Fix (bitcast (fabs x)), (bitcast (fneg x)) and (bitcast (fcopysign cst,

x)) combines for ppc_fp128, since signbit computation is more
complicated.

Discussion thread:
http://lists.llvm.org/pipermail/llvm-dev/2015-November/092863.html

Patch by Tim Shen!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255305 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 97a9646c3232a9af3bba3d9e79e270d39cd1479e..0872d7a9a22828a8a095f9cc8712b7dc3a4a226b 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -7244,6 +7244,12 @@ SDValue DAGCombiner::CombineConsecutiveLoads(SDNode *N, EVT VT) {
   return SDValue();
 }
 
+static unsigned getPPCf128HiElementSelector(const SelectionDAG &DAG) {
+  // On little-endian machines, bitcasting from ppcf128 to i128 does swap the Hi
+  // and Lo parts; on big-endian machines it doesn't.
+  return DAG.getDataLayout().isBigEndian() ? 1 : 0;
+}
+
 SDValue DAGCombiner::visitBITCAST(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   EVT VT = N->getValueType(0);
@@ -7310,6 +7316,14 @@ SDValue DAGCombiner::visitBITCAST(SDNode *N) {
 
   // fold (bitconvert (fneg x)) -> (xor (bitconvert x), signbit)
   // fold (bitconvert (fabs x)) -> (and (bitconvert x), (not signbit))
+  //
+  // For ppc_fp128:
+  // fold (bitcast (fneg x)) ->
+  //     flipbit = signbit
+  //     (xor (bitcast x) (build_pair flipbit, flipbit))
+  // fold (bitcast (fabs x)) ->
+  //     flipbit = (and (extract_element (bitcast x), 0), signbit)
+  //     (xor (bitcast x) (build_pair flipbit, flipbit))
   // This often reduces constant pool loads.
   if (((N0.getOpcode() == ISD::FNEG && !TLI.isFNegFree(N0.getValueType())) ||
        (N0.getOpcode() == ISD::FABS && !TLI.isFAbsFree(N0.getValueType()))) &&
@@ -7320,6 +7334,29 @@ SDValue DAGCombiner::visitBITCAST(SDNode *N) {
     AddToWorklist(NewConv.getNode());
 
     SDLoc DL(N);
+    if (N0.getValueType() == MVT::ppcf128 && !LegalTypes) {
+      assert(VT.getSizeInBits() == 128);
+      SDValue SignBit = DAG.getConstant(
+          APInt::getSignBit(VT.getSizeInBits() / 2), SDLoc(N0), MVT::i64);
+      SDValue FlipBit;
+      if (N0.getOpcode() == ISD::FNEG) {
+        FlipBit = SignBit;
+        AddToWorklist(FlipBit.getNode());
+      } else {
+        assert(N0.getOpcode() == ISD::FABS);
+        SDValue Hi =
+            DAG.getNode(ISD::EXTRACT_ELEMENT, SDLoc(NewConv), MVT::i64, NewConv,
+                        DAG.getIntPtrConstant(getPPCf128HiElementSelector(DAG),
+                                              SDLoc(NewConv)));
+        AddToWorklist(Hi.getNode());
+        FlipBit = DAG.getNode(ISD::AND, SDLoc(N0), MVT::i64, Hi, SignBit);
+        AddToWorklist(FlipBit.getNode());
+      }
+      SDValue FlipBits =
+          DAG.getNode(ISD::BUILD_PAIR, SDLoc(N0), VT, FlipBit, FlipBit);
+      AddToWorklist(FlipBits.getNode());
+      return DAG.getNode(ISD::XOR, DL, VT, NewConv, FlipBits);
+    }
     APInt SignBit = APInt::getSignBit(VT.getSizeInBits());
     if (N0.getOpcode() == ISD::FNEG)
       return DAG.getNode(ISD::XOR, DL, VT,
@@ -7333,6 +7370,13 @@ SDValue DAGCombiner::visitBITCAST(SDNode *N) {
   //         (or (and (bitconvert x), sign), (and cst, (not sign)))
   // Note that we don't handle (copysign x, cst) because this can always be
   // folded to an fneg or fabs.
+  //
+  // For ppc_fp128:
+  // fold (bitcast (fcopysign cst, x)) ->
+  //     flipbit = (and (extract_element
+  //                     (xor (bitcast cst), (bitcast x)), 0),
+  //                    signbit)
+  //     (xor (bitcast cst) (build_pair flipbit, flipbit))
   if (N0.getOpcode() == ISD::FCOPYSIGN && N0.getNode()->hasOneUse() &&
       isa<ConstantFPSDNode>(N0.getOperand(0)) &&
       VT.isInteger() && !VT.isVector()) {
@@ -7361,6 +7405,30 @@ SDValue DAGCombiner::visitBITCAST(SDNode *N) {
         AddToWorklist(X.getNode());
       }
 
+      if (N0.getValueType() == MVT::ppcf128 && !LegalTypes) {
+        APInt SignBit = APInt::getSignBit(VT.getSizeInBits() / 2);
+        SDValue Cst = DAG.getNode(ISD::BITCAST, SDLoc(N0.getOperand(0)), VT,
+                                  N0.getOperand(0));
+        AddToWorklist(Cst.getNode());
+        SDValue X = DAG.getNode(ISD::BITCAST, SDLoc(N0.getOperand(1)), VT,
+                                N0.getOperand(1));
+        AddToWorklist(X.getNode());
+        SDValue XorResult = DAG.getNode(ISD::XOR, SDLoc(N0), VT, Cst, X);
+        AddToWorklist(XorResult.getNode());
+        SDValue XorResult64 = DAG.getNode(
+            ISD::EXTRACT_ELEMENT, SDLoc(XorResult), MVT::i64, XorResult,
+            DAG.getIntPtrConstant(getPPCf128HiElementSelector(DAG),
+                                  SDLoc(XorResult)));
+        AddToWorklist(XorResult64.getNode());
+        SDValue FlipBit =
+            DAG.getNode(ISD::AND, SDLoc(XorResult64), MVT::i64, XorResult64,
+                        DAG.getConstant(SignBit, SDLoc(XorResult64), MVT::i64));
+        AddToWorklist(FlipBit.getNode());
+        SDValue FlipBits =
+            DAG.getNode(ISD::BUILD_PAIR, SDLoc(N0), VT, FlipBit, FlipBit);
+        AddToWorklist(FlipBits.getNode());
+        return DAG.getNode(ISD::XOR, SDLoc(N), VT, Cst, FlipBits);
+      }
       APInt SignBit = APInt::getSignBit(VT.getSizeInBits());
       X = DAG.getNode(ISD::AND, SDLoc(X), VT,
                       X, DAG.getConstant(SignBit, SDLoc(X), VT));

diff --git a/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll b/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
new file mode 100644 (file)
index 0000000..5f3c927
--- /dev/null
+++ b/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
@@ -0,0 +1,103 @@
+; RUN: llc -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s -check-prefix=PPC64
+; RUN: llc -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr7 < %s | FileCheck %s -check-prefix=PPC64
+; RUN: llc -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s -check-prefix=PPC64
+; RUN: llc -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 < %s | FileCheck %s -check-prefix=PPC64
+; RUN: llc -mtriple=powerpc-unknown-linux-gnu < %s | FileCheck %s -check-prefix=PPC32
+
+define i128 @test_abs(ppc_fp128 %x) nounwind  {
+entry:
+; PPC64-LABEL: test_abs:
+; PPC64-DAG: stxsdx 2, 0, [[ADDR_HI:[0-9]+]]
+; PPC64-DAG: stxsdx 1, 0, [[ADDR_LO:[0-9]+]]
+; PPC64-DAG: addi [[ADDR_HI]], [[SP:[0-9]+]], [[OFFSET_HI:-?[0-9]+]]
+; PPC64-DAG: addi [[ADDR_LO]], [[SP]], [[OFFSET_LO:-?[0-9]+]]
+; PPC64-DAG: li [[MASK_REG:[0-9]+]], 1
+; PPC64: sldi [[MASK_REG]], [[MASK_REG]], 63
+; PPC64-DAG: ld [[HI:[0-9]+]], [[OFFSET_LO]]([[SP]])
+; PPC64-DAG: ld [[LO:[0-9]+]], [[OFFSET_HI]]([[SP]])
+; PPC64: and [[FLIP_BIT:[0-9]+]], [[HI]], [[MASK_REG]]
+; PPC64-DAG: xor 3, [[HI]], [[FLIP_BIT]]
+; PPC64-DAG: xor 4, [[LO]], [[FLIP_BIT]]
+; PPC64: blr
+
+; PPC32-DAG: stfd 1, 24(1)
+; PPC32-DAG: stfd 2, 16(1)
+; PPC32: nop
+; PPC32-DAG: lwz [[HI0:[0-9]+]], 24(1)
+; PPC32-DAG: lwz [[LO0:[0-9]+]], 16(1)
+; PPC32-DAG: lwz [[HI1:[0-9]+]], 28(1)
+; PPC32-DAG: lwz [[LO1:[0-9]+]], 20(1)
+; PPC32: rlwinm [[FLIP_BIT:[0-9]+]], [[HI0]], 0, 0, 0
+; PPC32-DAG: xor [[HI0]], [[HI0]], [[FLIP_BIT]]
+; PPC32-DAG: xor [[LO0]], [[LO0]], [[FLIP_BIT]]
+; PPC32: blr
+       %0 = tail call ppc_fp128 @llvm.fabs.ppcf128(ppc_fp128 %x)
+       %1 = bitcast ppc_fp128 %0 to i128
+       ret i128 %1
+}
+
+define i128 @test_neg(ppc_fp128 %x) nounwind  {
+entry:
+; PPC64-LABEL: test_neg:
+; PPC64-DAG: stxsdx 2, 0, [[ADDR_HI:[0-9]+]]
+; PPC64-DAG: stxsdx 1, 0, [[ADDR_LO:[0-9]+]]
+; PPC64-DAG: addi [[ADDR_HI]], [[SP:[0-9]+]], [[OFFSET_HI:-?[0-9]+]]
+; PPC64-DAG: addi [[ADDR_LO]], [[SP]], [[OFFSET_LO:-?[0-9]+]]
+; PPC64-DAG: li [[FLIP_BIT:[0-9]+]], 1
+; PPC64-DAG: sldi [[FLIP_BIT]], [[FLIP_BIT]], 63
+; PPC64-DAG: ld [[HI:[0-9]+]], [[OFFSET_LO]]([[SP]])
+; PPC64-DAG: ld [[LO:[0-9]+]], [[OFFSET_HI]]([[SP]])
+; PPC64-NOT: BARRIER
+; PPC64-DAG: xor 3, [[HI]], [[FLIP_BIT]]
+; PPC64-DAG: xor 4, [[LO]], [[FLIP_BIT]]
+; PPC64: blr
+
+; PPC32-DAG: stfd 1, 24(1)
+; PPC32-DAG: stfd 2, 16(1)
+; PPC32: nop
+; PPC32-DAG: lwz [[HI0:[0-9]+]], 24(1)
+; PPC32-DAG: lwz [[LO0:[0-9]+]], 16(1)
+; PPC32-DAG: lwz [[HI1:[0-9]+]], 28(1)
+; PPC32-DAG: lwz [[LO1:[0-9]+]], 20(1)
+; PPC32-NOT: BARRIER
+; PPC32-DAG: xoris [[HI0]], [[HI0]], 32768
+; PPC32-DAG: xoris [[LO0]], [[LO0]], 32768
+; PPC32: blr
+       %0 = fsub ppc_fp128 0xM80000000000000000000000000000000, %x
+       %1 = bitcast ppc_fp128 %0 to i128
+       ret i128 %1
+}
+
+define i128 @test_copysign(ppc_fp128 %x) nounwind  {
+entry:
+; PPC64-LABEL: test_copysign:
+; PPC64-DAG: stxsdx 1, 0, [[ADDR_REG:[0-9]+]]
+; PPC64-DAG: addi [[ADDR_REG]], 1, [[OFFSET:-?[0-9]+]]
+; PPC64-DAG: li [[SIGN:[0-9]+]], 1
+; PPC64-DAG: sldi [[SIGN]], [[SIGN]], 63
+; PPC64-DAG: li [[HI_TMP:[0-9]+]], 16399
+; PPC64-DAG: sldi [[CST_HI:[0-9]+]], [[HI_TMP]], 48
+; PPC64-DAG: li [[LO_TMP:[0-9]+]], 3019
+; PPC64-DAG: sldi [[CST_LO:[0-9]+]], [[LO_TMP]], 52
+; PPC64-NOT: BARRIER
+; PPC64-DAG: ld [[X_HI:[0-9]+]], [[OFFSET]](1)
+; PPC64-DAG: and [[NEW_HI_TMP:[0-9]+]], [[X_HI]], [[SIGN]]
+; PPC64-DAG: or 3, [[NEW_HI_TMP]], [[CST_HI]]
+; PPC64-DAG: xor 4, [[SIGN]], [[CST_LO]]
+; PPC64: blr
+
+; PPC32: stfd 1, [[STACK:[0-9]+]](1)
+; PPC32: nop
+; PPC32: lwz [[HI:[0-9]+]], [[STACK]](1)
+; PPC32: rlwinm [[FLIP_BIT:[0-9]+]], [[HI]], 0, 0, 0
+; PPC32-NOT: BARRIER
+; PPC32-DAG: oris {{[0-9]+}}, [[FLIP_BIT]], 16399
+; PPC32-DAG: xoris {{[0-9]+}}, [[FLIP_BIT]], 48304
+; PPC32: blr
+       %0 = tail call ppc_fp128 @llvm.copysign.ppcf128(ppc_fp128 0xMBCB0000000000000400F000000000000, ppc_fp128 %x)
+       %1 = bitcast ppc_fp128 %0 to i128
+       ret i128 %1
+}
+
+declare ppc_fp128 @llvm.fabs.ppcf128(ppc_fp128)
+declare ppc_fp128 @llvm.copysign.ppcf128(ppc_fp128, ppc_fp128)