From: Guozhi Wei <carrot@google.com>
Date: Thu, 31 Jan 2019 20:46:42 +0000 (+0000)
Subject: [DAGCombine] Avoid CombineZExtLogicopShiftLoad if there is free ZEXT
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=7d44f474796af7676cffe829428a4f860f10ff5e;p=llvm

[DAGCombine] Avoid CombineZExtLogicopShiftLoad if there is free ZEXT

This patch fixes pr39098.

For the attached test case, CombineZExtLogicopShiftLoad can optimize it to

t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
  t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
    t58: i64 = srl t57, Constant:i8<1>
  t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64

But later visitANDLike transforms it to

t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
  t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
      t61: i32 = truncate t57
    t63: i32 = srl t61, Constant:i8<1>
  t64: i32 = and t63, Constant:i32<524287>
t65: i64 = zero_extend t64
    t58: i64 = srl t57, Constant:i8<1>
  t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64

And it triggers CombineZExtLogicopShiftLoad again, causes a dead loop.

Both forms should generate same instructions, CombineZExtLogicopShiftLoad generated IR looks cleaner. But it looks more difficult to prevent visitANDLike to do the transform, so I prevent CombineZExtLogicopShiftLoad to do the transform if the ZExt is free.

Differential Revision: https://reviews.llvm.org/D57491



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@352792 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 1f05a435bbe..f5339479b54 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -8402,6 +8402,9 @@ SDValue DAGCombiner::CombineExtLoad(SDNode *N) {
 SDValue DAGCombiner::CombineZExtLogicopShiftLoad(SDNode *N) {
   assert(N->getOpcode() == ISD::ZERO_EXTEND);
   EVT VT = N->getValueType(0);
+  EVT OrigVT = N->getOperand(0).getValueType();
+  if (TLI.isZExtFree(OrigVT, VT))
+    return SDValue();
 
   // and/or/xor
   SDValue N0 = N->getOperand(0);
diff --git a/test/CodeGen/X86/pr39098.ll b/test/CodeGen/X86/pr39098.ll
new file mode 100644
index 00000000000..fd586d7bb69
--- /dev/null
+++ b/test/CodeGen/X86/pr39098.ll
@@ -0,0 +1,20 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
+
+define dso_local void @test_cancel2(i40* %p1, i40* %p2) {
+; CHECK:       # %entry
+; CHECK-NEXT:  movl    (%rdi), %eax
+; CHECK-NEXT:  shrl    %eax
+; CHECK-NEXT:  andl    $524287, %eax
+; CHECK-NEXT:  movl    %eax, (%rsi)
+; CHECK-NEXT:  movb    $0, 4(%rsi)
+; CHECK-NEXT:  retq
+entry:
+  %0 = load i40, i40* %p1, align 8
+  %shl414 = shl i40 %0, 19
+  %unsclear415 = and i40 %shl414, 549755813887
+  %shr416 = lshr i40 %unsclear415, 20
+  %unsclear417 = and i40 %shr416, 549755813887
+  store i40 %unsclear417, i40* %p2, align 8
+  ret void
+}
+