[llvm-branch-commits] [llvm] release/19.x: [SCEV] Fix sext handling for `getConstantMultiple` (#117093) (PR #117136)

[via llvm-branch-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: None (llvmbot)

<details>
<summary>Changes</summary>

Backport 458dfbd855806461b4508bf8845cafe0411dbfd4

Requested by: @<!-- -->dtcxzyw

---
Full diff: https://github.com/llvm/llvm-project/pull/117136.diff


3 Files Affected:

- (modified) llvm/lib/Analysis/ScalarEvolution.cpp (+3-1) 
- (added) llvm/test/Analysis/ScalarEvolution/pr116483.ll (+26) 
- (added) llvm/test/Transforms/IndVarSimplify/pr116483.ll (+36) 


``````````diff
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 51cffac8087689..412cfe73d3e559 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -6313,8 +6313,10 @@ APInt ScalarEvolution::getConstantMultipleImpl(const SCEV *S) {
     return getConstantMultiple(Z->getOperand()).zext(BitWidth);
   }
   case scSignExtend: {
+    // Only multiples that are a power of 2 will hold after sext.
     const SCEVSignExtendExpr *E = cast<SCEVSignExtendExpr>(S);
-    return getConstantMultiple(E->getOperand()).sext(BitWidth);
+    uint32_t TZ = getMinTrailingZeros(E->getOperand());
+    return GetShiftedByZeros(TZ);
   }
   case scMulExpr: {
     const SCEVMulExpr *M = cast<SCEVMulExpr>(S);
diff --git a/llvm/test/Analysis/ScalarEvolution/pr116483.ll b/llvm/test/Analysis/ScalarEvolution/pr116483.ll
new file mode 100644
index 00000000000000..cc2334e9c64f92
--- /dev/null
+++ b/llvm/test/Analysis/ScalarEvolution/pr116483.ll
@@ -0,0 +1,26 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -disable-output "-passes=print<scalar-evolution>" < %s 2>&1 | FileCheck %s
+
+define i16 @test() {
+; CHECK-LABEL: 'test'
+; CHECK-NEXT:  Classifying expressions for: @test
+; CHECK-NEXT:    %xor = xor i32 0, 3
+; CHECK-NEXT:    --> %xor U: [3,4) S: [3,4)
+; CHECK-NEXT:    %mul = mul i32 %xor, 329
+; CHECK-NEXT:    --> (329 * %xor)<nuw><nsw> U: [987,988) S: [987,988)
+; CHECK-NEXT:    %conv = trunc i32 %mul to i16
+; CHECK-NEXT:    --> (329 * (trunc i32 %xor to i16))<nuw><nsw> U: [987,988) S: [987,988)
+; CHECK-NEXT:    %sext = shl i16 %conv, 8
+; CHECK-NEXT:    --> (18688 * (trunc i32 %xor to i16))<nuw> U: [-9472,-9471) S: [-9472,-9471)
+; CHECK-NEXT:    %conv1 = ashr i16 %sext, 8
+; CHECK-NEXT:    --> (sext i8 (73 * (trunc i32 %xor to i8))<nuw> to i16) U: [-37,-36) S: [-37,-36)
+; CHECK-NEXT:  Determining loop execution counts for: @test
+;
+entry:
+  %xor = xor i32 0, 3
+  %mul = mul i32 %xor, 329
+  %conv = trunc i32 %mul to i16
+  %sext = shl i16 %conv, 8
+  %conv1 = ashr i16 %sext, 8
+  ret i16 %conv1
+}
diff --git a/llvm/test/Transforms/IndVarSimplify/pr116483.ll b/llvm/test/Transforms/IndVarSimplify/pr116483.ll
new file mode 100644
index 00000000000000..ae108a525223e0
--- /dev/null
+++ b/llvm/test/Transforms/IndVarSimplify/pr116483.ll
@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -passes=indvars < %s | FileCheck %s
+
+define i32 @test() {
+; CHECK-LABEL: define i32 @test() {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[XOR:%.*]] = xor i32 0, 3
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[XOR]], 329
+; CHECK-NEXT:    [[CONV:%.*]] = trunc i32 [[MUL]] to i16
+; CHECK-NEXT:    [[SEXT:%.*]] = shl i16 [[CONV]], 8
+; CHECK-NEXT:    [[CONV1:%.*]] = ashr i16 [[SEXT]], 8
+; CHECK-NEXT:    br label %[[LOOP_BODY:.*]]
+; CHECK:       [[LOOP_BODY]]:
+; CHECK-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[LOOP_BODY]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[CONV3:%.*]] = zext i16 [[CONV1]] to i32
+; CHECK-NEXT:    ret i32 [[CONV3]]
+;
+entry:
+  %xor = xor i32 0, 3
+  %mul = mul i32 %xor, 329
+  %conv = trunc i32 %mul to i16
+  %sext = shl i16 %conv, 8
+  %conv1 = ashr i16 %sext, 8
+  %conv3 = zext i16 %conv1 to i32
+  br label %loop.body
+
+loop.body:
+  %indvar = phi i32 [ %indvar.inc, %loop.body ], [ 1, %entry ]
+  %indvar.inc = add nuw i32 %indvar, 1
+  %exitcond = icmp eq i32 %indvar, %conv3
+  br i1 %exitcond, label %exit, label %loop.body
+
+exit:
+  ret i32 %conv3
+}

``````````

</details>


https://github.com/llvm/llvm-project/pull/117136