[LAA] LLE 1/6: Expose Forward dependences
Summary:
Before this change, we didn't use to collect forward dependences since
none of the current clients (LV, LDist) required them.
The motivation to also collect forward dependences is a new pass
LoopLoadElimination (LLE) which discovers store-to-load forwarding
opportunities across the loop's backedge. The pass uses both lexically
forward or backward loop-carried dependences to detect these
opportunities.
The new pass also analyzes loop-independent (forward) dependences since
they can conflict with the loop-carried dependences in terms of how the
data flows through memory.
The newly added test only covers loop-carried forward dependences
because loop-independent ones are currently categorized as NoDep. The
next patch will fix this.
The two patches were tested together for compile-time regression. None
found in LNT/SPEC.
Note that with this change LAA provides all dependences rather than just
"interesting" ones. A subsequent NFC patch will remove the now trivial
isInterestingDependence and rename the APIs.
Reviewers: hfinkel
Subscribers: jmolloy, rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D13254
llvm-svn: 251972
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/forward-loop-carried.ll b/llvm/test/Analysis/LoopAccessAnalysis/forward-loop-carried.ll
new file mode 100644
index 0000000..138762c
--- /dev/null
+++ b/llvm/test/Analysis/LoopAccessAnalysis/forward-loop-carried.ll
@@ -0,0 +1,44 @@
+; RUN: opt -loop-accesses -analyze < %s | FileCheck %s
+
+; for (unsigned i = 0; i < 100; i++) {
+; A[i+8] = B[i] + 2;
+; C[i] = A[i] * 2;
+; }
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @f(i32* %A, i32* %B, i32* %C, i64 %N) {
+
+; CHECK: Interesting Dependences:
+; CHECK-NEXT: Forward:
+; CHECK-NEXT: store i32 %a_p1, i32* %Aidx_ahead, align 4 ->
+; CHECK-NEXT: %a = load i32, i32* %Aidx, align 4
+
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+ %idx = add nuw nsw i64 %indvars.iv, 8
+
+ %Aidx_ahead = getelementptr inbounds i32, i32* %A, i64 %idx
+ %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
+ %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
+ %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+
+ %b = load i32, i32* %Bidx, align 4
+ %a_p1 = add i32 %b, 2
+ store i32 %a_p1, i32* %Aidx_ahead, align 4
+
+ %a = load i32, i32* %Aidx, align 4
+ %c = mul i32 %a, 2
+ store i32 %c, i32* %Cidx, align 4
+
+ %exitcond = icmp eq i64 %indvars.iv.next, %N
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+}