Fix PPC unaligned 64-bit loads and stores

PPC64 supports unaligned loads and stores of 64-bit values, but
in order to use the r+i forms, the offset must be a multiple of 4.
Unfortunately, this cannot always be determined by examining the
immediate itself because it might be available only via a TOC entry.

In order to get around this issue, we additionally predicate the
selection of the r+i form on the alignment of the load or store
(forcing it to be at least 4 in order to select the r+i form).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177338 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/PowerPC/unal4-std.ll b/test/CodeGen/PowerPC/unal4-std.ll
new file mode 100644
index 0000000..dc4c20c
--- /dev/null
+++ b/test/CodeGen/PowerPC/unal4-std.ll
@@ -0,0 +1,24 @@
+; RUN: llc < %s -mcpu=pwr7 | FileCheck %s
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define fastcc void @copy_to_conceal() #0 {
+entry:
+  br i1 undef, label %if.then, label %if.end210
+
+if.then:                                          ; preds = %entry
+  br label %vector.body.i
+
+vector.body.i:                                    ; preds = %vector.body.i, %if.then
+  %index.i = phi i64 [ 0, %vector.body.i ], [ 0, %if.then ]
+  store <8 x i16> zeroinitializer, <8 x i16>* undef, align 2
+  br label %vector.body.i
+
+if.end210:                                        ; preds = %entry
+  ret void
+
+; CHECK: @copy_to_conceal
+; CHECK: stdx {{[0-9]+}}, 0,
+}
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }