From a64dc93ab3948291a96c338c58f33b2f3e4f36dd Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@intel.com>
Date: Mon, 25 Nov 2019 14:49:21 -0800
Subject: [PATCH] [X86] Add test case for pr44140. NFC

---
 llvm/test/CodeGen/X86/pr44140.ll | 98 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 98 insertions(+)
 create mode 100644 llvm/test/CodeGen/X86/pr44140.ll

diff --git a/llvm/test/CodeGen/X86/pr44140.ll b/llvm/test/CodeGen/X86/pr44140.ll
new file mode 100644
index 0000000..9916252e
--- /dev/null
+++ b/llvm/test/CodeGen/X86/pr44140.ll
@@ -0,0 +1,98 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=znver1 | FileCheck %s
+
+define win64cc void @opaque() {
+; CHECK-LABEL: opaque:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    retq
+  ret void
+}
+
+; We need xmm6 to be live from the loop header across all iterations of the loop.
+; We shouldn't clobber ymm6 inside the loop.
+; FIXME: We currently clobber ymm6
+define i32 @main() {
+; CHECK-LABEL: main:
+; CHECK:       # %bb.0: # %start
+; CHECK-NEXT:    subq $584, %rsp # imm = 0x248
+; CHECK-NEXT:    .cfi_def_cfa_offset 592
+; CHECK-NEXT:    vmovaps {{.*#+}} xmm6 = [1010101010101010101,2020202020202020202]
+; CHECK-NEXT:    xorl %esi, %esi
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB1_1: # %fake-loop
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm0
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm1
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm6
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm2
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm3
+; CHECK-NEXT:    vmovups %ymm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm1, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm1
+; CHECK-NEXT:    vmovups %ymm3, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm2, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm6, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm3, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm2, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm6, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm1, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm1, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm5
+; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm4
+; CHECK-NEXT:    vmovups %ymm5, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovups %ymm4, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    callq opaque
+; CHECK-NEXT:    vmovaps %xmm6, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    testb %sil, %sil
+; CHECK-NEXT:    jne .LBB1_1
+; CHECK-NEXT:  # %bb.2: # %exit
+; CHECK-NEXT:    movabsq $1010101010101010101, %rcx # imm = 0xE04998456557EB5
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    cmpq %rcx, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    sete %al
+; CHECK-NEXT:    decl %eax
+; CHECK-NEXT:    addq $584, %rsp # imm = 0x248
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
+start:
+  %dummy0 = alloca [22 x i64], align 8
+  %dummy1 = alloca [22 x i64], align 8
+  %dummy2 = alloca [22 x i64], align 8
+
+  %data = alloca <2 x i64>, align 8
+
+  br label %fake-loop
+
+fake-loop:                                        ; preds = %fake-loop, %start
+  %dummy0.cast = bitcast [22 x i64]* %dummy0 to i8*
+  %dummy1.cast = bitcast [22 x i64]* %dummy1 to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 %dummy1.cast, i8* nonnull align 8 %dummy0.cast, i64 176, i1 false)
+
+  %dummy1.cast.copy = bitcast [22 x i64]* %dummy1 to i8*
+  %dummy2.cast = bitcast [22 x i64]* %dummy2 to i8*
+  call void @llvm.lifetime.start.p0i8(i64 176, i8* nonnull %dummy2.cast)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 %dummy2.cast, i8* nonnull align 8 %dummy1.cast.copy, i64 176, i1 false)
+
+  call win64cc void @opaque()
+
+  store <2 x i64> <i64 1010101010101010101, i64 2020202020202020202>, <2 x i64>* %data, align 8
+
+  %opaque-false = icmp eq i8 0, 1
+  br i1 %opaque-false, label %fake-loop, label %exit
+
+exit:                                             ; preds = %fake-loop
+  %data.cast = bitcast <2 x i64>* %data to i64*
+  %0 = load i64, i64* %data.cast, align 8
+  %1 = icmp eq i64 %0, 1010101010101010101
+  %2 = select i1 %1, i32 0, i32 -1
+  ret i32 %2
+}
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1 immarg) #0
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture) #0
+
+attributes #0 = { argmemonly nounwind }
-- 
2.7.4