[LAA] Add extra test for #70819 showing incorrect Forward dep.

Add an additional test case where we currently incorrectly identify a
dependence as Foward instead of ForwardButPreventsForwarding.

Also cleans up the names in the tests a bit to improve readability.

Author: fhahn

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

@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 4
 ; 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"
@@ -9,32 +10,76 @@ target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 ;    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) {
+; CHECK-LABEL: 'vectorizable_Read_Write'
+; CHECK-NEXT:    loop:
+; CHECK-NEXT:      Report: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop
+; CHECK-NEXT:  Forward loop carried data dependence that prevents store-to-load forwarding.
+; CHECK-NEXT:      Dependences:
+; CHECK-NEXT:        ForwardButPreventsForwarding:
+; CHECK-NEXT:            %l = load i32, ptr %gep.A, align 4 ->
+; CHECK-NEXT:            store i32 %add, ptr %gep.A.plus.1, align 4
+; CHECK-EMPTY:
+; CHECK-NEXT:      Run-time memory checks:
+; CHECK-NEXT:      Grouped accesses:
+; CHECK-EMPTY:
+; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
+; CHECK-NEXT:      SCEV assumptions:
+; CHECK-EMPTY:
+; CHECK-NEXT:      Expressions re-written:
+;
 entry:
-  %invariant.gep = getelementptr i32, ptr %A, i64 1
-  br label %for.body
+  %A.plus.1 = getelementptr i32, ptr %A, i64 1
+  br label %loop
 
-for.cond.cleanup:
-  ret void
+loop:
+  %iv = phi i64 [ 1022, %entry ], [ %iv.next, %loop ]
+  %gep.A = getelementptr inbounds i32, ptr %A, i64 %iv
+  %l = load i32, ptr %gep.A, align 4
+  %add = add nsw i32 %l, 1
+  %gep.A.plus.1 = getelementptr i32, ptr %A.plus.1, i64 %iv
+  store i32 %add, ptr %gep.A.plus.1, align 4
+  %iv.next = add nsw i64 %iv, -1
+  %cmp.not = icmp eq i64 %iv, 0
+  br i1 %cmp.not, label %exit, label %loop
 
-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
+exit:
+  ret void
 }
 
+; FIXME: There's a forward dependency that prevents forwarding here.
+define void @neg_step_ForwardButPreventsForwarding(ptr nocapture %A, ptr noalias %B) {
+; CHECK-LABEL: 'neg_step_ForwardButPreventsForwarding'
+; CHECK-NEXT:    loop:
+; CHECK-NEXT:      Memory dependences are safe
+; CHECK-NEXT:      Dependences:
+; CHECK-NEXT:        Forward:
+; CHECK-NEXT:            store i32 0, ptr %gep.A, align 4 ->
+; CHECK-NEXT:            %l = load i32, ptr %gep.A.plus.1, align 4
+; CHECK-EMPTY:
+; CHECK-NEXT:      Run-time memory checks:
+; CHECK-NEXT:      Grouped accesses:
+; CHECK-EMPTY:
+; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
+; CHECK-NEXT:      SCEV assumptions:
+; CHECK-EMPTY:
+; CHECK-NEXT:      Expressions re-written:
+;
+entry:
+  %A.plus.1 = getelementptr i32, ptr %A, i64 1
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 1022, %entry ], [ %iv.next, %loop ]
+  %gep.A = getelementptr inbounds i32, ptr %A, i64 %iv
+  store i32 0, ptr %gep.A, align 4
+  %gep.A.plus.1 = getelementptr i32, ptr %A.plus.1, i64 %iv
+  %l = load i32, ptr %gep.A.plus.1, align 4
+  store i32 %l, ptr %B
+  %iv.next = add nsw i64 %iv, -1
+  %cmp.not = icmp eq i64 %iv, 0
+  br i1 %cmp.not, label %exit, label %loop
+
+exit:
+  ret void
+}