[InstSimplify] Precommit test for PR71528

Author: huntergr-arm

llvm/test/Transforms/InstSimplify/po2-shift-add-and-to-zero.ll

@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -passes=instcombine -S < %s | FileCheck %s
+
+;; The and X, (add Y, -1) pattern is from an earlier instcombine pass which
+;; converted
+
+;; define i64 @f1() #0 {
+;; entry:
+;;   %0 = call i64 @llvm.aarch64.sve.cntb(i32 31)
+;;   %1 = call i64 @llvm.aarch64.sve.cnth(i32 31)
+;;   %rem = urem i64 %0, %1
+;;   ret i64 %rem
+;; }
+
+;; into
+
+;; define i64 @f1() #0 {
+;; entry:
+;;   %0 = call i64 @llvm.vscale.i64()
+;;   %1 = shl nuw nsw i64 %0, 4
+;;   %2 = call i64 @llvm.vscale.i64()
+;;   %3 = shl nuw nsw i64 %2, 3
+;;   %4 = add nsw i64 %3, -1
+;;   %rem = and i64 %1, %4
+;;   ret i64 %rem
+;; }
+
+;; InstCombine would have folded the original to returning 0 if the vscale
+;; calls were the same Value*, but since there's two of them it doesn't
+;; work and we convert the urem to add/and. CSE then gets rid of the extra
+;; vscale, leaving us with a new pattern to match. This only works because
+;; vscale is known to be a nonzero power of 2 (assuming there's a defined
+;; range for it).
+
+define i64 @f1() #0 {
+; CHECK-LABEL: define i64 @f1
+; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 4
+; CHECK-NEXT:    [[TMP2:%.*]] = shl nuw nsw i64 [[TMP0]], 3
+; CHECK-NEXT:    [[TMP3:%.*]] = add nsw i64 [[TMP2]], -1
+; CHECK-NEXT:    [[REM:%.*]] = and i64 [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    ret i64 [[REM]]
+;
+entry:
+  %0 = call i64 @llvm.vscale.i64()
+  %1 = shl nuw nsw i64 %0, 4
+  %2 = shl nuw nsw i64 %0, 3
+  %3 = add nsw i64 %2, -1
+  %rem = and i64 %1, %3
+  ret i64 %rem
+}
+
+declare i64 @llvm.vscale.i64()
+
+attributes #0 = { vscale_range(1,16) }