From 14ea1ec2324cb595f2e035bbf54ddcd483f17c11 Mon Sep 17 00:00:00 2001
From: Dan Gohman <gohman@apple.com>
Date: Fri, 13 Mar 2009 20:42:20 +0000
Subject: [PATCH] Fix FastISel's assumption that i1 values are always
 zero-extended by inserting explicit zero extensions where necessary. Included
 is a testcase where SelectionDAG produces a virtual register holding an i1
 value which FastISel previously mistakenly assumed to be zero-extended.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@66941 91177308-0d34-0410-b5e6-96231b3b80d8
---
 include/llvm/CodeGen/FastISel.h       |  5 +++++
 lib/CodeGen/SelectionDAG/FastISel.cpp | 15 ++++++++++++++-
 lib/Target/X86/X86FastISel.cpp        |  6 ++++--
 test/CodeGen/X86/fast-isel-i1.ll      | 19 +++++++++++++++++++
 4 files changed, 42 insertions(+), 3 deletions(-)
 create mode 100644 test/CodeGen/X86/fast-isel-i1.ll

diff --git a/include/llvm/CodeGen/FastISel.h b/include/llvm/CodeGen/FastISel.h
index 1c26b3fd763..085810aaf11 100644
--- a/include/llvm/CodeGen/FastISel.h
+++ b/include/llvm/CodeGen/FastISel.h
@@ -269,6 +269,11 @@ protected:
   unsigned FastEmitInst_extractsubreg(MVT::SimpleValueType RetVT,
                                       unsigned Op0, uint32_t Idx);
 
+  /// FastEmitZExtFromI1 - Emit MachineInstrs to compute the value of Op
+  /// with all but the least significant bit set to zero.
+  unsigned FastEmitZExtFromI1(MVT::SimpleValueType VT,
+                              unsigned Op);
+
   /// FastEmitBranch - Emit an unconditional branch to the given block,
   /// unless it is the immediate (fall-through) successor, and update
   /// the CFG.
diff --git a/lib/CodeGen/SelectionDAG/FastISel.cpp b/lib/CodeGen/SelectionDAG/FastISel.cpp
index 229376d293c..3523dda97ea 100644
--- a/lib/CodeGen/SelectionDAG/FastISel.cpp
+++ b/lib/CodeGen/SelectionDAG/FastISel.cpp
@@ -497,7 +497,14 @@ bool FastISel::SelectCast(User *I, ISD::NodeType Opcode) {
   if (!InputReg)
     // Unhandled operand.  Halt "fast" selection and bail.
     return false;
-    
+
+  // If the operand is i1, arrange for the high bits in the register to be zero.
+  if (I->getOperand(0)->getType() == Type::Int1Ty) {
+   InputReg = FastEmitZExtFromI1(SrcVT.getSimpleVT(), InputReg);
+   if (!InputReg)
+     return false;
+  }
+
   unsigned ResultReg = FastEmit_r(SrcVT.getSimpleVT(),
                                   DstVT.getSimpleVT(),
                                   Opcode,
@@ -970,3 +977,9 @@ unsigned FastISel::FastEmitInst_extractsubreg(MVT::SimpleValueType RetVT,
   }
   return ResultReg;
 }
+
+/// FastEmitZExtFromI1 - Emit MachineInstrs to compute the value of Op
+/// with all but the least significant bit set to zero.
+unsigned FastISel::FastEmitZExtFromI1(MVT::SimpleValueType VT, unsigned Op) {
+  return FastEmit_ri(VT, VT, ISD::AND, Op, 1);
+}
diff --git a/lib/Target/X86/X86FastISel.cpp b/lib/Target/X86/X86FastISel.cpp
index d6cdc3fb64a..50f1935dcdb 100644
--- a/lib/Target/X86/X86FastISel.cpp
+++ b/lib/Target/X86/X86FastISel.cpp
@@ -671,12 +671,14 @@ bool X86FastISel::X86SelectCmp(Instruction *I) {
 }
 
 bool X86FastISel::X86SelectZExt(Instruction *I) {
-  // Special-case hack: The only i1 values we know how to produce currently
-  // set the upper bits of an i8 value to zero.
+  // Handle zero-extension from i1 to i8, which is common.
   if (I->getType() == Type::Int8Ty &&
       I->getOperand(0)->getType() == Type::Int1Ty) {
     unsigned ResultReg = getRegForValue(I->getOperand(0));
     if (ResultReg == 0) return false;
+    // Set the high bits to zero.
+    ResultReg = FastEmitZExtFromI1(MVT::i8, ResultReg);
+    if (ResultReg == 0) return false;
     UpdateValueMap(I, ResultReg);
     return true;
   }
diff --git a/test/CodeGen/X86/fast-isel-i1.ll b/test/CodeGen/X86/fast-isel-i1.ll
new file mode 100644
index 00000000000..e1ff7921a11
--- /dev/null
+++ b/test/CodeGen/X86/fast-isel-i1.ll
@@ -0,0 +1,19 @@
+; RUN: llvm-as < %s | llc -march=x86 -fast-isel | grep {andb	\$1, %}
+
+declare i64 @bar(i64)
+
+define i32 @foo(i64 %x) nounwind {
+	%y = add i64 %x, -3		; <i64> [#uses=1]
+	%t = call i64 @bar(i64 %y)		; <i64> [#uses=1]
+	%s = mul i64 %t, 77		; <i64> [#uses=1]
+	%z = trunc i64 %s to i1		; <i1> [#uses=1]
+	br label %next
+
+next:		; preds = %0
+	%u = zext i1 %z to i32		; <i32> [#uses=1]
+	%v = add i32 %u, 1999		; <i32> [#uses=1]
+	br label %exit
+
+exit:		; preds = %next
+	ret i32 %v
+}