From 4ec67ba9fdd9b517a50068f29b654c4d09e653de Mon Sep 17 00:00:00 2001
From: Joerg Sonnenberger <joerg@bec.de>
Date: Mon, 9 Mar 2015 21:12:42 +0000
Subject: [PATCH] Merging r231563 from adibiagio:

[DAGCombiner] Fix wrong folding of AND dag nodes.

This patch fixes the logic in the DAGCombiner that folds an AND node according
to rule: (and (X (load V)), C) -> (X (load V))

An AND between a vector load 'X' and a constant build_vector 'C' can be folded
into the load itself only if we can prove that the AND operation is redundant.
The algorithm implemented by 'visitAND' firstly computes the splat value 'S'
from C, and then checks if S has the lower 'B' bits set (where B is the size in
bits of the vector element type). The algorithm takes into account also the
'undef' bits in the splat mask.

Unfortunately, the algorithm only worked under the assumption that the size of S
is a multiple of the vector element type. With this patch, we conservatively
avoid folding the AND if the splat bits are not compatible with the vector
element type.

Added X86 test and-load-fold.ll

Differential Revision: http://reviews.llvm.org/D8085


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@231702 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/CodeGen/SelectionDAG/DAGCombiner.cpp | 10 +++++++---
 test/CodeGen/X86/and-load-fold.ll        | 15 +++++++++++++++
 2 files changed, 22 insertions(+), 3 deletions(-)
 create mode 100644 test/CodeGen/X86/and-load-fold.ll

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index afb986f1d7c..a71825836bd 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -2788,9 +2788,13 @@ SDValue DAGCombiner::visitAND(SDNode *N) {
                SplatBitSize = SplatBitSize * 2)
             SplatValue |= SplatValue.shl(SplatBitSize);
 
-        Constant = APInt::getAllOnesValue(BitWidth);
-        for (unsigned i = 0, n = SplatBitSize/BitWidth; i < n; ++i)
-          Constant &= SplatValue.lshr(i*BitWidth).zextOrTrunc(BitWidth);
+        // Make sure that variable 'Constant' is only set if 'SplatBitSize' is a
+        // multiple of 'BitWidth'. Otherwise, we could propagate a wrong value.
+        if (SplatBitSize % BitWidth == 0) {
+          Constant = APInt::getAllOnesValue(BitWidth);
+          for (unsigned i = 0, n = SplatBitSize/BitWidth; i < n; ++i)
+            Constant &= SplatValue.lshr(i*BitWidth).zextOrTrunc(BitWidth);
+        }
       }
     }
 
diff --git a/test/CodeGen/X86/and-load-fold.ll b/test/CodeGen/X86/and-load-fold.ll
new file mode 100644
index 00000000000..d6f68b3bc43
--- /dev/null
+++ b/test/CodeGen/X86/and-load-fold.ll
@@ -0,0 +1,15 @@
+; RUN: llc -mtriple=x86_64-unknown-unknown -mcpu=generic < %s | FileCheck %s
+
+; Verify that the DAGCombiner doesn't wrongly remove the 'and' from the dag.
+
+define i8 @foo(<4 x i8>* %V) {
+; CHECK-LABEL: foo:
+; CHECK: pand
+; CHECK: ret
+entry:
+  %Vp = bitcast <4 x i8>* %V to <3 x i8>*
+  %V3i8 = load <3 x i8>* %Vp, align 4
+  %0 = and <3 x i8> %V3i8, <i8 undef, i8 undef, i8 95>
+  %1 = extractelement <3 x i8> %0, i64 2
+  ret i8 %1
+}
-- 
2.40.0