[llvm] b37d593 - [FPEnv][ARM] Add lowering of STRICT_FSETCC and STRICT_FSETCCS
John Brawn via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 3 04:59:43 PST 2020
Author: John Brawn
Date: 2020-02-03T12:59:12Z
New Revision: b37d59353f699e99f139a9227a6a69964ef4b132
URL: https://github.com/llvm/llvm-project/commit/b37d59353f699e99f139a9227a6a69964ef4b132
DIFF: https://github.com/llvm/llvm-project/commit/b37d59353f699e99f139a9227a6a69964ef4b132.diff
LOG: [FPEnv][ARM] Add lowering of STRICT_FSETCC and STRICT_FSETCCS
These can be lowered to code sequences using CMPFP and CMPFPE which then get
selected to VCMP and VCMPE. The implementation isn't fully correct, as the chain
operand isn't handled correctly, but resolving that looks like it would involve
changes around FPSCR-handling instructions and how the FPSCR is modelled.
The fp-intrinsics test was already testing some of this but as the entire test
was being XFAILed it wasn't noticed. Un-XFAIL the test and instead leave the
cases where we aren't generating the right instruction sequences as FIXME.
Differential Revision: https://reviews.llvm.org/D73194
Added:
Modified:
llvm/lib/Target/ARM/ARMISelLowering.cpp
llvm/lib/Target/ARM/ARMISelLowering.h
llvm/lib/Target/ARM/ARMInstrVFP.td
llvm/test/CodeGen/ARM/fp-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index d5cc1e759d84..79dda1d022f7 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -1356,6 +1356,14 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FP16_TO_FP, MVT::f32, Expand);
setOperationAction(ISD::FP_TO_FP16, MVT::f32, Expand);
}
+
+ // Strict floating-point comparisons need custom lowering.
+ setOperationAction(ISD::STRICT_FSETCC, MVT::f16, Custom);
+ setOperationAction(ISD::STRICT_FSETCCS, MVT::f16, Custom);
+ setOperationAction(ISD::STRICT_FSETCC, MVT::f32, Custom);
+ setOperationAction(ISD::STRICT_FSETCCS, MVT::f32, Custom);
+ setOperationAction(ISD::STRICT_FSETCC, MVT::f64, Custom);
+ setOperationAction(ISD::STRICT_FSETCCS, MVT::f64, Custom);
}
// Use __sincos_stret if available.
@@ -1554,7 +1562,9 @@ const char *ARMTargetLowering::getTargetNodeName(unsigned Opcode) const {
case ARMISD::CMN: return "ARMISD::CMN";
case ARMISD::CMPZ: return "ARMISD::CMPZ";
case ARMISD::CMPFP: return "ARMISD::CMPFP";
+ case ARMISD::CMPFPE: return "ARMISD::CMPFPE";
case ARMISD::CMPFPw0: return "ARMISD::CMPFPw0";
+ case ARMISD::CMPFPEw0: return "ARMISD::CMPFPEw0";
case ARMISD::BCC_i64: return "ARMISD::BCC_i64";
case ARMISD::FMSTAT: return "ARMISD::FMSTAT";
@@ -4353,13 +4363,16 @@ SDValue ARMTargetLowering::getARMCmp(SDValue LHS, SDValue RHS, ISD::CondCode CC,
/// Returns a appropriate VFP CMP (fcmp{s|d}+fmstat) for the given operands.
SDValue ARMTargetLowering::getVFPCmp(SDValue LHS, SDValue RHS,
- SelectionDAG &DAG, const SDLoc &dl) const {
+ SelectionDAG &DAG, const SDLoc &dl,
+ bool Signaling) const {
assert(Subtarget->hasFP64() || RHS.getValueType() != MVT::f64);
SDValue Cmp;
if (!isFloatingPointZero(RHS))
- Cmp = DAG.getNode(ARMISD::CMPFP, dl, MVT::Glue, LHS, RHS);
+ Cmp = DAG.getNode(Signaling ? ARMISD::CMPFPE : ARMISD::CMPFP,
+ dl, MVT::Glue, LHS, RHS);
else
- Cmp = DAG.getNode(ARMISD::CMPFPw0, dl, MVT::Glue, LHS);
+ Cmp = DAG.getNode(Signaling ? ARMISD::CMPFPEw0 : ARMISD::CMPFPw0,
+ dl, MVT::Glue, LHS);
return DAG.getNode(ARMISD::FMSTAT, dl, MVT::Glue, Cmp);
}
@@ -9277,6 +9290,51 @@ static void ReplaceCMP_SWAP_64Results(SDNode *N,
Results.push_back(SDValue(CmpSwap, 2));
}
+SDValue ARMTargetLowering::LowerFSETCC(SDValue Op, SelectionDAG &DAG) const {
+ SDLoc dl(Op);
+ EVT VT = Op.getValueType();
+ SDValue Chain = Op.getOperand(0);
+ SDValue LHS = Op.getOperand(1);
+ SDValue RHS = Op.getOperand(2);
+ ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(3))->get();
+ bool IsSignaling = Op.getOpcode() == ISD::STRICT_FSETCCS;
+
+ // If we don't have instructions of this float type then soften to a libcall
+ // and use SETCC instead.
+ if (isUnsupportedFloatingType(LHS.getValueType())) {
+ DAG.getTargetLoweringInfo().softenSetCCOperands(
+ DAG, LHS.getValueType(), LHS, RHS, CC, dl, LHS, RHS, Chain, IsSignaling);
+ if (!RHS.getNode()) {
+ RHS = DAG.getConstant(0, dl, LHS.getValueType());
+ CC = ISD::SETNE;
+ }
+ SDValue Result = DAG.getNode(ISD::SETCC, dl, VT, LHS, RHS,
+ DAG.getCondCode(CC));
+ return DAG.getMergeValues({Result, Chain}, dl);
+ }
+
+ ARMCC::CondCodes CondCode, CondCode2;
+ FPCCToARMCC(CC, CondCode, CondCode2);
+
+ // FIXME: Chain is not handled correctly here. Currently the FPSCR is implicit
+ // in CMPFP and CMPFPE, but instead it should be made explicit by these
+ // instructions using a chain instead of glue. This would also fix the problem
+ // here (and also in LowerSELECT_CC) where we generate two comparisons when
+ // CondCode2 != AL.
+ SDValue True = DAG.getConstant(1, dl, VT);
+ SDValue False = DAG.getConstant(0, dl, VT);
+ SDValue ARMcc = DAG.getConstant(CondCode, dl, MVT::i32);
+ SDValue CCR = DAG.getRegister(ARM::CPSR, MVT::i32);
+ SDValue Cmp = getVFPCmp(LHS, RHS, DAG, dl, IsSignaling);
+ SDValue Result = getCMOV(dl, VT, False, True, ARMcc, CCR, Cmp, DAG);
+ if (CondCode2 != ARMCC::AL) {
+ ARMcc = DAG.getConstant(CondCode2, dl, MVT::i32);
+ Cmp = getVFPCmp(LHS, RHS, DAG, dl, IsSignaling);
+ Result = getCMOV(dl, VT, Result, True, ARMcc, CCR, Cmp, DAG);
+ }
+ return DAG.getMergeValues({Result, Chain}, dl);
+}
+
SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
LLVM_DEBUG(dbgs() << "Lowering node: "; Op.dump());
switch (Op.getOpcode()) {
@@ -9370,6 +9428,8 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::FP_ROUND: return LowerFP_ROUND(Op, DAG);
case ISD::STRICT_FP_EXTEND:
case ISD::FP_EXTEND: return LowerFP_EXTEND(Op, DAG);
+ case ISD::STRICT_FSETCC:
+ case ISD::STRICT_FSETCCS: return LowerFSETCC(Op, DAG);
case ARMISD::WIN__DBZCHK: return SDValue();
}
}
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.h b/llvm/lib/Target/ARM/ARMISelLowering.h
index 57817549d745..3b5a3793ade0 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.h
+++ b/llvm/lib/Target/ARM/ARMISelLowering.h
@@ -84,7 +84,9 @@ class VectorType;
CMN, // ARM CMN instructions.
CMPZ, // ARM compare that sets only Z flag.
CMPFP, // ARM VFP compare instruction, sets FPSCR.
+ CMPFPE, // ARM VFP signalling compare instruction, sets FPSCR.
CMPFPw0, // ARM VFP compare against zero instruction, sets FPSCR.
+ CMPFPEw0, // ARM VFP signalling compare against zero instruction, sets FPSCR.
FMSTAT, // ARM fmstat instruction.
CMOV, // ARM conditional move instructions.
@@ -731,6 +733,7 @@ class VectorType;
SDValue LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerFSETCC(SDValue Op, SelectionDAG &DAG) const;
void lowerABS(SDNode *N, SmallVectorImpl<SDValue> &Results,
SelectionDAG &DAG) const;
void LowerLOAD(SDNode *N, SmallVectorImpl<SDValue> &Results,
@@ -821,7 +824,7 @@ class VectorType;
SDValue getARMCmp(SDValue LHS, SDValue RHS, ISD::CondCode CC,
SDValue &ARMcc, SelectionDAG &DAG, const SDLoc &dl) const;
SDValue getVFPCmp(SDValue LHS, SDValue RHS, SelectionDAG &DAG,
- const SDLoc &dl) const;
+ const SDLoc &dl, bool Signaling = false) const;
SDValue duplicateCmp(SDValue Cmp, SelectionDAG &DAG) const;
SDValue OptimizeVFPBrcond(SDValue Op, SelectionDAG &DAG) const;
diff --git a/llvm/lib/Target/ARM/ARMInstrVFP.td b/llvm/lib/Target/ARM/ARMInstrVFP.td
index a41a483d1a4c..f1d1d8a89164 100644
--- a/llvm/lib/Target/ARM/ARMInstrVFP.td
+++ b/llvm/lib/Target/ARM/ARMInstrVFP.td
@@ -21,6 +21,8 @@ def SDT_VMOVSR : SDTypeProfile<1, 1, [SDTCisVT<0, f32>, SDTCisVT<1, i32>]>;
def arm_fmstat : SDNode<"ARMISD::FMSTAT", SDTNone, [SDNPInGlue, SDNPOutGlue]>;
def arm_cmpfp : SDNode<"ARMISD::CMPFP", SDT_ARMCmp, [SDNPOutGlue]>;
def arm_cmpfp0 : SDNode<"ARMISD::CMPFPw0", SDT_CMPFP0, [SDNPOutGlue]>;
+def arm_cmpfpe : SDNode<"ARMISD::CMPFPE", SDT_ARMCmp, [SDNPOutGlue]>;
+def arm_cmpfpe0: SDNode<"ARMISD::CMPFPEw0",SDT_CMPFP0, [SDNPOutGlue]>;
def arm_fmdrr : SDNode<"ARMISD::VMOVDRR", SDT_VMOVDRR>;
def arm_fmrrd : SDNode<"ARMISD::VMOVRRD", SDT_VMOVRRD>;
def arm_vmovsr : SDNode<"ARMISD::VMOVSR", SDT_VMOVSR>;
@@ -548,12 +550,12 @@ let Defs = [FPSCR_NZCV] in {
def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins DPR:$Dd, DPR:$Dm),
IIC_fpCMP64, "vcmpe", ".f64\t$Dd, $Dm",
- [/* For disassembly only; pattern left blank */]>;
+ [(arm_cmpfpe DPR:$Dd, (f64 DPR:$Dm))]>;
def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins SPR:$Sd, SPR:$Sm),
IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm",
- [/* For disassembly only; pattern left blank */]> {
+ [(arm_cmpfpe SPR:$Sd, SPR:$Sm)]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
@@ -562,7 +564,7 @@ def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0,
def VCMPEH : AHuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins HPR:$Sd, HPR:$Sm),
IIC_fpCMP16, "vcmpe", ".f16\t$Sd, $Sm",
- [/* For disassembly only; pattern left blank */]>;
+ [(arm_cmpfpe HPR:$Sd, HPR:$Sm)]>;
def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0,
(outs), (ins DPR:$Dd, DPR:$Dm),
@@ -611,7 +613,7 @@ let Defs = [FPSCR_NZCV] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins DPR:$Dd),
IIC_fpCMP64, "vcmpe", ".f64\t$Dd, #0",
- [/* For disassembly only; pattern left blank */]> {
+ [(arm_cmpfpe0 (f64 DPR:$Dd))]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
@@ -619,7 +621,7 @@ def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins SPR:$Sd),
IIC_fpCMP32, "vcmpe", ".f32\t$Sd, #0",
- [/* For disassembly only; pattern left blank */]> {
+ [(arm_cmpfpe0 SPR:$Sd)]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
@@ -631,7 +633,7 @@ def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0,
def VCMPEZH : AHuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins HPR:$Sd),
IIC_fpCMP16, "vcmpe", ".f16\t$Sd, #0",
- [/* For disassembly only; pattern left blank */]> {
+ [(arm_cmpfpe0 HPR:$Sd)]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
diff --git a/llvm/test/CodeGen/ARM/fp-intrinsics.ll b/llvm/test/CodeGen/ARM/fp-intrinsics.ll
index 9a15a626e28b..4352548ef3c8 100644
--- a/llvm/test/CodeGen/ARM/fp-intrinsics.ll
+++ b/llvm/test/CodeGen/ARM/fp-intrinsics.ll
@@ -8,9 +8,8 @@
; hardware being present or absent work as expected (i.e. we get an instruction
; when one is available, otherwise a libcall).
-; FIXME: Tests fails as various things in CodeGen and Target/ARM need fixing.
-; XFAIL: *
-
+; FIXME: We're not generating the right instructions for some of these
+; operations (see further FIXMEs down below).
; Single-precision intrinsics
@@ -71,7 +70,7 @@ define i32 @fptosi_f32(float %x) #0 {
; CHECK-LABEL: fptoui_f32:
; CHECK-NOSP: bl __aeabi_f2uiz
-; CHECK-SP: vcvt.u32.f32
+; FIXME-CHECK-SP: vcvt.u32.f32
define i32 @fptoui_f32(float %x) #0 {
%val = call i32 @llvm.experimental.constrained.fptoui.f32(float %x, metadata !"fpexcept.strict") #0
ret i32 %val
@@ -240,6 +239,226 @@ define float @trunc_f32(float %x) #0 {
ret float %val
}
+; CHECK-LABEL: fcmp_olt_f32:
+; CHECK-NOSP: bl __aeabi_fcmplt
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_olt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"olt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ole_f32:
+; CHECK-NOSP: bl __aeabi_fcmple
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ole_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ole", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ogt_f32:
+; CHECK-NOSP: bl __aeabi_fcmpgt
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ogt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ogt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_oge_f32:
+; CHECK-NOSP: bl __aeabi_fcmpge
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_oge_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"oge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_oeq_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_oeq_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"oeq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_one_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-NOSP: bl __aeabi_fcmpun
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_one_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"one", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ult_f32:
+; CHECK-NOSP: bl __aeabi_fcmpge
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ult_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ult", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ule_f32:
+; CHECK-NOSP: bl __aeabi_fcmpgt
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ule_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ule", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ugt_f32:
+; CHECK-NOSP: bl __aeabi_fcmple
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ugt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ugt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_uge_f32:
+; CHECK-NOSP: bl __aeabi_fcmplt
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_uge_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"uge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ueq_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-NOSP: bl __aeabi_fcmpun
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_ueq_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ueq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_une_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-SP: vcmp.f32
+define i32 @fcmp_une_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"une", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_olt_f32:
+; CHECK-NOSP: bl __aeabi_fcmplt
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_olt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"olt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ole_f32:
+; CHECK-NOSP: bl __aeabi_fcmple
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ole_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ole", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ogt_f32:
+; CHECK-NOSP: bl __aeabi_fcmpgt
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ogt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ogt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_oge_f32:
+; CHECK-NOSP: bl __aeabi_fcmpge
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_oge_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"oge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_oeq_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_oeq_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"oeq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_one_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-NOSP: bl __aeabi_fcmpun
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_one_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"one", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ult_f32:
+; CHECK-NOSP: bl __aeabi_fcmpge
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ult_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ult", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ule_f32:
+; CHECK-NOSP: bl __aeabi_fcmpgt
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ule_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ule", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ugt_f32:
+; CHECK-NOSP: bl __aeabi_fcmple
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ugt_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ugt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_uge_f32:
+; CHECK-NOSP: bl __aeabi_fcmplt
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_uge_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"uge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ueq_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-NOSP: bl __aeabi_fcmpun
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_ueq_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ueq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_une_f32:
+; CHECK-NOSP: bl __aeabi_fcmpeq
+; CHECK-SP: vcmpe.f32
+define i32 @fcmps_une_f32(float %a, float %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"une", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
; Double-precision intrinsics
@@ -300,7 +519,7 @@ define i32 @fptosi_f64(double %x) #0 {
; CHECK-LABEL: fptoui_f64:
; CHECK-NODP: bl __aeabi_d2uiz
-; CHECK-DP: vcvt.u32.f64
+; FIXME-CHECK-DP: vcvt.u32.f64
define i32 @fptoui_f64(double %x) #0 {
%val = call i32 @llvm.experimental.constrained.fptoui.f64(double %x, metadata !"fpexcept.strict") #0
ret i32 %val
@@ -469,6 +688,226 @@ define double @trunc_f64(double %x) #0 {
ret double %val
}
+; CHECK-LABEL: fcmp_olt_f64:
+; CHECK-NODP: bl __aeabi_dcmplt
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_olt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"olt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ole_f64:
+; CHECK-NODP: bl __aeabi_dcmple
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ole_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ole", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ogt_f64:
+; CHECK-NODP: bl __aeabi_dcmpgt
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ogt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ogt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_oge_f64:
+; CHECK-NODP: bl __aeabi_dcmpge
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_oge_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"oge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_oeq_f64:
+; CHECK-NODP: bl __aeabi_dcmpeq
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_oeq_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"oeq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_one_f64:
+; CHECK-NODP-DAG: bl __aeabi_dcmpeq
+; CHECK-NODP-DAG: bl __aeabi_dcmpun
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_one_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"one", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ult_f64:
+; CHECK-NODP: bl __aeabi_dcmpge
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ult_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ult", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ule_f64:
+; CHECK-NODP: bl __aeabi_dcmpgt
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ule_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ule", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ugt_f64:
+; CHECK-NODP: bl __aeabi_dcmple
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ugt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ugt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_uge_f64:
+; CHECK-NODP: bl __aeabi_dcmplt
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_uge_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"uge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_ueq_f64:
+; CHECK-NODP-DAG: bl __aeabi_dcmpeq
+; CHECK-NODP-DAG: bl __aeabi_dcmpun
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_ueq_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ueq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmp_une_f64:
+; CHECK-NODP: bl __aeabi_dcmpeq
+; CHECK-DP: vcmp.f64
+define i32 @fcmp_une_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"une", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_olt_f64:
+; CHECK-NODP: bl __aeabi_dcmplt
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_olt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"olt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ole_f64:
+; CHECK-NODP: bl __aeabi_dcmple
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ole_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ole", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ogt_f64:
+; CHECK-NODP: bl __aeabi_dcmpgt
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ogt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ogt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_oge_f64:
+; CHECK-NODP: bl __aeabi_dcmpge
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_oge_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"oge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_oeq_f64:
+; CHECK-NODP: bl __aeabi_dcmpeq
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_oeq_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"oeq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_one_f64:
+; CHECK-NODP-DAG: bl __aeabi_dcmpeq
+; CHECK-NODP-DAG: bl __aeabi_dcmpun
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_one_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"one", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ult_f64:
+; CHECK-NODP: bl __aeabi_dcmpge
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ult_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ult", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ule_f64:
+; CHECK-NODP: bl __aeabi_dcmpgt
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ule_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ule", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ugt_f64:
+; CHECK-NODP: bl __aeabi_dcmple
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ugt_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ugt", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_uge_f64:
+; CHECK-NODP: bl __aeabi_dcmplt
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_uge_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"uge", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_ueq_f64:
+; CHECK-NODP-DAG: bl __aeabi_dcmpeq
+; CHECK-NODP-DAG: bl __aeabi_dcmpun
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_ueq_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ueq", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
+; CHECK-LABEL: fcmps_une_f64:
+; CHECK-NODP: bl __aeabi_dcmpeq
+; CHECK-DP: vcmpe.f64
+define i32 @fcmps_une_f64(double %a, double %b) #0 {
+ %cmp = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"une", metadata !"fpexcept.strict") #0
+ %conv = zext i1 %cmp to i32
+ ret i32 %conv
+}
+
; Single/Double conversion intrinsics
@@ -490,15 +929,15 @@ define double @fpext_f32(float %x) #0 {
; CHECK-LABEL: sitofp_f32_i32:
; CHECK-NOSP: bl __aeabi_i2f
-; CHECK-SP: vcvt.f32.s32
+; FIXME-CHECK-SP: vcvt.f32.s32
define float @sitofp_f32_i32(i32 %x) #0 {
%val = call float @llvm.experimental.constrained.sitofp.f32.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
ret float %val
}
; CHECK-LABEL: sitofp_f64_i32:
-; CHECK-NODP: bl __aeabi_i2d
-; CHECK-DP: vcvt.f64.s32
+; FIXME-CHECK-NODP: bl __aeabi_i2d
+; FIXME-CHECK-DP: vcvt.f64.s32
define double @sitofp_f64_i32(i32 %x) #0 {
%val = call double @llvm.experimental.constrained.sitofp.f64.i32(i32 %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
ret double %val
@@ -537,6 +976,8 @@ declare i32 @llvm.experimental.constrained.lround.f32(float, metadata)
declare i32 @llvm.experimental.constrained.llround.f32(float, metadata)
declare float @llvm.experimental.constrained.round.f32(float, metadata)
declare float @llvm.experimental.constrained.trunc.f32(float, metadata)
+declare i1 @llvm.experimental.constrained.fcmps.f32(float, float, metadata, metadata)
+declare i1 @llvm.experimental.constrained.fcmp.f32(float, float, metadata, metadata)
declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.fsub.f64(double, double, metadata, metadata)
@@ -568,6 +1009,8 @@ declare i32 @llvm.experimental.constrained.lround.f64(double, metadata)
declare i32 @llvm.experimental.constrained.llround.f64(double, metadata)
declare double @llvm.experimental.constrained.round.f64(double, metadata)
declare double @llvm.experimental.constrained.trunc.f64(double, metadata)
+declare i1 @llvm.experimental.constrained.fcmps.f64(double, double, metadata, metadata)
+declare i1 @llvm.experimental.constrained.fcmp.f64(double, double, metadata, metadata)
declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.fpext.f64.f32(float, metadata)
More information about the llvm-commits
mailing list