[LegalizeTypes][X86] Add ExpandIntegerResult support for STRICT_FP_TO_SINT/STRICT_FP_TO_UINT.

3 files changed, 199 insertions, 6 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
index 9f8da60eb9a..dd082646ae5 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
@@ -1698,7 +1698,9 @@ void DAGTypeLegalizer::ExpandIntegerResult(SDNode *N, unsigned ResNo) {
   case ISD::CTTZ_ZERO_UNDEF:
   case ISD::CTTZ:        ExpandIntRes_CTTZ(N, Lo, Hi); break;
   case ISD::FLT_ROUNDS_: ExpandIntRes_FLT_ROUNDS(N, Lo, Hi); break;
+  case ISD::STRICT_FP_TO_SINT:
   case ISD::FP_TO_SINT:  ExpandIntRes_FP_TO_SINT(N, Lo, Hi); break;
+  case ISD::STRICT_FP_TO_UINT:
   case ISD::FP_TO_UINT:  ExpandIntRes_FP_TO_UINT(N, Lo, Hi); break;
   case ISD::STRICT_LLROUND:
   case ISD::STRICT_LLRINT:
@@ -2564,7 +2566,9 @@ void DAGTypeLegalizer::ExpandIntRes_FP_TO_SINT(SDNode *N, SDValue &Lo,
   SDLoc dl(N);
   EVT VT = N->getValueType(0);
 
-  SDValue Op = N->getOperand(0);
+  bool IsStrict = N->isStrictFPOpcode();
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
+  SDValue Op = N->getOperand(IsStrict ? 1 : 0);
   if (getTypeAction(Op.getValueType()) == TargetLowering::TypePromoteFloat)
     Op = GetPromotedFloat(Op);
 
@@ -2572,8 +2576,12 @@ void DAGTypeLegalizer::ExpandIntRes_FP_TO_SINT(SDNode *N, SDValue &Lo,
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unexpected fp-to-sint conversion!");
   TargetLowering::MakeLibCallOptions CallOptions;
   CallOptions.setSExt(true);
-  SplitInteger(TLI.makeLibCall(DAG, LC, VT, Op, CallOptions, dl).first,
-               Lo, Hi);
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, VT, Op,
+                                                    CallOptions, dl, Chain);
+  SplitInteger(Tmp.first, Lo, Hi);
+
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
 }
 
 void DAGTypeLegalizer::ExpandIntRes_FP_TO_UINT(SDNode *N, SDValue &Lo,
@@ -2581,15 +2589,21 @@ void DAGTypeLegalizer::ExpandIntRes_FP_TO_UINT(SDNode *N, SDValue &Lo,
   SDLoc dl(N);
   EVT VT = N->getValueType(0);
 
-  SDValue Op = N->getOperand(0);
+  bool IsStrict = N->isStrictFPOpcode();
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
+  SDValue Op = N->getOperand(IsStrict ? 1 : 0);
   if (getTypeAction(Op.getValueType()) == TargetLowering::TypePromoteFloat)
     Op = GetPromotedFloat(Op);
 
   RTLIB::Libcall LC = RTLIB::getFPTOUINT(Op.getValueType(), VT);
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unexpected fp-to-uint conversion!");
   TargetLowering::MakeLibCallOptions CallOptions;
-  SplitInteger(TLI.makeLibCall(DAG, LC, VT, Op, CallOptions, dl).first,
-               Lo, Hi);
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, VT, Op,
+                                                    CallOptions, dl, Chain);
+  SplitInteger(Tmp.first, Lo, Hi);
+
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
 }
 
 void DAGTypeLegalizer::ExpandIntRes_LLROUND_LLRINT(SDNode *N, SDValue &Lo,
diff --git a/llvm/test/CodeGen/X86/fp-intrinsics.ll b/llvm/test/CodeGen/X86/fp-intrinsics.ll
index 58041c29ab6..011d235c39f 100644
--- a/llvm/test/CodeGen/X86/fp-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/fp-intrinsics.ll
@@ -1087,6 +1087,81 @@ entry:
 ; Verify that fptoui(%x) isn't simplified when the rounding mode is
 ; unknown.
 ; Verify that no gross errors happen.
+define i128 @f20s128(double %x) nounwind strictfp {
+; X87-LABEL: f20s128:
+; X87:       # %bb.0: # %entry
+; X87-NEXT:    pushl %edi
+; X87-NEXT:    pushl %esi
+; X87-NEXT:    subl $36, %esp
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X87-NEXT:    fldl {{[0-9]+}}(%esp)
+; X87-NEXT:    fstpl {{[0-9]+}}(%esp)
+; X87-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X87-NEXT:    movl %eax, (%esp)
+; X87-NEXT:    calll __fixdfti
+; X87-NEXT:    subl $4, %esp
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X87-NEXT:    movl %edi, 8(%esi)
+; X87-NEXT:    movl %edx, 12(%esi)
+; X87-NEXT:    movl %eax, (%esi)
+; X87-NEXT:    movl %ecx, 4(%esi)
+; X87-NEXT:    movl %esi, %eax
+; X87-NEXT:    addl $36, %esp
+; X87-NEXT:    popl %esi
+; X87-NEXT:    popl %edi
+; X87-NEXT:    retl $4
+;
+; X86-SSE-LABEL: f20s128:
+; X86-SSE:       # %bb.0: # %entry
+; X86-SSE-NEXT:    pushl %edi
+; X86-SSE-NEXT:    pushl %esi
+; X86-SSE-NEXT:    subl $36, %esp
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; X86-SSE-NEXT:    movsd %xmm0, {{[0-9]+}}(%esp)
+; X86-SSE-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT:    movl %eax, (%esp)
+; X86-SSE-NEXT:    calll __fixdfti
+; X86-SSE-NEXT:    subl $4, %esp
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-SSE-NEXT:    movl %edi, 8(%esi)
+; X86-SSE-NEXT:    movl %edx, 12(%esi)
+; X86-SSE-NEXT:    movl %eax, (%esi)
+; X86-SSE-NEXT:    movl %ecx, 4(%esi)
+; X86-SSE-NEXT:    movl %esi, %eax
+; X86-SSE-NEXT:    addl $36, %esp
+; X86-SSE-NEXT:    popl %esi
+; X86-SSE-NEXT:    popl %edi
+; X86-SSE-NEXT:    retl $4
+;
+; SSE-LABEL: f20s128:
+; SSE:       # %bb.0: # %entry
+; SSE-NEXT:    pushq %rax
+; SSE-NEXT:    callq __fixdfti
+; SSE-NEXT:    popq %rcx
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: f20s128:
+; AVX:       # %bb.0: # %entry
+; AVX-NEXT:    pushq %rax
+; AVX-NEXT:    callq __fixdfti
+; AVX-NEXT:    popq %rcx
+; AVX-NEXT:    retq
+entry:
+  %result = call i128 @llvm.experimental.constrained.fptosi.i128.f64(double %x,
+                                               metadata !"fpexcept.strict") #0
+  ret i128 %result
+}
+
+; Verify that fptoui(%x) isn't simplified when the rounding mode is
+; unknown.
+; Verify that no gross errors happen.
 ; FIXME: The SSE/AVX code does not raise an invalid exception for all values
 ; that don't fit in i8.
 define i8 @f20u8(double %x) #0 {
@@ -1348,6 +1423,82 @@ entry:
   ret i64 %result
 }
 
+
+; Verify that fptoui(%x) isn't simplified when the rounding mode is
+; unknown.
+; Verify that no gross errors happen.
+define i128 @f20u128(double %x) nounwind strictfp {
+; X87-LABEL: f20u128:
+; X87:       # %bb.0: # %entry
+; X87-NEXT:    pushl %edi
+; X87-NEXT:    pushl %esi
+; X87-NEXT:    subl $36, %esp
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X87-NEXT:    fldl {{[0-9]+}}(%esp)
+; X87-NEXT:    fstpl {{[0-9]+}}(%esp)
+; X87-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X87-NEXT:    movl %eax, (%esp)
+; X87-NEXT:    calll __fixunsdfti
+; X87-NEXT:    subl $4, %esp
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X87-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X87-NEXT:    movl %edi, 8(%esi)
+; X87-NEXT:    movl %edx, 12(%esi)
+; X87-NEXT:    movl %eax, (%esi)
+; X87-NEXT:    movl %ecx, 4(%esi)
+; X87-NEXT:    movl %esi, %eax
+; X87-NEXT:    addl $36, %esp
+; X87-NEXT:    popl %esi
+; X87-NEXT:    popl %edi
+; X87-NEXT:    retl $4
+;
+; X86-SSE-LABEL: f20u128:
+; X86-SSE:       # %bb.0: # %entry
+; X86-SSE-NEXT:    pushl %edi
+; X86-SSE-NEXT:    pushl %esi
+; X86-SSE-NEXT:    subl $36, %esp
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-SSE-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; X86-SSE-NEXT:    movsd %xmm0, {{[0-9]+}}(%esp)
+; X86-SSE-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT:    movl %eax, (%esp)
+; X86-SSE-NEXT:    calll __fixunsdfti
+; X86-SSE-NEXT:    subl $4, %esp
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-SSE-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-SSE-NEXT:    movl %edi, 8(%esi)
+; X86-SSE-NEXT:    movl %edx, 12(%esi)
+; X86-SSE-NEXT:    movl %eax, (%esi)
+; X86-SSE-NEXT:    movl %ecx, 4(%esi)
+; X86-SSE-NEXT:    movl %esi, %eax
+; X86-SSE-NEXT:    addl $36, %esp
+; X86-SSE-NEXT:    popl %esi
+; X86-SSE-NEXT:    popl %edi
+; X86-SSE-NEXT:    retl $4
+;
+; SSE-LABEL: f20u128:
+; SSE:       # %bb.0: # %entry
+; SSE-NEXT:    pushq %rax
+; SSE-NEXT:    callq __fixunsdfti
+; SSE-NEXT:    popq %rcx
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: f20u128:
+; AVX:       # %bb.0: # %entry
+; AVX-NEXT:    pushq %rax
+; AVX-NEXT:    callq __fixunsdfti
+; AVX-NEXT:    popq %rcx
+; AVX-NEXT:    retq
+entry:
+  %result = call i128 @llvm.experimental.constrained.fptoui.i128.f64(double %x,
+                                               metadata !"fpexcept.strict") #0
+  ret i128 %result
+}
+
 ; Verify that round(42.1) isn't simplified when the rounding mode is
 ; unknown.
 ; Verify that no gross errors happen.
@@ -1823,10 +1974,12 @@ declare i8  @llvm.experimental.constrained.fptosi.i8.f64(double, metadata)
 declare i16 @llvm.experimental.constrained.fptosi.i16.f64(double, metadata)
 declare i32 @llvm.experimental.constrained.fptosi.i32.f64(double, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.f64(double, metadata)
+declare i128 @llvm.experimental.constrained.fptosi.i128.f64(double, metadata)
 declare i8  @llvm.experimental.constrained.fptoui.i8.f64(double, metadata)
 declare i16 @llvm.experimental.constrained.fptoui.i16.f64(double, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.f64(double, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.f64(double, metadata)
+declare i128 @llvm.experimental.constrained.fptoui.i128.f64(double, metadata)
 declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)
 declare double @llvm.experimental.constrained.fpext.f64.f32(float, metadata)
 declare i32 @llvm.experimental.constrained.lrint.i32.f64(double, metadata, metadata)
diff --git a/llvm/test/CodeGen/X86/fp128-cast-strict.ll b/llvm/test/CodeGen/X86/fp128-cast-strict.ll
index 99bca70964c..48751e1d9e1 100644
--- a/llvm/test/CodeGen/X86/fp128-cast-strict.ll
+++ b/llvm/test/CodeGen/X86/fp128-cast-strict.ll
@@ -215,6 +215,18 @@ entry:
   ret i64 %conv
 }
 
+define i128 @fptosi_i128(fp128 %x) nounwind strictfp {
+; X64-LABEL: fptosi_i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    pushq %rax
+; X64-NEXT:    callq __fixtfti
+; X64-NEXT:    popq %rcx
+; X64-NEXT:    retq
+entry:
+  %conv = call i128 @llvm.experimental.constrained.fptosi.i128.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i128 %conv
+}
+
 define i8 @fptoui_i8(fp128 %x) nounwind strictfp {
 ; X64-LABEL: fptoui_i8:
 ; X64:       # %bb.0: # %entry
@@ -265,6 +277,18 @@ entry:
   ret i64 %conv
 }
 
+define i128 @fptoui_i128(fp128 %x) nounwind strictfp {
+; X64-LABEL: fptoui_i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    pushq %rax
+; X64-NEXT:    callq __fixunstfti
+; X64-NEXT:    popq %rcx
+; X64-NEXT:    retq
+entry:
+  %conv = call i128 @llvm.experimental.constrained.fptoui.i128.f128(fp128 %x, metadata !"fpexcept.strict") #0
+  ret i128 %conv
+}
+
 attributes #0 = { strictfp }
 
 declare float @llvm.experimental.constrained.fptrunc.f32.f128(fp128, metadata, metadata)
@@ -277,7 +301,9 @@ declare i8 @llvm.experimental.constrained.fptosi.i8.f128(fp128, metadata)
 declare i16 @llvm.experimental.constrained.fptosi.i16.f128(fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptosi.i32.f128(fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptosi.i64.f128(fp128, metadata)
+declare i128 @llvm.experimental.constrained.fptosi.i128.f128(fp128, metadata)
 declare i8 @llvm.experimental.constrained.fptoui.i8.f128(fp128, metadata)
 declare i16 @llvm.experimental.constrained.fptoui.i16.f128(fp128, metadata)
 declare i32 @llvm.experimental.constrained.fptoui.i32.f128(fp128, metadata)
 declare i64 @llvm.experimental.constrained.fptoui.i64.f128(fp128, metadata)
+declare i128 @llvm.experimental.constrained.fptoui.i128.f128(fp128, metadata)