ArgumentPromotion: Drop sret attribute on functions that are only called directly.

If the first argument to a function is a 'this' argument and the second
has the sret attribute, the ArgumentPromotion pass may promote the 'this'
argument to more than one argument, violating the IR constraint that 'sret'
may only be applied to the first or second argument.

Although this IR constraint is arguably unnecessary, it highlighted the fact
that ArgPromotion does not need to preserve this attribute. Dropping the
attribute reduces register pressure in the backend by avoiding the register
copy required by sret. Because sret implies noalias, we also replace the
former with the latter.

Differential Revision: http://reviews.llvm.org/D10353

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239488 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/IR/Function.cpp b/lib/IR/Function.cpp
index cf8e3ed571e3402ea816b767c1b1ff83ca25c74c..2b439bb46bf7b0cd5f116a79638cbe6d8ff515b7 100644 (file)
--- a/lib/IR/Function.cpp
+++ b/lib/IR/Function.cpp
@@ -154,10 +154,8 @@ bool Argument::hasNoCaptureAttr() const {
 /// 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

diff --git a/lib/Transforms/IPO/ArgumentPromotion.cpp b/lib/Transforms/IPO/ArgumentPromotion.cpp
index c7c57ab56444232764c03441d8cec30a0dec3ec1..440f3f20d61a509953fa1095c0da8fe06114b252 100644 (file)
--- a/lib/Transforms/IPO/ArgumentPromotion.cpp
+++ b/lib/Transforms/IPO/ArgumentPromotion.cpp
@@ -245,6 +245,24 @@ CallGraphNode *ArgPromotion::PromoteArguments(CallGraphNode *CGN) {
     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

diff --git a/test/Transforms/ArgumentPromotion/sret.ll b/test/Transforms/ArgumentPromotion/sret.ll
new file mode 100644 (file)
index 0000000..8e5521f
--- /dev/null
+++ b/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
+}