readonly }
+attributes #1 = { nounwind inaccessiblememonly }