Undo a previous restriction on the inline cost calculation which Nick

introduced. Specifically, there are cost reductions for all
constant-operand icmp instructions against an alloca, regardless of
whether the alloca will in fact be elligible for SROA. That means we
don't want to abort the icmp reduction computation when we abort the
SROA reduction computation. That in turn frees us from the need to keep
a separate worklist and defer the ICmp calculations.

Use this new-found freedom and some judicious function boundaries to
factor the innards of computing the cost factor of any given instruction
out of the loop over the instructions and into static helper functions.
This greatly simplifies the code, and hopefully makes it more clear what
is happening here.

Reviewed by Eric Christopher. There is some concern that we'd like to
ensure this doesn't get out of hand, and I plan to benchmark the effects
of this change over the next few days along with some further fixes to
the inline cost.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152368 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 41 insertions, 0 deletions

diff --git a/test/Transforms/Inline/alloca-bonus.ll b/test/Transforms/Inline/alloca-bonus.ll
index 91ab40ae16..fb4062f708 100644
--- a/test/Transforms/Inline/alloca-bonus.ll
+++ b/test/Transforms/Inline/alloca-bonus.ll
@@ -81,3 +81,44 @@ bb.true:
 bb.false:
   ret void
 }
+
+define void @outer4(i32 %A) {
+; CHECK: @outer4
+; CHECK-NOT: call void @inner4
+  %ptr = alloca i32
+  call void @inner4(i32* %ptr, i32 %A)
+  ret void
+}
+
+; %D poisons this call, scalar-repl can't handle that instruction. However, we
+; still want to detect that the icmp and branch *can* be handled.
+define void @inner4(i32 *%ptr, i32 %A) {
+  %B = getelementptr i32* %ptr, i32 %A
+  %E = icmp eq i32* %ptr, null
+  br i1 %E, label %bb.true, label %bb.false
+bb.true:
+  ; This block musn't be counted in the inline cost.
+  %t1 = load i32* %ptr
+  %t2 = add i32 %t1, 1
+  %t3 = add i32 %t2, 1
+  %t4 = add i32 %t3, 1
+  %t5 = add i32 %t4, 1
+  %t6 = add i32 %t5, 1
+  %t7 = add i32 %t6, 1
+  %t8 = add i32 %t7, 1
+  %t9 = add i32 %t8, 1
+  %t10 = add i32 %t9, 1
+  %t11 = add i32 %t10, 1
+  %t12 = add i32 %t11, 1
+  %t13 = add i32 %t12, 1
+  %t14 = add i32 %t13, 1
+  %t15 = add i32 %t14, 1
+  %t16 = add i32 %t15, 1
+  %t17 = add i32 %t16, 1
+  %t18 = add i32 %t17, 1
+  %t19 = add i32 %t18, 1
+  %t20 = add i32 %t19, 1
+  ret void
+bb.false:
+  ret void
+}