Index: llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h
+++ llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h
@@ -186,7 +186,8 @@
     /// BUILD_PAIR - This is the opposite of EXTRACT_ELEMENT in some ways.
     /// Given two values of the same integer value type, this produces a value
     /// twice as big.  Like EXTRACT_ELEMENT, this can only be used before
-    /// legalization.
+    /// legalization. The lower part of the composite value should be in
+    /// element 0 and the upper part should be in element 1.
     BUILD_PAIR,
 
     /// MERGE_VALUES - This node takes multiple discrete operands and returns
Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -8622,6 +8622,13 @@
 
   LoadSDNode *LD1 = dyn_cast<LoadSDNode>(getBuildPairElt(N, 0));
   LoadSDNode *LD2 = dyn_cast<LoadSDNode>(getBuildPairElt(N, 1));
+
+  // A BUILD_PAIR is always having the least significant part in elt 0 and the
+  // most significant part in elt 1. So when combining into one large load, we
+  // need to consider the endianness.
+  if (DAG.getDataLayout().isBigEndian())
+    std::swap(LD1, LD2);
+
   if (!LD1 || !LD2 || !ISD::isNON_EXTLoad(LD1) || !LD1->hasOneUse() ||
       LD1->getAddressSpace() != LD2->getAddressSpace())
     return SDValue();
Index: llvm/trunk/test/CodeGen/PowerPC/combine_loads_from_build_pair.ll
===================================================================
--- llvm/trunk/test/CodeGen/PowerPC/combine_loads_from_build_pair.ll
+++ llvm/trunk/test/CodeGen/PowerPC/combine_loads_from_build_pair.ll
@@ -0,0 +1,19 @@
+; RUN: llc -verify-machineinstrs -O0 -mcpu=g4 -mtriple=powerpc-apple-darwin8 < %s -debug -stop-after=machineverifier 2>&1 | FileCheck %s
+
+define i64 @func1(i64 %p1, i64 %p2, i64 %p3, i64 %p4, { i64, i8* } %struct) {
+; Verify that we get a combine on the build_pair, creating a LD8 load somewhere
+; between "Initial selection DAG" and "Optimized lowered selection DAG".
+; The target is big-endian, and stack grows towards higher addresses,
+; so we expect the LD8 to load from the address used in the original HIBITS
+; load.
+; CHECK-LABEL: Initial selection DAG:
+; CHECK-DAG:     [[LOBITS:t[0-9]+]]: i32,ch = load<LD4[FixedStack-2]>
+; CHECK-DAG:     [[HIBITS:t[0-9]+]]: i32,ch = load<LD4[FixedStack-1]>
+; CHECK: Combining: t{{[0-9]+}}: i64 = build_pair [[LOBITS]], [[HIBITS]]
+; CHECK-NEXT: into
+; CHECK-SAME: load<LD8[FixedStack-1]
+; CHECK-LABEL: Optimized lowered selection DAG:
+  %result = extractvalue {i64, i8* } %struct, 0
+  ret i64 %result
+}
+