Index: llvm/trunk/lib/IR/Function.cpp
===================================================================
--- llvm/trunk/lib/IR/Function.cpp
+++ llvm/trunk/lib/IR/Function.cpp
@@ -154,10 +154,8 @@
 /// it in its containing function.
 bool Argument::hasStructRetAttr() const {
   if (!getType()->isPointerTy()) return false;
-  if (this != getParent()->arg_begin())
-    return false; // StructRet param must be first param
   return getParent()->getAttributes().
-    hasAttribute(1, Attribute::StructRet);
+    hasAttribute(getArgNo()+1, Attribute::StructRet);
 }
 
 /// hasReturnedAttr - Return true if this argument has the returned attribute on
Index: llvm/trunk/lib/Transforms/IPO/ArgumentPromotion.cpp
===================================================================
--- llvm/trunk/lib/Transforms/IPO/ArgumentPromotion.cpp
+++ llvm/trunk/lib/Transforms/IPO/ArgumentPromotion.cpp
@@ -245,6 +245,24 @@
     Argument *PtrArg = PointerArgs[i];
     Type *AgTy = cast<PointerType>(PtrArg->getType())->getElementType();
 
+    // Replace sret attribute with noalias. This reduces register pressure by
+    // avoiding a register copy.
+    if (PtrArg->hasStructRetAttr()) {
+      unsigned ArgNo = PtrArg->getArgNo();
+      F->setAttributes(
+          F->getAttributes()
+              .removeAttribute(F->getContext(), ArgNo + 1, Attribute::StructRet)
+              .addAttribute(F->getContext(), ArgNo + 1, Attribute::NoAlias));
+      for (Use &U : F->uses()) {
+        CallSite CS(U.getUser());
+        CS.setAttributes(
+            CS.getAttributes()
+                .removeAttribute(F->getContext(), ArgNo + 1,
+                                 Attribute::StructRet)
+                .addAttribute(F->getContext(), ArgNo + 1, Attribute::NoAlias));
+      }
+    }
+
     // If this is a byval argument, and if the aggregate type is small, just
     // pass the elements, which is always safe, if the passed value is densely
     // packed or if we can prove the padding bytes are never accessed. This does
Index: llvm/trunk/test/Transforms/ArgumentPromotion/sret.ll
===================================================================
--- llvm/trunk/test/Transforms/ArgumentPromotion/sret.ll
+++ llvm/trunk/test/Transforms/ArgumentPromotion/sret.ll
@@ -0,0 +1,28 @@
+; RUN: opt < %s -argpromotion -S | FileCheck %s
+
+target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-windows-msvc"
+
+; CHECK: define internal void @add(i32 %[[THIS1:.*]], i32 %[[THIS2:.*]], i32* noalias %[[SR:.*]])
+define internal void @add({i32, i32}* %this, i32* sret %r) {
+  %ap = getelementptr {i32, i32}, {i32, i32}* %this, i32 0, i32 0
+  %bp = getelementptr {i32, i32}, {i32, i32}* %this, i32 0, i32 1
+  %a = load i32, i32* %ap
+  %b = load i32, i32* %bp
+  ; CHECK: %[[AB:.*]] = add i32 %[[THIS1]], %[[THIS2]]
+  %ab = add i32 %a, %b
+  ; CHECK: store i32 %[[AB]], i32* %[[SR]]
+  store i32 %ab, i32* %r
+  ret void
+}
+
+; CHECK: define void @f()
+define void @f() {
+  ; CHECK: %[[R:.*]] = alloca i32
+  %r = alloca i32
+  %pair = alloca {i32, i32}
+
+  ; CHECK: call void @add(i32 %{{.*}}, i32 %{{.*}}, i32* noalias %[[R]])
+  call void @add({i32, i32}* %pair, i32* sret %r)
+  ret void
+}