[llvm] 421a8c5 - [InstCombine] Add phase ordering test for #88239. NFC

[Craig Topper via llvm-commits]

Author: Craig Topper
Date: 2024-04-17T10:40:25-07:00
New Revision: 421a8c5892b7e59f27b2c21452f81fa789a758fd

URL: https://github.com/llvm/llvm-project/commit/421a8c5892b7e59f27b2c21452f81fa789a758fd
DIFF: https://github.com/llvm/llvm-project/commit/421a8c5892b7e59f27b2c21452f81fa789a758fd.diff

LOG: [InstCombine] Add phase ordering test for #88239. NFC

Added: 
    llvm/test/Transforms/PhaseOrdering/X86/pr88239.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/PhaseOrdering/X86/pr88239.ll b/llvm/test/Transforms/PhaseOrdering/X86/pr88239.ll
new file mode 100644
index 00000000000000..3afa1904fb249a
--- /dev/null
+++ b/llvm/test/Transforms/PhaseOrdering/X86/pr88239.ll
@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -passes="default<O3>" -mcpu=skx -S | FileCheck %s
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @foo(ptr noalias noundef %0, ptr noalias noundef %1) optsize {
+; CHECK-LABEL: define void @foo(
+; CHECK-SAME: ptr noalias nocapture noundef readonly [[TMP0:%.*]], ptr noalias nocapture noundef writeonly [[TMP1:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  vector.ph:
+; CHECK-NEXT:    br label [[TMP4:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[TMP2:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[TMP4]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <8 x i64> [ <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>, [[TMP2]] ], [ [[VEC_IND_NEXT:%.*]], [[TMP4]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = and <8 x i64> [[VEC_IND]], <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
+; CHECK-NEXT:    [[TMP3:%.*]] = xor <8 x i64> [[TMP6]], <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP0]], <8 x i64> [[TMP3]]
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = tail call <8 x i32> @llvm.masked.gather.v8i32.v8p0(<8 x ptr> [[TMP7]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> poison)
+; CHECK-NEXT:    [[TMP5:%.*]] = add nsw <8 x i32> [[WIDE_MASKED_GATHER]], <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store <8 x i32> [[TMP5]], ptr [[TMP10]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw i64 [[INDVARS_IV]], 8
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <8 x i64> [[VEC_IND]], <i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8>
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 256
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[MIDDLE_BLOCK:%.*]], label [[TMP4]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    ret void
+;
+  br label %3
+
+3:                                                ; preds = %7, %2
+  %4 = phi i32 [ 0, %2 ], [ %15, %7 ]
+  %5 = icmp slt i32 %4, 256
+  br i1 %5, label %7, label %6
+
+6:                                                ; preds = %3
+  ret void
+
+7:                                                ; preds = %3
+  %8 = sub nsw i32 255, %4
+  %9 = zext nneg i32 %8 to i64
+  %10 = getelementptr inbounds i32, ptr %0, i64 %9
+  %11 = load i32, ptr %10, align 4
+  %12 = add nsw i32 %11, 5
+  %13 = sext i32 %4 to i64
+  %14 = getelementptr inbounds i32, ptr %1, i64 %13
+  store i32 %12, ptr %14, align 4
+  %15 = add nsw i32 %4, 1
+  br label %3
+}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+;.