[X86] Change precision control to FP80 during u64->fp32 conversion on Windows.

This is an alternative to D141074 to fix the problem by adjusting
the precision control dynamically.

Reviewed By: icedrocket

Differential Revision: https://reviews.llvm.org/D142178

(cherry picked from commit 11fb09ec0afa8620bba44f374763e2ad64332e2e)

4 files changed, 145 insertions, 5 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 5aa1c5a885e2..cf17c51b04fc 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -21986,15 +21986,25 @@ SDValue X86TargetLowering::LowerUINT_TO_FP(SDValue Op,
   // Extend everything to 80 bits to force it to be done on x87.
   // TODO: Are there any fast-math-flags to propagate here?
   if (IsStrict) {
-    SDValue Add = DAG.getNode(ISD::STRICT_FADD, dl, {MVT::f80, MVT::Other},
-                              {Chain, Fild, Fudge});
+    unsigned Opc = ISD::STRICT_FADD;
+    // Windows needs the precision control changed to 80bits around this add.
+    if (Subtarget.isOSWindows() && DstVT == MVT::f32)
+      Opc = X86ISD::STRICT_FP80_ADD;
+
+    SDValue Add =
+        DAG.getNode(Opc, dl, {MVT::f80, MVT::Other}, {Chain, Fild, Fudge});
     // STRICT_FP_ROUND can't handle equal types.
     if (DstVT == MVT::f80)
       return Add;
     return DAG.getNode(ISD::STRICT_FP_ROUND, dl, {DstVT, MVT::Other},
                        {Add.getValue(1), Add, DAG.getIntPtrConstant(0, dl)});
   }
-  SDValue Add = DAG.getNode(ISD::FADD, dl, MVT::f80, Fild, Fudge);
+  unsigned Opc = ISD::FADD;
+  // Windows needs the precision control changed to 80bits around this add.
+  if (Subtarget.isOSWindows() && DstVT == MVT::f32)
+    Opc = X86ISD::FP80_ADD;
+
+  SDValue Add = DAG.getNode(Opc, dl, MVT::f80, Fild, Fudge);
   return DAG.getNode(ISD::FP_ROUND, dl, DstVT, Add,
                      DAG.getIntPtrConstant(0, dl, /*isTarget=*/true));
 }
@@ -34790,6 +34800,8 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
   NODE_NAME_CASE(AESDECWIDE256KL)
   NODE_NAME_CASE(CMPCCXADD)
   NODE_NAME_CASE(TESTUI)
+  NODE_NAME_CASE(FP80_ADD)
+  NODE_NAME_CASE(STRICT_FP80_ADD)
   }
   return nullptr;
 #undef NODE_NAME_CASE
@@ -37300,6 +37312,69 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
     return BB;
   }
 
+  case X86::FP80_ADDr:
+  case X86::FP80_ADDm32: {
+    // Change the floating point control register to use double extended
+    // precision when performing the addition.
+    int OrigCWFrameIdx =
+        MF->getFrameInfo().CreateStackObject(2, Align(2), false);
+    addFrameReference(BuildMI(*BB, MI, DL, TII->get(X86::FNSTCW16m)),
+                      OrigCWFrameIdx);
+
+    // Load the old value of the control word...
+    Register OldCW = MF->getRegInfo().createVirtualRegister(&X86::GR32RegClass);
+    addFrameReference(BuildMI(*BB, MI, DL, TII->get(X86::MOVZX32rm16), OldCW),
+                      OrigCWFrameIdx);
+
+    // OR 0b11 into bit 8 and 9. 0b11 is the encoding for double extended
+    // precision.
+    Register NewCW = MF->getRegInfo().createVirtualRegister(&X86::GR32RegClass);
+    BuildMI(*BB, MI, DL, TII->get(X86::OR32ri), NewCW)
+        .addReg(OldCW, RegState::Kill)
+        .addImm(0x300);
+
+    // Extract to 16 bits.
+    Register NewCW16 =
+        MF->getRegInfo().createVirtualRegister(&X86::GR16RegClass);
+    BuildMI(*BB, MI, DL, TII->get(TargetOpcode::COPY), NewCW16)
+        .addReg(NewCW, RegState::Kill, X86::sub_16bit);
+
+    // Prepare memory for FLDCW.
+    int NewCWFrameIdx =
+        MF->getFrameInfo().CreateStackObject(2, Align(2), false);
+    addFrameReference(BuildMI(*BB, MI, DL, TII->get(X86::MOV16mr)),
+                      NewCWFrameIdx)
+        .addReg(NewCW16, RegState::Kill);
+
+    // Reload the modified control word now...
+    addFrameReference(BuildMI(*BB, MI, DL, TII->get(X86::FLDCW16m)),
+                      NewCWFrameIdx);
+
+    // Do the addition.
+    if (MI.getOpcode() == X86::FP80_ADDr) {
+      BuildMI(*BB, MI, DL, TII->get(X86::ADD_Fp80))
+          .add(MI.getOperand(0))
+          .add(MI.getOperand(1))
+          .add(MI.getOperand(2));
+    } else {
+      BuildMI(*BB, MI, DL, TII->get(X86::ADD_Fp80m32))
+          .add(MI.getOperand(0))
+          .add(MI.getOperand(1))
+          .add(MI.getOperand(2))
+          .add(MI.getOperand(3))
+          .add(MI.getOperand(4))
+          .add(MI.getOperand(5))
+          .add(MI.getOperand(6));
+    }
+
+    // Reload the original control word now.
+    addFrameReference(BuildMI(*BB, MI, DL, TII->get(X86::FLDCW16m)),
+                      OrigCWFrameIdx);
+
+    MI.eraseFromParent(); // The pseudo instruction is gone now.
+    return BB;
+  }
+
   case X86::FP32_TO_INT16_IN_MEM:
   case X86::FP32_TO_INT32_IN_MEM:
   case X86::FP32_TO_INT64_IN_MEM:
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index c5c115047271..d802d5f53aa2 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -740,6 +740,9 @@ namespace llvm {
     // User level interrupts - testui
     TESTUI,
 
+    // Perform an FP80 add after changing precision control in FPCW.
+    FP80_ADD,
+
     /// X86 strict FP compare instructions.
     STRICT_FCMP = ISD::FIRST_TARGET_STRICTFP_OPCODE,
     STRICT_FCMPS,
@@ -779,6 +782,9 @@ namespace llvm {
     STRICT_CVTPS2PH,
     STRICT_CVTPH2PS,
 
+    // Perform an FP80 add after changing precision control in FPCW.
+    STRICT_FP80_ADD,
+
     // WARNING: Only add nodes here if they are strict FP nodes. Non-memory and
     // non-strict FP nodes should be above FIRST_TARGET_STRICTFP_OPCODE.
 
diff --git a/llvm/lib/Target/X86/X86InstrFPStack.td b/llvm/lib/Target/X86/X86InstrFPStack.td
index a68d61043c5c..fbbd3c83dc5c 100644
--- a/llvm/lib/Target/X86/X86InstrFPStack.td
+++ b/llvm/lib/Target/X86/X86InstrFPStack.td
@@ -26,6 +26,13 @@ def SDTX86Fist      : SDTypeProfile<0, 2, [SDTCisFP<0>, SDTCisPtrTy<1>]>;
 def SDTX86CwdStore  : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>;
 def SDTX86CwdLoad   : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>;
 
+def X86fp80_add     : SDNode<"X86ISD::FP80_ADD", SDTFPBinOp, [SDNPCommutative]>;
+def X86strict_fp80_add : SDNode<"X86ISD::STRICT_FP80_ADD", SDTFPBinOp,
+                        [SDNPHasChain,SDNPCommutative]>;
+def any_X86fp80_add : PatFrags<(ops node:$lhs, node:$rhs),
+                               [(X86strict_fp80_add node:$lhs, node:$rhs),
+                                (X86fp80_add node:$lhs, node:$rhs)]>;
+
 def X86fld          : SDNode<"X86ISD::FLD", SDTX86Fld,
                              [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
 def X86fst          : SDNode<"X86ISD::FST", SDTX86Fst,
@@ -141,6 +148,14 @@ let usesCustomInserter = 1, hasNoSchedulingInfo = 1, Defs = [EFLAGS] in {
                               [(X86fp_to_i32mem RFP80:$src, addr:$dst)]>;
   def FP80_TO_INT64_IN_MEM : PseudoI<(outs), (ins i64mem:$dst, RFP80:$src),
                               [(X86fp_to_i64mem RFP80:$src, addr:$dst)]>;
+
+  def FP80_ADDr : PseudoI<(outs RFP80:$dst), (ins RFP80:$src1, RFP80:$src2),
+                          [(set RFP80:$dst,
+                                (any_X86fp80_add  RFP80:$src1, RFP80:$src2))]>;
+  def FP80_ADDm32 : PseudoI<(outs RFP80:$dst), (ins RFP80:$src1, f32mem:$src2),
+                            [(set RFP80:$dst,
+                                  (any_X86fp80_add RFP80:$src1,
+                                                   (f80 (extloadf32 addr:$src2))))]>;
 }
 
 // All FP Stack operations are represented with four instructions here.  The
diff --git a/llvm/test/CodeGen/X86/uint64-to-float.ll b/llvm/test/CodeGen/X86/uint64-to-float.ll
index 8b6623476eba..03a817158962 100644
--- a/llvm/test/CodeGen/X86/uint64-to-float.ll
+++ b/llvm/test/CodeGen/X86/uint64-to-float.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=i686-apple-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
-; RUN: llc < %s -mtriple=x86_64-apple-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=i686-windows -mattr=+sse2 | FileCheck %s --check-prefix=X86-WIN
+; RUN: llc < %s -mtriple=x86_64-windows -mattr=+sse2 | FileCheck %s --check-prefix=X64-WIN
 
 ; Verify that we are using the efficient uitofp --> sitofp lowering illustrated
 ; by the compiler_rt implementation of __floatundisf.
@@ -42,6 +44,48 @@ define float @test(i64 %a) nounwind {
 ; X64-NEXT:    cvtsi2ss %rdi, %xmm0
 ; X64-NEXT:    addss %xmm0, %xmm0
 ; X64-NEXT:    retq
+;
+; X86-WIN-LABEL: test:
+; X86-WIN:       # %bb.0: # %entry
+; X86-WIN-NEXT:    pushl %ebp
+; X86-WIN-NEXT:    movl %esp, %ebp
+; X86-WIN-NEXT:    andl $-8, %esp
+; X86-WIN-NEXT:    subl $24, %esp
+; X86-WIN-NEXT:    movl 12(%ebp), %eax
+; X86-WIN-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; X86-WIN-NEXT:    movlps %xmm0, {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    shrl $31, %eax
+; X86-WIN-NEXT:    fildll {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    fnstcw {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    movzwl {{[0-9]+}}(%esp), %ecx
+; X86-WIN-NEXT:    orl $768, %ecx # imm = 0x300
+; X86-WIN-NEXT:    movw %cx, {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    fldcw {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    fadds __real@5f80000000000000(,%eax,4)
+; X86-WIN-NEXT:    fldcw {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    fstps {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X86-WIN-NEXT:    movss %xmm0, {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    flds {{[0-9]+}}(%esp)
+; X86-WIN-NEXT:    movl %ebp, %esp
+; X86-WIN-NEXT:    popl %ebp
+; X86-WIN-NEXT:    retl
+;
+; X64-WIN-LABEL: test:
+; X64-WIN:       # %bb.0: # %entry
+; X64-WIN-NEXT:    testq %rcx, %rcx
+; X64-WIN-NEXT:    js .LBB0_1
+; X64-WIN-NEXT:  # %bb.2: # %entry
+; X64-WIN-NEXT:    cvtsi2ss %rcx, %xmm0
+; X64-WIN-NEXT:    retq
+; X64-WIN-NEXT:  .LBB0_1:
+; X64-WIN-NEXT:    movq %rcx, %rax
+; X64-WIN-NEXT:    shrq %rax
+; X64-WIN-NEXT:    andl $1, %ecx
+; X64-WIN-NEXT:    orq %rax, %rcx
+; X64-WIN-NEXT:    cvtsi2ss %rcx, %xmm0
+; X64-WIN-NEXT:    addss %xmm0, %xmm0
+; X64-WIN-NEXT:    retq
 entry:
   %b = uitofp i64 %a to float
   ret float %b