[llvm] 7d21d73 - [LAA] Add a test case to show incorrect dependency classification (NFC). (#70473)

[via llvm-commits]

Author: Alexandros Lamprineas
Date: 2023-10-31T15:01:28Z
New Revision: 7d21d7395ccc8613e5a4144a1b9735e5c719cda3

URL: https://github.com/llvm/llvm-project/commit/7d21d7395ccc8613e5a4144a1b9735e5c719cda3
DIFF: https://github.com/llvm/llvm-project/commit/7d21d7395ccc8613e5a4144a1b9735e5c719cda3.diff

LOG: [LAA] Add a test case to show incorrect dependency classification (NFC). (#70473)

Currently the loop access analysis classifies this loop as unsafe to
vectorize because the memory dependencies are
'ForwardButPreventsForwarding'. However, the access pattern is
'write-after-read' with no subsequent read accessing the written memory
locations. I can't see how store-to-load forwarding is applicable here.

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

Added: 
    llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll b/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll
new file mode 100644
index 000000000000000..89c1737fb730513
--- /dev/null
+++ b/llvm/test/Analysis/LoopAccessAnalysis/forward-negative-step.ll
@@ -0,0 +1,40 @@
+; RUN: opt -passes='print<access-info>' -disable-output  < %s 2>&1 | FileCheck %s
+
+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;
+; }
+
+; 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:     Dependences:
+; CHECK-NEXT:       ForwardButPreventsForwarding:
+; CHECK-NEXT:           %0 = load i32, ptr %arrayidx, align 4 ->
+; CHECK-NEXT:           store i32 %add, ptr %gep, align 4
+
+define void @vectorizable_Read_Write(ptr nocapture %A) {
+entry:
+  %invariant.gep = getelementptr i32, ptr %A, i64 1
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %indvars.iv = phi i64 [ 1022, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
+  %0 = load i32, ptr %arrayidx, align 4
+  %add = add nsw i32 %0, 1
+  %gep = getelementptr i32, ptr %invariant.gep, i64 %indvars.iv
+  store i32 %add, ptr %gep, align 4
+  %indvars.iv.next = add nsw i64 %indvars.iv, -1
+  %cmp.not = icmp eq i64 %indvars.iv, 0
+  br i1 %cmp.not, label %for.cond.cleanup, label %for.body
+}
+