[SCEV] Add one more case in computeConstantDifference

This patch teaches `computeConstantDifference` handle calculation of constant
difference between `(X + C1)` and `(X + C2)` which is `(C2 - C1)`.

Differential Revision: https://reviews.llvm.org/D43759
Reviewed By: anna

llvm-svn: 328609

2 files changed, 107 insertions, 10 deletions

diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 004eac7f555..b44107d9a89 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -9449,17 +9449,25 @@ Optional<APInt> ScalarEvolution::computeConstantDifference(const SCEV *More,
     return M - L;
   }
 
-  const SCEV *L, *R;
   SCEV::NoWrapFlags Flags;
-  if (splitBinaryAdd(Less, L, R, Flags))
-    if (const auto *LC = dyn_cast<SCEVConstant>(L))
-      if (R == More)
-        return -(LC->getAPInt());
-
-  if (splitBinaryAdd(More, L, R, Flags))
-    if (const auto *LC = dyn_cast<SCEVConstant>(L))
-      if (R == Less)
-        return LC->getAPInt();
+  const SCEV *LLess = nullptr, *RLess = nullptr;
+  const SCEV *LMore = nullptr, *RMore = nullptr;
+  const SCEVConstant *C1 = nullptr, *C2 = nullptr;
+  // Compare (X + C1) vs X.
+  if (splitBinaryAdd(Less, LLess, RLess, Flags))
+    if ((C1 = dyn_cast<SCEVConstant>(LLess)))
+      if (RLess == More)
+        return -(C1->getAPInt());
+
+  // Compare X vs (X + C2).
+  if (splitBinaryAdd(More, LMore, RMore, Flags))
+    if ((C2 = dyn_cast<SCEVConstant>(LMore)))
+      if (RMore == Less)
+        return C2->getAPInt();
+
+  // Compare (X + C1) vs (X + C2).
+  if (C1 && C2 && RLess == RMore)
+    return C2->getAPInt() - C1->getAPInt();
 
   return None;
 }
diff --git a/llvm/test/Transforms/IndVarSimplify/promote-iv-to-eliminate-casts.ll b/llvm/test/Transforms/IndVarSimplify/promote-iv-to-eliminate-casts.ll
index 956999b7cde..5872e4e03a8 100644
--- a/llvm/test/Transforms/IndVarSimplify/promote-iv-to-eliminate-casts.ll
+++ b/llvm/test/Transforms/IndVarSimplify/promote-iv-to-eliminate-casts.ll
@@ -101,3 +101,92 @@ bb:             ; preds = %bb, %bb.thread
 return:         ; preds = %bb
   ret void
 }
+
+define void @promote_latch_condition_decrementing_loop_01(i32* %p, i32* %a) {
+
+; CHECK-LABEL: @promote_latch_condition_decrementing_loop_01(
+; CHECK-NOT:     trunc
+
+entry:
+  %len = load i32, i32* %p, align 4, !range !0
+  %len.minus.1 = add nsw i32 %len, -1
+  %zero_check = icmp eq i32 %len, 0
+  br i1 %zero_check, label %loopexit, label %preheader
+
+preheader:
+  br label %loop
+
+loopexit:
+  ret void
+
+loop:
+  %iv = phi i32 [ %iv.next, %loop ], [ %len.minus.1, %preheader ]
+  ; CHECK: %indvars.iv = phi i64
+  %iv.wide = zext i32 %iv to i64
+  %el = getelementptr inbounds i32, i32* %a, i64 %iv.wide
+  store atomic i32 0, i32* %el unordered, align 4
+  %iv.next = add nsw i32 %iv, -1
+  ; CHECK: %loopcond = icmp slt i64 %indvars.iv, 1
+  %loopcond = icmp slt i32 %iv, 1
+  br i1 %loopcond, label %loopexit, label %loop
+}
+
+define void @promote_latch_condition_decrementing_loop_02(i32* %p, i32* %a) {
+
+; CHECK-LABEL: @promote_latch_condition_decrementing_loop_02(
+; CHECK-NOT:     trunc
+
+entry:
+  %len = load i32, i32* %p, align 4, !range !0
+  %zero_check = icmp eq i32 %len, 0
+  br i1 %zero_check, label %loopexit, label %preheader
+
+preheader:
+  br label %loop
+
+loopexit:
+  ret void
+
+loop:
+  %iv = phi i32 [ %iv.next, %loop ], [ %len, %preheader ]
+  ; CHECK: %indvars.iv = phi i64
+  %iv.wide = zext i32 %iv to i64
+  %el = getelementptr inbounds i32, i32* %a, i64 %iv.wide
+  store atomic i32 0, i32* %el unordered, align 4
+  %iv.next = add nsw i32 %iv, -1
+  ; CHECK: %loopcond = icmp slt i64 %indvars.iv, 1
+  %loopcond = icmp slt i32 %iv, 1
+  br i1 %loopcond, label %loopexit, label %loop
+}
+
+define void @promote_latch_condition_decrementing_loop_03(i32* %p, i32* %a) {
+
+; CHECK-LABEL: @promote_latch_condition_decrementing_loop_03(
+; CHECK-NOT:     trunc
+
+entry:
+  %len = load i32, i32* %p, align 4, !range !0
+  %len.plus.1 = add i32 %len, 1
+  %zero_check = icmp eq i32 %len, 0
+  br i1 %zero_check, label %loopexit, label %preheader
+
+preheader:
+  br label %loop
+
+loopexit:
+  ret void
+
+loop:
+  %iv = phi i32 [ %iv.next, %loop ], [ %len.plus.1, %preheader ]
+  ; CHECK: %indvars.iv = phi i64
+  %iv.wide = zext i32 %iv to i64
+  %el = getelementptr inbounds i32, i32* %a, i64 %iv.wide
+  store atomic i32 0, i32* %el unordered, align 4
+  %iv.next = add nsw i32 %iv, -1
+  ; CHECK: %loopcond = icmp slt i64 %indvars.iv, 1
+  %loopcond = icmp slt i32 %iv, 1
+  br i1 %loopcond, label %loopexit, label %loop
+}
+
+
+!0 = !{i32 0, i32 2147483647}