When inlining a function and adding its inner call sites to the

candidate set for subsequent inlining, try to simplify the arguments to
the inner call site now that inlining has been performed.

The goal here is to propagate and fold constants through deeply nested
call chains. Without doing this, we loose the inliner bonus that should
be applied because the arguments don't match the exact pattern the cost
estimator uses.

Reviewed on IRC by Benjamin Kramer.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152556 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 75 insertions, 0 deletions

diff --git a/test/Transforms/Inline/inline_constprop.ll b/test/Transforms/Inline/inline_constprop.ll
index 18edf15ab4..cc7aaac2b3 100644
--- a/test/Transforms/Inline/inline_constprop.ll
+++ b/test/Transforms/Inline/inline_constprop.ll
@@ -12,3 +12,78 @@ define i32 @caller1() {
   %X = call i32 @callee1( i32 10, i32 3 )
   ret i32 %X
 }
+
+define i32 @caller2() {
+; CHECK: @caller2
+; CHECK-NOT: call void @callee2
+; CHECK: ret
+
+; We contrive to make this hard for *just* the inline pass to do in order to
+; simulate what can actually happen with large, complex functions getting
+; inlined.
+  %a = add i32 42, 0
+  %b = add i32 48, 0
+
+  %x = call i32 @callee21(i32 %a, i32 %b)
+  ret i32 %x
+}
+
+define i32 @callee21(i32 %x, i32 %y) {
+  %sub = sub i32 %y, %x
+  %result = call i32 @callee22(i32 %sub)
+  ret i32 %result
+}
+
+declare i8* @getptr()
+
+define i32 @callee22(i32 %x) {
+  %icmp = icmp ugt i32 %x, 42
+  br i1 %icmp, label %bb.true, label %bb.false
+bb.true:
+  ; This block musn't be counted in the inline cost.
+  %ptr = call i8* @getptr()
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+  load volatile i8* %ptr
+
+  ret i32 %x
+bb.false:
+  ret i32 %x
+}