Pull in r180121 from upstream llvm trunk:

  LoopVectorizer: Fix 15830. When scalarizing and unrolling stores make
  sure that the order in which the elements are scalarized is the same
  as the original order.
  This fixes a miscompilation in FreeBSD's regex library.

This should fix lib/libc/regex/regcomp.c at -O3 with clang 3.3 r178860
on CPUs with SSE.  Before this change, the vectorizer could incorrectly
rearrange the second loop in computejumps(), leading to possibly invalid
entries in the re_gets::charjump table.

The net result was that for example "sed s/@CC@/foo/" failed to work
correctly, leading to trouble with many configure scripts.

1 files changed, 4 insertions, 4 deletions

diff --git a/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index acf2b81..8d51df4 100644
--- a/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1040,10 +1040,10 @@ void InnerLoopVectorizer::scalarizeInstruction(Instruction *Instr) {
   // Create a new entry in the WidenMap and initialize it to Undef or Null.
   VectorParts &VecResults = WidenMap.splat(Instr, UndefVec);
 
-  // For each scalar that we create:
-  for (unsigned Width = 0; Width < VF; ++Width) {
-    // For each vector unroll 'part':
-    for (unsigned Part = 0; Part < UF; ++Part) {
+  // For each vector unroll 'part':
+  for (unsigned Part = 0; Part < UF; ++Part) {
+    // For each scalar that we create:
+    for (unsigned Width = 0; Width < VF; ++Width) {
       Instruction *Cloned = Instr->clone();
       if (!IsVoidRetTy)
         Cloned->setName(Instr->getName() + ".cloned");