[llvm] [LAA] Fix incorrect dependency classification. (PR #70819)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-analysis

Author: Alexandros Lamprineas (labrinea)

<details>
<summary>Changes</summary>

As shown in #<!-- -->70473, the following loop was not considered safe to vectorize. When determining the memory access dependencies in a loop which has negative iteration step, we invert the source and sink of the dependence. Perhaps we should just invert the operands to getMinusSCEV(). This way the dependency is not regarded to be true.

void vectorizable_Read_Write(int *A) {
  for (unsigned i = 1022; i >= 0; i--)
    A[i+1] = A[i] + 1;
}

---
Full diff: https://github.com/llvm/llvm-project/pull/70819.diff


2 Files Affected:

- (modified) llvm/lib/Analysis/LoopAccessAnalysis.cpp (+2-10) 
- (modified) llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll (+2-5) 


``````````diff
diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index 3d1edd5f038a25e..7ab2959c4d88a34 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -1885,17 +1885,9 @@ MemoryDepChecker::isDependent(const MemAccessInfo &A, unsigned AIdx,
 
   // If the induction step is negative we have to invert source and sink of the
   // dependence.
-  if (StrideAPtr < 0) {
-    std::swap(APtr, BPtr);
-    std::swap(ATy, BTy);
-    std::swap(Src, Sink);
-    std::swap(AIsWrite, BIsWrite);
-    std::swap(AIdx, BIdx);
-    std::swap(StrideAPtr, StrideBPtr);
-  }
-
   ScalarEvolution &SE = *PSE.getSE();
-  const SCEV *Dist = SE.getMinusSCEV(Sink, Src);
+  const SCEV *Dist = StrideAPtr < 0 ? SE.getMinusSCEV(Src, Sink) :
+                                      SE.getMinusSCEV(Sink, Src);
 
   LLVM_DEBUG(dbgs() << "LAA: Src Scev: " << *Src << "Sink Scev: " << *Sink
                     << "(Induction step: " << StrideAPtr << ")\n");
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll b/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll
index 89c1737fb730513..683c44be6da87fc 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll
@@ -2,8 +2,6 @@
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
-; FIXME: This should be vectorizable
-
 ; void vectorizable_Read_Write(int *A) {
 ;  for (unsigned i = 1022; i >= 0; i--)
 ;    A[i+1] = A[i] + 1;
@@ -11,10 +9,9 @@ target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
 ; CHECK: function 'vectorizable_Read_Write':
 ; CHECK-NEXT:   for.body:
-; CHECK-NEXT:     Report: unsafe dependent memory operations in loop
-; CHECK-NEXT:     Forward loop carried data dependence that prevents store-to-load forwarding.
+; CHECK-NEXT:     Memory dependences are safe
 ; CHECK-NEXT:     Dependences:
-; CHECK-NEXT:       ForwardButPreventsForwarding:
+; CHECK-NEXT:       Forward:
 ; CHECK-NEXT:           %0 = load i32, ptr %arrayidx, align 4 ->
 ; CHECK-NEXT:           store i32 %add, ptr %gep, align 4
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/70819