Index: lib/Target/X86/X86SelectionDAGInfo.cpp
===================================================================
--- lib/Target/X86/X86SelectionDAGInfo.cpp
+++ lib/Target/X86/X86SelectionDAGInfo.cpp
@@ -236,6 +236,7 @@
   // If the target has enhanced REPMOVSB, then it's at least as fast to use
   // REP MOVSB instead of REP MOVS{W,D,Q}, and it avoids having to handle
   // BytesLeft.
+  bool Use64BitRegs = Subtarget.isTarget64BitLP64();
   if (!Subtarget.hasERMSB() && !(Align & 1)) {
     if (Align & 2)
       // WORD aligned
@@ -245,7 +246,7 @@
       Repeats.AVT = MVT::i32;
     else
       // QWORD aligned
-      Repeats.AVT = Subtarget.is64Bit() ? MVT::i64 : MVT::i32;
+      Repeats.AVT = Use64BitRegs ? MVT::i64 : MVT::i32;
 
     if (Repeats.BytesLeft() > 0 &&
         DAG.getMachineFunction().getFunction().optForMinSize()) {
@@ -256,13 +257,13 @@
   }
 
   SDValue InFlag;
-  Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RCX : X86::ECX,
+  Chain = DAG.getCopyToReg(Chain, dl, Use64BitRegs ? X86::RCX : X86::ECX,
                            DAG.getIntPtrConstant(Repeats.Count(), dl), InFlag);
   InFlag = Chain.getValue(1);
-  Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RDI : X86::EDI,
+  Chain = DAG.getCopyToReg(Chain, dl, Use64BitRegs ? X86::RDI : X86::EDI,
                            Dst, InFlag);
   InFlag = Chain.getValue(1);
-  Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RSI : X86::ESI,
+  Chain = DAG.getCopyToReg(Chain, dl, Use64BitRegs ? X86::RSI : X86::ESI,
                            Src, InFlag);
   InFlag = Chain.getValue(1);
 
Index: test/CodeGen/X86/pr38865.ll
===================================================================
--- /dev/null
+++ test/CodeGen/X86/pr38865.ll
@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s | FileCheck %s
+
+target datalayout = "e-m:e-p:32:32-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnux32"
+
+%struct.a = type { [65 x i32] }
+
+@c = global %struct.a zeroinitializer, align 4
+
+define void @e() nounwind {
+; CHECK-LABEL: e:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    subl $528, %esp # imm = 0x210
+; CHECK-NEXT:    leal {{[0-9]+}}(%rsp), %ebx
+; CHECK-NEXT:    movl $c, %esi
+; CHECK-NEXT:    movl $260, %edx # imm = 0x104
+; CHECK-NEXT:    movl %ebx, %edi
+; CHECK-NEXT:    callq memcpy
+; CHECK-NEXT:    movl $65, %ecx
+; CHECK-NEXT:    movl %esp, %edi
+; CHECK-NEXT:    movl %ebx, %esi
+; CHECK-NEXT:    rep;movsl
+; CHECK-NEXT:    callq d
+; CHECK-NEXT:    addl $528, %esp # imm = 0x210
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    retq
+entry:
+  %byval-temp = alloca %struct.a, align 8
+  %0 = bitcast %struct.a* %byval-temp to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* nonnull align 8 %0, i8* align 4 bitcast (%struct.a* @c to i8*), i32 260, i1 false)
+  call void @d(%struct.a* byval nonnull align 8 %byval-temp)
+  ret void
+}
+
+declare void @d(%struct.a* byval align 8) local_unnamed_addr #1
+
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)