From b9a7b7a84d35fc13c2f49d81c3353dd58f12ee03 Mon Sep 17 00:00:00 2001
From: Lei Liu <lei.liu2@windriver.com>
Date: Thu, 2 Aug 2018 01:54:12 +0000
Subject: [PATCH] Fix FCOPYSIGN expansion

In expansion of FCOPYSIGN, the shift node is missing when the two
operands of FCOPYSIGN are of the same size. We should always generate
shift node (if the required shift bit is not zero) to put the sign
bit into the right position, regardless of the size of underlying
types.

Differential Revision: https://reviews.llvm.org/D49973

llvm-svn: 338665
---
 llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 30 ++++++++-----------
 llvm/test/CodeGen/AArch64/fcopysign.ll        | 25 ++++++++++++++--
 2 files changed, 35 insertions(+), 20 deletions(-)

diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index 2b7ba1ffb309..36c436918916 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -1489,24 +1489,20 @@ SDValue SelectionDAGLegalize::ExpandFCOPYSIGN(SDNode *Node) const {
 
   // Get the signbit at the right position for MagAsInt.
   int ShiftAmount = SignAsInt.SignBit - MagAsInt.SignBit;
-  if (SignBit.getValueSizeInBits() > ClearedSign.getValueSizeInBits()) {
-    if (ShiftAmount > 0) {
-      SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, IntVT);
-      SignBit = DAG.getNode(ISD::SRL, DL, IntVT, SignBit, ShiftCnst);
-    } else if (ShiftAmount < 0) {
-      SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, IntVT);
-      SignBit = DAG.getNode(ISD::SHL, DL, IntVT, SignBit, ShiftCnst);
-    }
-    SignBit = DAG.getNode(ISD::TRUNCATE, DL, MagVT, SignBit);
-  } else if (SignBit.getValueSizeInBits() < ClearedSign.getValueSizeInBits()) {
+  EVT ShiftVT = IntVT;
+  if (SignBit.getValueSizeInBits() < ClearedSign.getValueSizeInBits()) {
     SignBit = DAG.getNode(ISD::ZERO_EXTEND, DL, MagVT, SignBit);
-    if (ShiftAmount > 0) {
-      SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, MagVT);
-      SignBit = DAG.getNode(ISD::SRL, DL, MagVT, SignBit, ShiftCnst);
-    } else if (ShiftAmount < 0) {
-      SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, MagVT);
-      SignBit = DAG.getNode(ISD::SHL, DL, MagVT, SignBit, ShiftCnst);
-    }
+    ShiftVT = MagVT;
+  }
+  if (ShiftAmount > 0) {
+    SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, ShiftVT);
+    SignBit = DAG.getNode(ISD::SRL, DL, ShiftVT, SignBit, ShiftCnst);
+  } else if (ShiftAmount < 0) {
+    SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, ShiftVT);
+    SignBit = DAG.getNode(ISD::SHL, DL, ShiftVT, SignBit, ShiftCnst);
+  }
+  if (SignBit.getValueSizeInBits() > ClearedSign.getValueSizeInBits()) {
+    SignBit = DAG.getNode(ISD::TRUNCATE, DL, MagVT, SignBit);
   }
 
   // Store the part with the modified sign and convert back to float.
diff --git a/llvm/test/CodeGen/AArch64/fcopysign.ll b/llvm/test/CodeGen/AArch64/fcopysign.ll
index 6bda33cf76ef..a625a9eb2a6c 100644
--- a/llvm/test/CodeGen/AArch64/fcopysign.ll
+++ b/llvm/test/CodeGen/AArch64/fcopysign.ll
@@ -5,10 +5,12 @@ target triple = "aarch64--"
 
 declare fp128 @llvm.copysign.f128(fp128, fp128)
 
-@val = global double zeroinitializer, align 8
+@val_float = global float zeroinitializer, align 4
+@val_double = global double zeroinitializer, align 8
+@val_fp128 = global fp128 zeroinitializer, align 16
 
 ; CHECK-LABEL: copysign0
-; CHECK: ldr [[REG:x[0-9]+]], [x8, :lo12:val]
+; CHECK: ldr [[REG:x[0-9]+]], [x8, :lo12:val_double]
 ; CHECK: and [[ANDREG:x[0-9]+]], [[REG]], #0x8000000000000000
 ; CHECK: lsr x[[LSRREGNUM:[0-9]+]], [[ANDREG]], #56
 ; CHECK: bfxil w[[LSRREGNUM]], w{{[0-9]+}}, #0, #7
@@ -16,8 +18,25 @@ declare fp128 @llvm.copysign.f128(fp128, fp128)
 ; CHECK: ldr q{{[0-9]+}},
 define fp128 @copysign0() {
 entry:
-  %v = load double, double* @val, align 8
+  %v = load double, double* @val_double, align 8
   %conv = fpext double %v to fp128
   %call = tail call fp128 @llvm.copysign.f128(fp128 0xL00000000000000007FFF000000000000, fp128 %conv) #2
   ret fp128 %call
 }
+
+; CHECK-LABEL: copysign1
+; CHECK-DAG: ldr [[REG:q[0-9]+]], [x8, :lo12:val_fp128]
+; CHECK-DAG: ldr [[REG:w[0-9]+]], [x8, :lo12:val_float]
+; CHECK: and [[ANDREG:w[0-9]+]], [[REG]], #0x80000000
+; CHECK: lsr w[[LSRREGNUM:[0-9]+]], [[ANDREG]], #24
+; CHECK: bfxil w[[LSRREGNUM]], w{{[0-9]+}}, #0, #7
+; CHECK: strb w[[LSRREGNUM]],
+; CHECK: ldr q{{[0-9]+}},
+define fp128@copysign1() {
+entry:
+  %v0 = load fp128, fp128* @val_fp128, align 16
+  %v1 = load float, float* @val_float, align 4
+  %conv = fpext float %v1 to fp128
+  %call = tail call fp128 @llvm.copysign.f128(fp128 %v0, fp128 %conv)
+  ret fp128 %call
+}