Implement "superhero" strength reduction, or full strength

reduction of address calculations down to basic pointer arithmetic.
This is currently off by default, as it needs a few other features
before it becomes generally useful. And even when enabled, full
strength reduction is only performed when it doesn't increase
register pressure, and when several other conditions are true.

This also factors out a bunch of exisiting LSR code out of
StrengthReduceStridedIVUsers into separate functions, and tidies
up IV insertion. This actually decreases register pressure even
in non-superhero mode. The change in iv-users-in-other-loops.ll
is an example of this; there are two more adds because there are
two fewer leas, and there is less spilling.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@65108 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 33 insertions, 0 deletions

diff --git a/test/CodeGen/X86/full-lsr.ll b/test/CodeGen/X86/full-lsr.ll
new file mode 100644
index 0000000000..ee9eaf95c8
--- /dev/null
+++ b/test/CodeGen/X86/full-lsr.ll
@@ -0,0 +1,33 @@
+; RUN: llvm-as < %s | llc -march=x86 -enable-full-lsr >%t
+; RUN: grep {addl	\\\$4,} %t | count 3
+; RUN: not grep {,%} %t
+
+define void @foo(float* nocapture %A, float* nocapture %B, float* nocapture %C, i32 %N) nounwind {
+entry:
+	%0 = icmp sgt i32 %N, 0		; <i1> [#uses=1]
+	br i1 %0, label %bb, label %return
+
+bb:		; preds = %bb, %entry
+	%i.03 = phi i32 [ 0, %entry ], [ %indvar.next, %bb ]		; <i32> [#uses=5]
+	%1 = getelementptr float* %A, i32 %i.03		; <float*> [#uses=1]
+	%2 = load float* %1, align 4		; <float> [#uses=1]
+	%3 = getelementptr float* %B, i32 %i.03		; <float*> [#uses=1]
+	%4 = load float* %3, align 4		; <float> [#uses=1]
+	%5 = add float %2, %4		; <float> [#uses=1]
+	%6 = getelementptr float* %C, i32 %i.03		; <float*> [#uses=1]
+	store float %5, float* %6, align 4
+	%7 = add i32 %i.03, 10		; <i32> [#uses=3]
+	%8 = getelementptr float* %A, i32 %7		; <float*> [#uses=1]
+	%9 = load float* %8, align 4		; <float> [#uses=1]
+	%10 = getelementptr float* %B, i32 %7		; <float*> [#uses=1]
+	%11 = load float* %10, align 4		; <float> [#uses=1]
+	%12 = add float %9, %11		; <float> [#uses=1]
+	%13 = getelementptr float* %C, i32 %7		; <float*> [#uses=1]
+	store float %12, float* %13, align 4
+	%indvar.next = add i32 %i.03, 1		; <i32> [#uses=2]
+	%exitcond = icmp eq i32 %indvar.next, %N		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb
+
+return:		; preds = %bb, %entry
+	ret void
+}