[llvm] bb9580a - [SCEV] Use ashr to adjust constant multipliers (#135534)

[via llvm-commits]

Author: Yingwei Zheng
Date: 2025-04-13T20:22:48+08:00
New Revision: bb9580a02b393683ff0b6c360df684f33c715a1f

URL: https://github.com/llvm/llvm-project/commit/bb9580a02b393683ff0b6c360df684f33c715a1f
DIFF: https://github.com/llvm/llvm-project/commit/bb9580a02b393683ff0b6c360df684f33c715a1f.diff

LOG: [SCEV] Use ashr to adjust constant multipliers (#135534)

SCEV converts "-2 *nsw (i32 V)" into "2148473647 *nsw (i32 V)". But we
cannot preserve the nsw flag when the constant multiplier is negative.
This patch changes lshr to ashr so that we can preserve both nsw and nuw
flags.

Alive2 proof: https://alive2.llvm.org/ce/z/LZVSEa
Closes https://github.com/llvm/llvm-project/issues/135531.

Added: 
    llvm/test/Analysis/ScalarEvolution/pr135531.ll

Modified: 
    llvm/lib/Analysis/ScalarEvolution.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index c62ea1526981d..d193c9e3210ea 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -7841,7 +7841,7 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
               unsigned GCD = std::min(MulZeros, TZ);
               APInt DivAmt = APInt::getOneBitSet(BitWidth, TZ - GCD);
               SmallVector<const SCEV*, 4> MulOps;
-              MulOps.push_back(getConstant(OpC->getAPInt().lshr(GCD)));
+              MulOps.push_back(getConstant(OpC->getAPInt().ashr(GCD)));
               append_range(MulOps, LHSMul->operands().drop_front());
               auto *NewMul = getMulExpr(MulOps, LHSMul->getNoWrapFlags());
               ShiftedLHS = getUDivExpr(NewMul, getConstant(DivAmt));

diff  --git a/llvm/test/Analysis/ScalarEvolution/pr135531.ll b/llvm/test/Analysis/ScalarEvolution/pr135531.ll
new file mode 100644
index 0000000000000..e172d56d3a515
--- /dev/null
+++ b/llvm/test/Analysis/ScalarEvolution/pr135531.ll
@@ -0,0 +1,19 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -disable-output -passes='print<scalar-evolution>' < %s 2>&1 | FileCheck %s
+
+define i32 @pr135511(i32 %x) {
+; CHECK-LABEL: 'pr135511'
+; CHECK-NEXT:  Classifying expressions for: @pr135511
+; CHECK-NEXT:    %and = and i32 %x, 16382
+; CHECK-NEXT:    --> (2 * (zext i13 (trunc i32 (%x /u 2) to i13) to i32))<nuw><nsw> U: [0,16383) S: [0,16383)
+; CHECK-NEXT:    %neg = sub nsw i32 0, %and
+; CHECK-NEXT:    --> (-2 * (zext i13 (trunc i32 (%x /u 2) to i13) to i32))<nsw> U: [0,-1) S: [-16382,1)
+; CHECK-NEXT:    %res = and i32 %neg, 268431360
+; CHECK-NEXT:    --> (4096 * (zext i16 (trunc i32 ((-1 * (zext i13 (trunc i32 (%x /u 2) to i13) to i32))<nsw> /u 2048) to i16) to i32))<nuw><nsw> U: [0,268431361) S: [0,268431361)
+; CHECK-NEXT:  Determining loop execution counts for: @pr135511
+;
+  %and = and i32 %x, 16382
+  %neg = sub nsw i32 0, %and
+  %res = and i32 %neg, 268431360
+  ret i32 %res
+}