forked from OSchip/llvm-project
Use vAny type to get rid of Neon intrinsics that differed only in whether
the overloaded vector types allowed floating-point or integer vector elements. Most of these operations actually depend on the element type, so bitcasting was not an option. If you include the vpadd intrinsics that I updated earlier, this gets rid of 20 intrinsics. llvm-svn: 78646
This commit is contained in:
Bob Wilson
parent
a16548e301
commit
12842f9865
|
|
@ -27,53 +27,42 @@ let TargetPrefix = "arm" in { // All intrinsics start with "llvm.arm.".
|
|||
|
||||
// The following classes do not correspond directly to GCC builtins.
|
||||
class Neon_1Arg_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
||||
class Neon_1Arg_Float_Intrinsic
|
||||
: Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
||||
: Intrinsic<[llvm_anyvector_ty], [LLVMMatchType<0>], [IntrNoMem]>;
|
||||
class Neon_1Arg_Narrow_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMExtendedElementVectorType<0>], [IntrNoMem]>;
|
||||
class Neon_1Arg_Long_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMTruncatedElementVectorType<0>], [IntrNoMem]>;
|
||||
class Neon_2Arg_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Arg_Float_Intrinsic
|
||||
: Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Arg_Vector_Intrinsic
|
||||
: Intrinsic<[llvm_anyvector_ty], [LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Arg_Narrow_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMExtendedElementVectorType<0>,
|
||||
LLVMExtendedElementVectorType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Arg_Long_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMTruncatedElementVectorType<0>,
|
||||
LLVMTruncatedElementVectorType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Arg_Wide_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMMatchType<0>, LLVMTruncatedElementVectorType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_3Arg_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_3Arg_Long_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty],
|
||||
: Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMMatchType<0>,
|
||||
LLVMTruncatedElementVectorType<0>,
|
||||
LLVMTruncatedElementVectorType<0>],
|
||||
[IntrNoMem]>;
|
||||
class Neon_2Result_Intrinsic
|
||||
: Intrinsic<[llvm_anyint_ty, LLVMMatchType<0>],
|
||||
[LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
|
||||
class Neon_2Result_Float_Intrinsic
|
||||
: Intrinsic<[llvm_anyfloat_ty, LLVMMatchType<0>],
|
||||
: Intrinsic<[llvm_anyvector_ty, LLVMMatchType<0>],
|
||||
[LLVMMatchType<0>, LLVMMatchType<0>], [IntrNoMem]>;
|
||||
class Neon_CvtFxToFP_Intrinsic
|
||||
: Intrinsic<[llvm_anyfloat_ty], [llvm_anyint_ty, llvm_i32_ty], [IntrNoMem]>;
|
||||
|
|
@ -141,18 +130,16 @@ let Properties = [IntrNoMem, Commutative] in {
|
|||
// Vector Maximum.
|
||||
def int_arm_neon_vmaxs : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vmaxu : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vmaxf : Neon_2Arg_Float_Intrinsic;
|
||||
|
||||
// Vector Minimum.
|
||||
def int_arm_neon_vmins : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vminu : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vminf : Neon_2Arg_Float_Intrinsic;
|
||||
|
||||
// Vector Reciprocal Step.
|
||||
def int_arm_neon_vrecps : Neon_2Arg_Float_Intrinsic;
|
||||
def int_arm_neon_vrecps : Neon_2Arg_Intrinsic;
|
||||
|
||||
// Vector Reciprocal Square Root Step.
|
||||
def int_arm_neon_vrsqrts : Neon_2Arg_Float_Intrinsic;
|
||||
def int_arm_neon_vrsqrts : Neon_2Arg_Intrinsic;
|
||||
}
|
||||
|
||||
// Vector Subtract.
|
||||
|
|
@ -186,7 +173,6 @@ let TargetPrefix = "arm" in {
|
|||
// Vector Absolute Differences.
|
||||
def int_arm_neon_vabds : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vabdu : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vabdf : Neon_2Arg_Float_Intrinsic;
|
||||
def int_arm_neon_vabdls : Neon_2Arg_Long_Intrinsic;
|
||||
def int_arm_neon_vabdlu : Neon_2Arg_Long_Intrinsic;
|
||||
|
||||
|
|
@ -197,16 +183,16 @@ def int_arm_neon_vabals : Neon_3Arg_Long_Intrinsic;
|
|||
def int_arm_neon_vabalu : Neon_3Arg_Long_Intrinsic;
|
||||
|
||||
// Vector Pairwise Add.
|
||||
def int_arm_neon_vpadd : Neon_2Arg_Vector_Intrinsic;
|
||||
def int_arm_neon_vpadd : Neon_2Arg_Intrinsic;
|
||||
|
||||
// Vector Pairwise Add Long.
|
||||
// Note: This is different than the other "long" NEON intrinsics because
|
||||
// the result vector has half as many elements as the source vector.
|
||||
// The source and destination vector types must be specified separately.
|
||||
let TargetPrefix = "arm" in {
|
||||
def int_arm_neon_vpaddls : Intrinsic<[llvm_anyint_ty], [llvm_anyint_ty],
|
||||
def int_arm_neon_vpaddls : Intrinsic<[llvm_anyvector_ty], [llvm_anyvector_ty],
|
||||
[IntrNoMem]>;
|
||||
def int_arm_neon_vpaddlu : Intrinsic<[llvm_anyint_ty], [llvm_anyint_ty],
|
||||
def int_arm_neon_vpaddlu : Intrinsic<[llvm_anyvector_ty], [llvm_anyvector_ty],
|
||||
[IntrNoMem]>;
|
||||
}
|
||||
|
||||
|
|
@ -214,21 +200,19 @@ let TargetPrefix = "arm" in {
|
|||
// Note: This is similar to vpaddl but the destination vector also appears
|
||||
// as the first argument.
|
||||
let TargetPrefix = "arm" in {
|
||||
def int_arm_neon_vpadals : Intrinsic<[llvm_anyint_ty],
|
||||
[LLVMMatchType<0>, llvm_anyint_ty],
|
||||
def int_arm_neon_vpadals : Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMMatchType<0>, llvm_anyvector_ty],
|
||||
[IntrNoMem]>;
|
||||
def int_arm_neon_vpadalu : Intrinsic<[llvm_anyint_ty],
|
||||
[LLVMMatchType<0>, llvm_anyint_ty],
|
||||
def int_arm_neon_vpadalu : Intrinsic<[llvm_anyvector_ty],
|
||||
[LLVMMatchType<0>, llvm_anyvector_ty],
|
||||
[IntrNoMem]>;
|
||||
}
|
||||
|
||||
// Vector Pairwise Maximum and Minimum.
|
||||
def int_arm_neon_vpmaxs : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vpmaxu : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vpmaxf : Neon_2Arg_Float_Intrinsic;
|
||||
def int_arm_neon_vpmins : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vpminu : Neon_2Arg_Intrinsic;
|
||||
def int_arm_neon_vpminf : Neon_2Arg_Float_Intrinsic;
|
||||
|
||||
// Vector Shifts:
|
||||
//
|
||||
|
|
@ -283,7 +267,6 @@ def int_arm_neon_vshiftins : Neon_3Arg_Intrinsic;
|
|||
|
||||
// Vector Absolute Value and Saturating Absolute Value.
|
||||
def int_arm_neon_vabs : Neon_1Arg_Intrinsic;
|
||||
def int_arm_neon_vabsf : Neon_1Arg_Float_Intrinsic;
|
||||
def int_arm_neon_vqabs : Neon_1Arg_Intrinsic;
|
||||
|
||||
// Vector Saturating Negate.
|
||||
|
|
@ -298,11 +281,9 @@ def int_arm_neon_vcnt : Neon_1Arg_Intrinsic;
|
|||
|
||||
// Vector Reciprocal Estimate.
|
||||
def int_arm_neon_vrecpe : Neon_1Arg_Intrinsic;
|
||||
def int_arm_neon_vrecpef : Neon_1Arg_Float_Intrinsic;
|
||||
|
||||
// Vector Reciprocal Square Root Estimate.
|
||||
def int_arm_neon_vrsqrte : Neon_1Arg_Intrinsic;
|
||||
def int_arm_neon_vrsqrtef : Neon_1Arg_Float_Intrinsic;
|
||||
|
||||
// Vector Conversions Between Floating-point and Fixed-point.
|
||||
def int_arm_neon_vcvtfp2fxs : Neon_CvtFPToFx_Intrinsic;
|
||||
|
|
@ -331,68 +312,41 @@ def int_arm_neon_vtbx3 : Neon_Tbl5Arg_Intrinsic;
|
|||
def int_arm_neon_vtbx4 : Neon_Tbl6Arg_Intrinsic;
|
||||
|
||||
// Vector Transpose.
|
||||
def int_arm_neon_vtrni : Neon_2Result_Intrinsic;
|
||||
def int_arm_neon_vtrnf : Neon_2Result_Float_Intrinsic;
|
||||
def int_arm_neon_vtrn : Neon_2Result_Intrinsic;
|
||||
|
||||
// Vector Interleave (vzip).
|
||||
def int_arm_neon_vzipi : Neon_2Result_Intrinsic;
|
||||
def int_arm_neon_vzipf : Neon_2Result_Float_Intrinsic;
|
||||
def int_arm_neon_vzip : Neon_2Result_Intrinsic;
|
||||
|
||||
// Vector Deinterleave (vuzp).
|
||||
def int_arm_neon_vuzpi : Neon_2Result_Intrinsic;
|
||||
def int_arm_neon_vuzpf : Neon_2Result_Float_Intrinsic;
|
||||
def int_arm_neon_vuzp : Neon_2Result_Intrinsic;
|
||||
|
||||
let TargetPrefix = "arm" in {
|
||||
|
||||
// De-interleaving vector loads from N-element structures.
|
||||
def int_arm_neon_vld1i : Intrinsic<[llvm_anyint_ty],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld1f : Intrinsic<[llvm_anyfloat_ty],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld2i : Intrinsic<[llvm_anyint_ty, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld2f : Intrinsic<[llvm_anyfloat_ty, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld3i : Intrinsic<[llvm_anyint_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld3f : Intrinsic<[llvm_anyfloat_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld4i : Intrinsic<[llvm_anyint_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld4f : Intrinsic<[llvm_anyfloat_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld1 : Intrinsic<[llvm_anyvector_ty],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld2 : Intrinsic<[llvm_anyvector_ty, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld3 : Intrinsic<[llvm_anyvector_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
def int_arm_neon_vld4 : Intrinsic<[llvm_anyvector_ty, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[llvm_ptr_ty], [IntrReadArgMem]>;
|
||||
|
||||
// Interleaving vector stores from N-element structures.
|
||||
def int_arm_neon_vst1i : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyint_ty],
|
||||
def int_arm_neon_vst1 : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyvector_ty],
|
||||
[IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst2 : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyvector_ty,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst3 : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyvector_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst1f : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyfloat_ty],
|
||||
[IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst2i : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyint_ty,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst2f : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyfloat_ty,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst3i : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyint_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst3f : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyfloat_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>],
|
||||
[IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst4i : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyint_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst4f : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyfloat_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
def int_arm_neon_vst4 : Intrinsic<[llvm_void_ty],
|
||||
[llvm_ptr_ty, llvm_anyvector_ty,
|
||||
LLVMMatchType<0>, LLVMMatchType<0>,
|
||||
LLVMMatchType<0>], [IntrWriteArgMem]>;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1466,8 +1466,7 @@ SDNode *ARMDAGToDAGISel::Select(SDValue Op) {
|
|||
switch (IntNo) {
|
||||
default: break;
|
||||
|
||||
case Intrinsic::arm_neon_vtrni:
|
||||
case Intrinsic::arm_neon_vtrnf:
|
||||
case Intrinsic::arm_neon_vtrn:
|
||||
switch (VT.getSimpleVT()) {
|
||||
default: return NULL;
|
||||
case EVT::v8i8: Opc = ARM::VTRNd8; break;
|
||||
|
|
@ -1482,8 +1481,7 @@ SDNode *ARMDAGToDAGISel::Select(SDValue Op) {
|
|||
return CurDAG->getTargetNode(Opc, dl, VT, VT, N->getOperand(1),
|
||||
N->getOperand(2));
|
||||
|
||||
case Intrinsic::arm_neon_vuzpi:
|
||||
case Intrinsic::arm_neon_vuzpf:
|
||||
case Intrinsic::arm_neon_vuzp:
|
||||
switch (VT.getSimpleVT()) {
|
||||
default: return NULL;
|
||||
case EVT::v8i8: Opc = ARM::VUZPd8; break;
|
||||
|
|
@ -1498,8 +1496,7 @@ SDNode *ARMDAGToDAGISel::Select(SDValue Op) {
|
|||
return CurDAG->getTargetNode(Opc, dl, VT, VT, N->getOperand(1),
|
||||
N->getOperand(2));
|
||||
|
||||
case Intrinsic::arm_neon_vzipi:
|
||||
case Intrinsic::arm_neon_vzipf:
|
||||
case Intrinsic::arm_neon_vzip:
|
||||
switch (VT.getSimpleVT()) {
|
||||
default: return NULL;
|
||||
case EVT::v8i8: Opc = ARM::VZIPd8; break;
|
||||
|
|
|
|||
|
|
@ -1360,23 +1360,17 @@ SDValue
|
|||
ARMTargetLowering::LowerINTRINSIC_W_CHAIN(SDValue Op, SelectionDAG &DAG) {
|
||||
unsigned IntNo = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue();
|
||||
switch (IntNo) {
|
||||
case Intrinsic::arm_neon_vld2i:
|
||||
case Intrinsic::arm_neon_vld2f:
|
||||
case Intrinsic::arm_neon_vld2:
|
||||
return LowerNeonVLDIntrinsic(Op, DAG, ARMISD::VLD2D);
|
||||
case Intrinsic::arm_neon_vld3i:
|
||||
case Intrinsic::arm_neon_vld3f:
|
||||
case Intrinsic::arm_neon_vld3:
|
||||
return LowerNeonVLDIntrinsic(Op, DAG, ARMISD::VLD3D);
|
||||
case Intrinsic::arm_neon_vld4i:
|
||||
case Intrinsic::arm_neon_vld4f:
|
||||
case Intrinsic::arm_neon_vld4:
|
||||
return LowerNeonVLDIntrinsic(Op, DAG, ARMISD::VLD4D);
|
||||
case Intrinsic::arm_neon_vst2i:
|
||||
case Intrinsic::arm_neon_vst2f:
|
||||
case Intrinsic::arm_neon_vst2:
|
||||
return LowerNeonVSTIntrinsic(Op, DAG, ARMISD::VST2D, 2);
|
||||
case Intrinsic::arm_neon_vst3i:
|
||||
case Intrinsic::arm_neon_vst3f:
|
||||
case Intrinsic::arm_neon_vst3:
|
||||
return LowerNeonVSTIntrinsic(Op, DAG, ARMISD::VST3D, 3);
|
||||
case Intrinsic::arm_neon_vst4i:
|
||||
case Intrinsic::arm_neon_vst4f:
|
||||
case Intrinsic::arm_neon_vst4:
|
||||
return LowerNeonVSTIntrinsic(Op, DAG, ARMISD::VST4D, 4);
|
||||
default: return SDValue(); // Don't custom lower most intrinsics.
|
||||
}
|
||||
|
|
|
|||
|
|
@ -173,17 +173,17 @@ class VLD1Q<string OpcodeStr, ValueType Ty, Intrinsic IntOp>
|
|||
!strconcat(OpcodeStr, "\t${dst:dregpair}, $addr"),
|
||||
[(set QPR:$dst, (Ty (IntOp addrmode6:$addr)))]>;
|
||||
|
||||
def VLD1d8 : VLD1D<"vld1.8", v8i8, int_arm_neon_vld1i>;
|
||||
def VLD1d16 : VLD1D<"vld1.16", v4i16, int_arm_neon_vld1i>;
|
||||
def VLD1d32 : VLD1D<"vld1.32", v2i32, int_arm_neon_vld1i>;
|
||||
def VLD1df : VLD1D<"vld1.32", v2f32, int_arm_neon_vld1f>;
|
||||
def VLD1d64 : VLD1D<"vld1.64", v1i64, int_arm_neon_vld1i>;
|
||||
def VLD1d8 : VLD1D<"vld1.8", v8i8, int_arm_neon_vld1>;
|
||||
def VLD1d16 : VLD1D<"vld1.16", v4i16, int_arm_neon_vld1>;
|
||||
def VLD1d32 : VLD1D<"vld1.32", v2i32, int_arm_neon_vld1>;
|
||||
def VLD1df : VLD1D<"vld1.32", v2f32, int_arm_neon_vld1>;
|
||||
def VLD1d64 : VLD1D<"vld1.64", v1i64, int_arm_neon_vld1>;
|
||||
|
||||
def VLD1q8 : VLD1Q<"vld1.8", v16i8, int_arm_neon_vld1i>;
|
||||
def VLD1q16 : VLD1Q<"vld1.16", v8i16, int_arm_neon_vld1i>;
|
||||
def VLD1q32 : VLD1Q<"vld1.32", v4i32, int_arm_neon_vld1i>;
|
||||
def VLD1qf : VLD1Q<"vld1.32", v4f32, int_arm_neon_vld1f>;
|
||||
def VLD1q64 : VLD1Q<"vld1.64", v2i64, int_arm_neon_vld1i>;
|
||||
def VLD1q8 : VLD1Q<"vld1.8", v16i8, int_arm_neon_vld1>;
|
||||
def VLD1q16 : VLD1Q<"vld1.16", v8i16, int_arm_neon_vld1>;
|
||||
def VLD1q32 : VLD1Q<"vld1.32", v4i32, int_arm_neon_vld1>;
|
||||
def VLD1qf : VLD1Q<"vld1.32", v4f32, int_arm_neon_vld1>;
|
||||
def VLD1q64 : VLD1Q<"vld1.64", v2i64, int_arm_neon_vld1>;
|
||||
|
||||
// VLD2 : Vector Load (multiple 2-element structures)
|
||||
class VLD2D<string OpcodeStr>
|
||||
|
|
@ -228,17 +228,17 @@ class VST1Q<string OpcodeStr, ValueType Ty, Intrinsic IntOp>
|
|||
!strconcat(OpcodeStr, "\t${src:dregpair}, $addr"),
|
||||
[(IntOp addrmode6:$addr, (Ty QPR:$src))]>;
|
||||
|
||||
def VST1d8 : VST1D<"vst1.8", v8i8, int_arm_neon_vst1i>;
|
||||
def VST1d16 : VST1D<"vst1.16", v4i16, int_arm_neon_vst1i>;
|
||||
def VST1d32 : VST1D<"vst1.32", v2i32, int_arm_neon_vst1i>;
|
||||
def VST1df : VST1D<"vst1.32", v2f32, int_arm_neon_vst1f>;
|
||||
def VST1d64 : VST1D<"vst1.64", v1i64, int_arm_neon_vst1i>;
|
||||
def VST1d8 : VST1D<"vst1.8", v8i8, int_arm_neon_vst1>;
|
||||
def VST1d16 : VST1D<"vst1.16", v4i16, int_arm_neon_vst1>;
|
||||
def VST1d32 : VST1D<"vst1.32", v2i32, int_arm_neon_vst1>;
|
||||
def VST1df : VST1D<"vst1.32", v2f32, int_arm_neon_vst1>;
|
||||
def VST1d64 : VST1D<"vst1.64", v1i64, int_arm_neon_vst1>;
|
||||
|
||||
def VST1q8 : VST1Q<"vst1.8", v16i8, int_arm_neon_vst1i>;
|
||||
def VST1q16 : VST1Q<"vst1.16", v8i16, int_arm_neon_vst1i>;
|
||||
def VST1q32 : VST1Q<"vst1.32", v4i32, int_arm_neon_vst1i>;
|
||||
def VST1qf : VST1Q<"vst1.32", v4f32, int_arm_neon_vst1f>;
|
||||
def VST1q64 : VST1Q<"vst1.64", v2i64, int_arm_neon_vst1i>;
|
||||
def VST1q8 : VST1Q<"vst1.8", v16i8, int_arm_neon_vst1>;
|
||||
def VST1q16 : VST1Q<"vst1.16", v8i16, int_arm_neon_vst1>;
|
||||
def VST1q32 : VST1Q<"vst1.32", v4i32, int_arm_neon_vst1>;
|
||||
def VST1qf : VST1Q<"vst1.32", v4f32, int_arm_neon_vst1>;
|
||||
def VST1q64 : VST1Q<"vst1.64", v2i64, int_arm_neon_vst1>;
|
||||
|
||||
// VST2 : Vector Store (multiple 2-element structures)
|
||||
class VST2D<string OpcodeStr>
|
||||
|
|
@ -1223,9 +1223,9 @@ def VBSLq : N3V<1, 0, 0b01, 0b0001, 1, 1, (outs QPR:$dst),
|
|||
defm VABDs : N3VInt_QHS<0, 0, 0b0111, 0, "vabd.s", int_arm_neon_vabds, 0>;
|
||||
defm VABDu : N3VInt_QHS<1, 0, 0b0111, 0, "vabd.u", int_arm_neon_vabdu, 0>;
|
||||
def VABDfd : N3VDInt<1, 0, 0b10, 0b1101, 0, "vabd.f32", v2f32, v2f32,
|
||||
int_arm_neon_vabdf, 0>;
|
||||
int_arm_neon_vabds, 0>;
|
||||
def VABDfq : N3VQInt<1, 0, 0b10, 0b1101, 0, "vabd.f32", v4f32, v4f32,
|
||||
int_arm_neon_vabdf, 0>;
|
||||
int_arm_neon_vabds, 0>;
|
||||
|
||||
// VABDL : Vector Absolute Difference Long (Q = | D - D |)
|
||||
defm VABDLs : N3VLInt_QHS<0,1,0b0111,0, "vabdl.s", int_arm_neon_vabdls, 0>;
|
||||
|
|
@ -1245,17 +1245,17 @@ defm VABALu : N3VLInt3_QHS<1,1,0b0101,0, "vabal.u", int_arm_neon_vabalu>;
|
|||
defm VMAXs : N3VInt_QHS<0, 0, 0b0110, 0, "vmax.s", int_arm_neon_vmaxs, 1>;
|
||||
defm VMAXu : N3VInt_QHS<1, 0, 0b0110, 0, "vmax.u", int_arm_neon_vmaxu, 1>;
|
||||
def VMAXfd : N3VDInt<0, 0, 0b00, 0b1111, 0, "vmax.f32", v2f32, v2f32,
|
||||
int_arm_neon_vmaxf, 1>;
|
||||
int_arm_neon_vmaxs, 1>;
|
||||
def VMAXfq : N3VQInt<0, 0, 0b00, 0b1111, 0, "vmax.f32", v4f32, v4f32,
|
||||
int_arm_neon_vmaxf, 1>;
|
||||
int_arm_neon_vmaxs, 1>;
|
||||
|
||||
// VMIN : Vector Minimum
|
||||
defm VMINs : N3VInt_QHS<0, 0, 0b0110, 1, "vmin.s", int_arm_neon_vmins, 1>;
|
||||
defm VMINu : N3VInt_QHS<1, 0, 0b0110, 1, "vmin.u", int_arm_neon_vminu, 1>;
|
||||
def VMINfd : N3VDInt<0, 0, 0b10, 0b1111, 0, "vmin.f32", v2f32, v2f32,
|
||||
int_arm_neon_vminf, 1>;
|
||||
int_arm_neon_vmins, 1>;
|
||||
def VMINfq : N3VQInt<0, 0, 0b10, 0b1111, 0, "vmin.f32", v4f32, v4f32,
|
||||
int_arm_neon_vminf, 1>;
|
||||
int_arm_neon_vmins, 1>;
|
||||
|
||||
// Vector Pairwise Operations.
|
||||
|
||||
|
|
@ -1295,7 +1295,7 @@ def VPMAXu16 : N3VDInt<1, 0, 0b01, 0b1010, 0, "vpmax.u16", v4i16, v4i16,
|
|||
def VPMAXu32 : N3VDInt<1, 0, 0b10, 0b1010, 0, "vpmax.u32", v2i32, v2i32,
|
||||
int_arm_neon_vpmaxu, 0>;
|
||||
def VPMAXf : N3VDInt<1, 0, 0b00, 0b1111, 0, "vpmax.f32", v2f32, v2f32,
|
||||
int_arm_neon_vpmaxf, 0>;
|
||||
int_arm_neon_vpmaxs, 0>;
|
||||
|
||||
// VPMIN : Vector Pairwise Minimum
|
||||
def VPMINs8 : N3VDInt<0, 0, 0b00, 0b1010, 1, "vpmin.s8", v8i8, v8i8,
|
||||
|
|
@ -1311,7 +1311,7 @@ def VPMINu16 : N3VDInt<1, 0, 0b01, 0b1010, 1, "vpmin.u16", v4i16, v4i16,
|
|||
def VPMINu32 : N3VDInt<1, 0, 0b10, 0b1010, 1, "vpmin.u32", v2i32, v2i32,
|
||||
int_arm_neon_vpminu, 0>;
|
||||
def VPMINf : N3VDInt<1, 0, 0b10, 0b1111, 0, "vpmin.f32", v2f32, v2f32,
|
||||
int_arm_neon_vpminf, 0>;
|
||||
int_arm_neon_vpmins, 0>;
|
||||
|
||||
// Vector Reciprocal and Reciprocal Square Root Estimate and Step.
|
||||
|
||||
|
|
@ -1321,9 +1321,9 @@ def VRECPEd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01000, 0, "vrecpe.u32",
|
|||
def VRECPEq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01000, 0, "vrecpe.u32",
|
||||
v4i32, v4i32, int_arm_neon_vrecpe>;
|
||||
def VRECPEfd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01010, 0, "vrecpe.f32",
|
||||
v2f32, v2f32, int_arm_neon_vrecpef>;
|
||||
v2f32, v2f32, int_arm_neon_vrecpe>;
|
||||
def VRECPEfq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01010, 0, "vrecpe.f32",
|
||||
v4f32, v4f32, int_arm_neon_vrecpef>;
|
||||
v4f32, v4f32, int_arm_neon_vrecpe>;
|
||||
|
||||
// VRECPS : Vector Reciprocal Step
|
||||
def VRECPSfd : N3VDInt<0, 0, 0b00, 0b1111, 1, "vrecps.f32", v2f32, v2f32,
|
||||
|
|
@ -1337,9 +1337,9 @@ def VRSQRTEd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01001, 0, "vrsqrte.u32",
|
|||
def VRSQRTEq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01001, 0, "vrsqrte.u32",
|
||||
v4i32, v4i32, int_arm_neon_vrsqrte>;
|
||||
def VRSQRTEfd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01011, 0, "vrsqrte.f32",
|
||||
v2f32, v2f32, int_arm_neon_vrsqrtef>;
|
||||
v2f32, v2f32, int_arm_neon_vrsqrte>;
|
||||
def VRSQRTEfq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01011, 0, "vrsqrte.f32",
|
||||
v4f32, v4f32, int_arm_neon_vrsqrtef>;
|
||||
v4f32, v4f32, int_arm_neon_vrsqrte>;
|
||||
|
||||
// VRSQRTS : Vector Reciprocal Square Root Step
|
||||
def VRSQRTSfd : N3VDInt<0, 0, 0b10, 0b1111, 1, "vrsqrts.f32", v2f32, v2f32,
|
||||
|
|
@ -1480,9 +1480,9 @@ defm VSRI : N2VShIns_QHSD<1, 1, 0b0100, 1, "vsri.", NEONvsri>;
|
|||
defm VABS : N2VInt_QHS<0b11, 0b11, 0b01, 0b00110, 0, "vabs.s",
|
||||
int_arm_neon_vabs>;
|
||||
def VABSfd : N2VDInt<0b11, 0b11, 0b10, 0b01, 0b01110, 0, "vabs.f32",
|
||||
v2f32, v2f32, int_arm_neon_vabsf>;
|
||||
v2f32, v2f32, int_arm_neon_vabs>;
|
||||
def VABSfq : N2VQInt<0b11, 0b11, 0b10, 0b01, 0b01110, 0, "vabs.f32",
|
||||
v4f32, v4f32, int_arm_neon_vabsf>;
|
||||
v4f32, v4f32, int_arm_neon_vabs>;
|
||||
|
||||
// VQABS : Vector Saturating Absolute Value
|
||||
defm VQABS : N2VInt_QHS<0b11, 0b11, 0b00, 0b01110, 0, "vqabs.s",
|
||||
|
|
@ -2017,7 +2017,7 @@ def : N3VDMulOpsPat<fmul, fsub, VMLSfd_sfp>;
|
|||
// Vector Absolute used for single-precision FP
|
||||
let neverHasSideEffects = 1 in
|
||||
def VABSfd_sfp : N2VDInts<0b11, 0b11, 0b10, 0b01, 0b01110, 0, "vabs.f32",
|
||||
v2f32, v2f32, int_arm_neon_vabsf>;
|
||||
v2f32, v2f32, int_arm_neon_vabs>;
|
||||
def : N2VDIntsPat<fabs, VABSfd_sfp>;
|
||||
|
||||
// Vector Negate used for single-precision FP
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ define <2 x float> @vabdf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vabd.f32
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vabdf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
ret <2 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -122,7 +122,7 @@ define <4 x float> @vabdQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|||
;CHECK: vabd.f32
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vabdf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
ret <4 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -134,7 +134,7 @@ declare <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8>, <8 x i8>) nounwind readnon
|
|||
declare <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vabdf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vabds.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
|
|
@ -144,4 +144,4 @@ declare <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8>, <16 x i8>) nounwind read
|
|||
declare <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
|
||||
declare <4 x float> @llvm.arm.neon.vabdf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vabds.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ define <2 x float> @vabsf32(<2 x float>* %A) nounwind {
|
|||
;CHECK: vabsf32:
|
||||
;CHECK: vabs.f32
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vabsf.v2f32(<2 x float> %tmp1)
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vabs.v2f32(<2 x float> %tmp1)
|
||||
ret <2 x float> %tmp2
|
||||
}
|
||||
|
||||
|
|
@ -60,17 +60,17 @@ define <4 x float> @vabsQf32(<4 x float>* %A) nounwind {
|
|||
;CHECK: vabsQf32:
|
||||
;CHECK: vabs.f32
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vabsf.v4f32(<4 x float> %tmp1)
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vabs.v4f32(<4 x float> %tmp1)
|
||||
ret <4 x float> %tmp2
|
||||
}
|
||||
|
||||
declare <8 x i8> @llvm.arm.neon.vabs.v8i8(<8 x i8>) nounwind readnone
|
||||
declare <4 x i16> @llvm.arm.neon.vabs.v4i16(<4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vabs.v2i32(<2 x i32>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vabsf.v2f32(<2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vabs.v2f32(<2 x float>) nounwind readnone
|
||||
|
||||
declare <16 x i8> @llvm.arm.neon.vabs.v16i8(<16 x i8>) nounwind readnone
|
||||
declare <8 x i16> @llvm.arm.neon.vabs.v8i16(<8 x i16>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vabs.v4i32(<4 x i32>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vabsf.v4f32(<4 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vabs.v4f32(<4 x float>) nounwind readnone
|
||||
|
||||
|
|
|
|||
|
|
@ -3,81 +3,81 @@
|
|||
define <8 x i8> @vld1i8(i8* %A) nounwind {
|
||||
;CHECK: vld1i8:
|
||||
;CHECK: vld1.8
|
||||
%tmp1 = call <8 x i8> @llvm.arm.neon.vld1i.v8i8(i8* %A)
|
||||
%tmp1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8(i8* %A)
|
||||
ret <8 x i8> %tmp1
|
||||
}
|
||||
|
||||
define <4 x i16> @vld1i16(i16* %A) nounwind {
|
||||
;CHECK: vld1i16:
|
||||
;CHECK: vld1.16
|
||||
%tmp1 = call <4 x i16> @llvm.arm.neon.vld1i.v4i16(i16* %A)
|
||||
%tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i16* %A)
|
||||
ret <4 x i16> %tmp1
|
||||
}
|
||||
|
||||
define <2 x i32> @vld1i32(i32* %A) nounwind {
|
||||
;CHECK: vld1i32:
|
||||
;CHECK: vld1.32
|
||||
%tmp1 = call <2 x i32> @llvm.arm.neon.vld1i.v2i32(i32* %A)
|
||||
%tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i32* %A)
|
||||
ret <2 x i32> %tmp1
|
||||
}
|
||||
|
||||
define <2 x float> @vld1f(float* %A) nounwind {
|
||||
;CHECK: vld1f:
|
||||
;CHECK: vld1.32
|
||||
%tmp1 = call <2 x float> @llvm.arm.neon.vld1f.v2f32(float* %A)
|
||||
%tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(float* %A)
|
||||
ret <2 x float> %tmp1
|
||||
}
|
||||
|
||||
define <1 x i64> @vld1i64(i64* %A) nounwind {
|
||||
;CHECK: vld1i64:
|
||||
;CHECK: vld1.64
|
||||
%tmp1 = call <1 x i64> @llvm.arm.neon.vld1i.v1i64(i64* %A)
|
||||
%tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i64* %A)
|
||||
ret <1 x i64> %tmp1
|
||||
}
|
||||
|
||||
define <16 x i8> @vld1Qi8(i8* %A) nounwind {
|
||||
;CHECK: vld1Qi8:
|
||||
;CHECK: vld1.8
|
||||
%tmp1 = call <16 x i8> @llvm.arm.neon.vld1i.v16i8(i8* %A)
|
||||
%tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A)
|
||||
ret <16 x i8> %tmp1
|
||||
}
|
||||
|
||||
define <8 x i16> @vld1Qi16(i16* %A) nounwind {
|
||||
;CHECK: vld1Qi16:
|
||||
;CHECK: vld1.16
|
||||
%tmp1 = call <8 x i16> @llvm.arm.neon.vld1i.v8i16(i16* %A)
|
||||
%tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i16* %A)
|
||||
ret <8 x i16> %tmp1
|
||||
}
|
||||
|
||||
define <4 x i32> @vld1Qi32(i32* %A) nounwind {
|
||||
;CHECK: vld1Qi32:
|
||||
;CHECK: vld1.32
|
||||
%tmp1 = call <4 x i32> @llvm.arm.neon.vld1i.v4i32(i32* %A)
|
||||
%tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i32* %A)
|
||||
ret <4 x i32> %tmp1
|
||||
}
|
||||
|
||||
define <4 x float> @vld1Qf(float* %A) nounwind {
|
||||
;CHECK: vld1Qf:
|
||||
;CHECK: vld1.32
|
||||
%tmp1 = call <4 x float> @llvm.arm.neon.vld1f.v4f32(float* %A)
|
||||
%tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(float* %A)
|
||||
ret <4 x float> %tmp1
|
||||
}
|
||||
|
||||
define <2 x i64> @vld1Qi64(i64* %A) nounwind {
|
||||
;CHECK: vld1Qi64:
|
||||
;CHECK: vld1.64
|
||||
%tmp1 = call <2 x i64> @llvm.arm.neon.vld1i.v2i64(i64* %A)
|
||||
%tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i64* %A)
|
||||
ret <2 x i64> %tmp1
|
||||
}
|
||||
|
||||
declare <8 x i8> @llvm.arm.neon.vld1i.v8i8(i8*) nounwind readonly
|
||||
declare <4 x i16> @llvm.arm.neon.vld1i.v4i16(i8*) nounwind readonly
|
||||
declare <2 x i32> @llvm.arm.neon.vld1i.v2i32(i8*) nounwind readonly
|
||||
declare <2 x float> @llvm.arm.neon.vld1f.v2f32(i8*) nounwind readonly
|
||||
declare <1 x i64> @llvm.arm.neon.vld1i.v1i64(i8*) nounwind readonly
|
||||
declare <8 x i8> @llvm.arm.neon.vld1.v8i8(i8*) nounwind readonly
|
||||
declare <4 x i16> @llvm.arm.neon.vld1.v4i16(i8*) nounwind readonly
|
||||
declare <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*) nounwind readonly
|
||||
declare <2 x float> @llvm.arm.neon.vld1.v2f32(i8*) nounwind readonly
|
||||
declare <1 x i64> @llvm.arm.neon.vld1.v1i64(i8*) nounwind readonly
|
||||
|
||||
declare <16 x i8> @llvm.arm.neon.vld1i.v16i8(i8*) nounwind readonly
|
||||
declare <8 x i16> @llvm.arm.neon.vld1i.v8i16(i8*) nounwind readonly
|
||||
declare <4 x i32> @llvm.arm.neon.vld1i.v4i32(i8*) nounwind readonly
|
||||
declare <4 x float> @llvm.arm.neon.vld1f.v4f32(i8*) nounwind readonly
|
||||
declare <2 x i64> @llvm.arm.neon.vld1i.v2i64(i8*) nounwind readonly
|
||||
declare <16 x i8> @llvm.arm.neon.vld1.v16i8(i8*) nounwind readonly
|
||||
declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*) nounwind readonly
|
||||
declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*) nounwind readonly
|
||||
declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*) nounwind readonly
|
||||
declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*) nounwind readonly
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@
|
|||
define <8 x i8> @vld2i8(i8* %A) nounwind {
|
||||
;CHECK: vld2i8:
|
||||
;CHECK: vld2.8
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vld2i.v8i8(i8* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vld2.v8i8(i8* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v8qi2 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v8qi2 %tmp1, 1
|
||||
%tmp4 = add <8 x i8> %tmp2, %tmp3
|
||||
|
|
@ -18,7 +18,7 @@ define <8 x i8> @vld2i8(i8* %A) nounwind {
|
|||
define <4 x i16> @vld2i16(i16* %A) nounwind {
|
||||
;CHECK: vld2i16:
|
||||
;CHECK: vld2.16
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vld2i.v4i16(i16* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vld2.v4i16(i16* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v4hi2 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v4hi2 %tmp1, 1
|
||||
%tmp4 = add <4 x i16> %tmp2, %tmp3
|
||||
|
|
@ -28,7 +28,7 @@ define <4 x i16> @vld2i16(i16* %A) nounwind {
|
|||
define <2 x i32> @vld2i32(i32* %A) nounwind {
|
||||
;CHECK: vld2i32:
|
||||
;CHECK: vld2.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vld2i.v2i32(i32* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vld2.v2i32(i32* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2si2 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2si2 %tmp1, 1
|
||||
%tmp4 = add <2 x i32> %tmp2, %tmp3
|
||||
|
|
@ -38,14 +38,14 @@ define <2 x i32> @vld2i32(i32* %A) nounwind {
|
|||
define <2 x float> @vld2f(float* %A) nounwind {
|
||||
;CHECK: vld2f:
|
||||
;CHECK: vld2.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vld2f.v2f32(float* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vld2.v2f32(float* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2sf2 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2sf2 %tmp1, 1
|
||||
%tmp4 = add <2 x float> %tmp2, %tmp3
|
||||
ret <2 x float> %tmp4
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vld2i.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vld2i.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vld2i.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vld2f.v2f32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vld2.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vld2.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vld2.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vld2.v2f32(i8*) nounwind readonly
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@
|
|||
define <8 x i8> @vld3i8(i8* %A) nounwind {
|
||||
;CHECK: vld3i8:
|
||||
;CHECK: vld3.8
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi3 @llvm.arm.neon.vld3i.v8i8(i8* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi3 @llvm.arm.neon.vld3.v8i8(i8* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v8qi3 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v8qi3 %tmp1, 2
|
||||
%tmp4 = add <8 x i8> %tmp2, %tmp3
|
||||
|
|
@ -18,7 +18,7 @@ define <8 x i8> @vld3i8(i8* %A) nounwind {
|
|||
define <4 x i16> @vld3i16(i16* %A) nounwind {
|
||||
;CHECK: vld3i16:
|
||||
;CHECK: vld3.16
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi3 @llvm.arm.neon.vld3i.v4i16(i16* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi3 @llvm.arm.neon.vld3.v4i16(i16* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v4hi3 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v4hi3 %tmp1, 2
|
||||
%tmp4 = add <4 x i16> %tmp2, %tmp3
|
||||
|
|
@ -28,7 +28,7 @@ define <4 x i16> @vld3i16(i16* %A) nounwind {
|
|||
define <2 x i32> @vld3i32(i32* %A) nounwind {
|
||||
;CHECK: vld3i32:
|
||||
;CHECK: vld3.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2si3 @llvm.arm.neon.vld3i.v2i32(i32* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2si3 @llvm.arm.neon.vld3.v2i32(i32* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2si3 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2si3 %tmp1, 2
|
||||
%tmp4 = add <2 x i32> %tmp2, %tmp3
|
||||
|
|
@ -38,14 +38,14 @@ define <2 x i32> @vld3i32(i32* %A) nounwind {
|
|||
define <2 x float> @vld3f(float* %A) nounwind {
|
||||
;CHECK: vld3f:
|
||||
;CHECK: vld3.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf3 @llvm.arm.neon.vld3f.v2f32(float* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf3 @llvm.arm.neon.vld3.v2f32(float* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2sf3 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2sf3 %tmp1, 2
|
||||
%tmp4 = add <2 x float> %tmp2, %tmp3
|
||||
ret <2 x float> %tmp4
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi3 @llvm.arm.neon.vld3i.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi3 @llvm.arm.neon.vld3i.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si3 @llvm.arm.neon.vld3i.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf3 @llvm.arm.neon.vld3f.v2f32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v8qi3 @llvm.arm.neon.vld3.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi3 @llvm.arm.neon.vld3.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si3 @llvm.arm.neon.vld3.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf3 @llvm.arm.neon.vld3.v2f32(i8*) nounwind readonly
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@
|
|||
define <8 x i8> @vld4i8(i8* %A) nounwind {
|
||||
;CHECK: vld4i8:
|
||||
;CHECK: vld4.8
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi4 @llvm.arm.neon.vld4i.v8i8(i8* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v8qi4 @llvm.arm.neon.vld4.v8i8(i8* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v8qi4 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v8qi4 %tmp1, 2
|
||||
%tmp4 = add <8 x i8> %tmp2, %tmp3
|
||||
|
|
@ -18,7 +18,7 @@ define <8 x i8> @vld4i8(i8* %A) nounwind {
|
|||
define <4 x i16> @vld4i16(i16* %A) nounwind {
|
||||
;CHECK: vld4i16:
|
||||
;CHECK: vld4.16
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi4 @llvm.arm.neon.vld4i.v4i16(i16* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v4hi4 @llvm.arm.neon.vld4.v4i16(i16* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v4hi4 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v4hi4 %tmp1, 2
|
||||
%tmp4 = add <4 x i16> %tmp2, %tmp3
|
||||
|
|
@ -28,7 +28,7 @@ define <4 x i16> @vld4i16(i16* %A) nounwind {
|
|||
define <2 x i32> @vld4i32(i32* %A) nounwind {
|
||||
;CHECK: vld4i32:
|
||||
;CHECK: vld4.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2si4 @llvm.arm.neon.vld4i.v2i32(i32* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2si4 @llvm.arm.neon.vld4.v2i32(i32* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2si4 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2si4 %tmp1, 2
|
||||
%tmp4 = add <2 x i32> %tmp2, %tmp3
|
||||
|
|
@ -38,14 +38,14 @@ define <2 x i32> @vld4i32(i32* %A) nounwind {
|
|||
define <2 x float> @vld4f(float* %A) nounwind {
|
||||
;CHECK: vld4f:
|
||||
;CHECK: vld4.32
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf4 @llvm.arm.neon.vld4f.v2f32(float* %A)
|
||||
%tmp1 = call %struct.__builtin_neon_v2sf4 @llvm.arm.neon.vld4.v2f32(float* %A)
|
||||
%tmp2 = extractvalue %struct.__builtin_neon_v2sf4 %tmp1, 0
|
||||
%tmp3 = extractvalue %struct.__builtin_neon_v2sf4 %tmp1, 2
|
||||
%tmp4 = add <2 x float> %tmp2, %tmp3
|
||||
ret <2 x float> %tmp4
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi4 @llvm.arm.neon.vld4i.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi4 @llvm.arm.neon.vld4i.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si4 @llvm.arm.neon.vld4i.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf4 @llvm.arm.neon.vld4f.v2f32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v8qi4 @llvm.arm.neon.vld4.v8i8(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v4hi4 @llvm.arm.neon.vld4.v4i16(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2si4 @llvm.arm.neon.vld4.v2i32(i8*) nounwind readonly
|
||||
declare %struct.__builtin_neon_v2sf4 @llvm.arm.neon.vld4.v2f32(i8*) nounwind readonly
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vmaxf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
ret <2 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -101,7 +101,7 @@ define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|||
define <4 x float> @vmaxQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vmaxf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
ret <4 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -113,7 +113,7 @@ declare <8 x i8> @llvm.arm.neon.vmaxu.v8i8(<8 x i8>, <8 x i8>) nounwind readnon
|
|||
declare <4 x i16> @llvm.arm.neon.vmaxu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vmaxu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vmaxf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare <16 x i8> @llvm.arm.neon.vmaxs.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare <8 x i16> @llvm.arm.neon.vmaxs.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
|
|
@ -123,4 +123,4 @@ declare <16 x i8> @llvm.arm.neon.vmaxu.v16i8(<16 x i8>, <16 x i8>) nounwind read
|
|||
declare <8 x i16> @llvm.arm.neon.vmaxu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vmaxu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
|
||||
declare <4 x float> @llvm.arm.neon.vmaxf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ define <2 x i32> @vminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
define <2 x float> @vminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vminf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vmins.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
ret <2 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -101,7 +101,7 @@ define <4 x i32> @vminQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|||
define <4 x float> @vminQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vminf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call <4 x float> @llvm.arm.neon.vmins.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
ret <4 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -113,7 +113,7 @@ declare <8 x i8> @llvm.arm.neon.vminu.v8i8(<8 x i8>, <8 x i8>) nounwind readnon
|
|||
declare <4 x i16> @llvm.arm.neon.vminu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vminu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vminf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vmins.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare <16 x i8> @llvm.arm.neon.vmins.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare <8 x i16> @llvm.arm.neon.vmins.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
|
|
@ -123,4 +123,4 @@ declare <16 x i8> @llvm.arm.neon.vminu.v16i8(<16 x i8>, <16 x i8>) nounwind read
|
|||
declare <8 x i16> @llvm.arm.neon.vminu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vminu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
|
||||
declare <4 x float> @llvm.arm.neon.vminf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vmins.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ define <2 x i32> @vpmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
define <2 x float> @vpmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vpmaxf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vpmaxs.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
ret <2 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -64,4 +64,4 @@ declare <8 x i8> @llvm.arm.neon.vpmaxu.v8i8(<8 x i8>, <8 x i8>) nounwind readno
|
|||
declare <4 x i16> @llvm.arm.neon.vpmaxu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vpmaxu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vpmaxf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vpmaxs.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ define <2 x i32> @vpminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
define <2 x float> @vpminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vpminf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call <2 x float> @llvm.arm.neon.vpmins.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
ret <2 x float> %tmp3
|
||||
}
|
||||
|
||||
|
|
@ -64,4 +64,4 @@ declare <8 x i8> @llvm.arm.neon.vpminu.v8i8(<8 x i8>, <8 x i8>) nounwind readno
|
|||
declare <4 x i16> @llvm.arm.neon.vpminu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare <2 x i32> @llvm.arm.neon.vpminu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vpminf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vpmins.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -16,18 +16,18 @@ define <4 x i32> @vrecpeQi32(<4 x i32>* %A) nounwind {
|
|||
|
||||
define <2 x float> @vrecpef32(<2 x float>* %A) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vrecpef.v2f32(<2 x float> %tmp1)
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vrecpe.v2f32(<2 x float> %tmp1)
|
||||
ret <2 x float> %tmp2
|
||||
}
|
||||
|
||||
define <4 x float> @vrecpeQf32(<4 x float>* %A) nounwind {
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vrecpef.v4f32(<4 x float> %tmp1)
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vrecpe.v4f32(<4 x float> %tmp1)
|
||||
ret <4 x float> %tmp2
|
||||
}
|
||||
|
||||
declare <2 x i32> @llvm.arm.neon.vrecpe.v2i32(<2 x i32>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vrecpe.v4i32(<4 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vrecpef.v2f32(<2 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vrecpef.v4f32(<4 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vrecpe.v2f32(<2 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vrecpe.v4f32(<4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -16,18 +16,18 @@ define <4 x i32> @vrsqrteQi32(<4 x i32>* %A) nounwind {
|
|||
|
||||
define <2 x float> @vrsqrtef32(<2 x float>* %A) nounwind {
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vrsqrtef.v2f32(<2 x float> %tmp1)
|
||||
%tmp2 = call <2 x float> @llvm.arm.neon.vrsqrte.v2f32(<2 x float> %tmp1)
|
||||
ret <2 x float> %tmp2
|
||||
}
|
||||
|
||||
define <4 x float> @vrsqrteQf32(<4 x float>* %A) nounwind {
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vrsqrtef.v4f32(<4 x float> %tmp1)
|
||||
%tmp2 = call <4 x float> @llvm.arm.neon.vrsqrte.v4f32(<4 x float> %tmp1)
|
||||
ret <4 x float> %tmp2
|
||||
}
|
||||
|
||||
declare <2 x i32> @llvm.arm.neon.vrsqrte.v2i32(<2 x i32>) nounwind readnone
|
||||
declare <4 x i32> @llvm.arm.neon.vrsqrte.v4i32(<4 x i32>) nounwind readnone
|
||||
|
||||
declare <2 x float> @llvm.arm.neon.vrsqrtef.v2f32(<2 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vrsqrtef.v4f32(<4 x float>) nounwind readnone
|
||||
declare <2 x float> @llvm.arm.neon.vrsqrte.v2f32(<2 x float>) nounwind readnone
|
||||
declare <4 x float> @llvm.arm.neon.vrsqrte.v4f32(<4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ define void @vst1i8(i8* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vst1i8:
|
||||
;CHECK: vst1.8
|
||||
%tmp1 = load <8 x i8>* %B
|
||||
call void @llvm.arm.neon.vst1i.v8i8(i8* %A, <8 x i8> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v8i8(i8* %A, <8 x i8> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -12,7 +12,7 @@ define void @vst1i16(i16* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vst1i16:
|
||||
;CHECK: vst1.16
|
||||
%tmp1 = load <4 x i16>* %B
|
||||
call void @llvm.arm.neon.vst1i.v4i16(i16* %A, <4 x i16> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v4i16(i16* %A, <4 x i16> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ define void @vst1i32(i32* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vst1i32:
|
||||
;CHECK: vst1.32
|
||||
%tmp1 = load <2 x i32>* %B
|
||||
call void @llvm.arm.neon.vst1i.v2i32(i32* %A, <2 x i32> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v2i32(i32* %A, <2 x i32> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -28,7 +28,7 @@ define void @vst1f(float* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vst1f:
|
||||
;CHECK: vst1.32
|
||||
%tmp1 = load <2 x float>* %B
|
||||
call void @llvm.arm.neon.vst1f.v2f32(float* %A, <2 x float> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v2f32(float* %A, <2 x float> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -36,7 +36,7 @@ define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind {
|
|||
;CHECK: vst1i64:
|
||||
;CHECK: vst1.64
|
||||
%tmp1 = load <1 x i64>* %B
|
||||
call void @llvm.arm.neon.vst1i.v1i64(i64* %A, <1 x i64> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v1i64(i64* %A, <1 x i64> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -44,7 +44,7 @@ define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind {
|
|||
;CHECK: vst1Qi8:
|
||||
;CHECK: vst1.8
|
||||
%tmp1 = load <16 x i8>* %B
|
||||
call void @llvm.arm.neon.vst1i.v16i8(i8* %A, <16 x i8> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v16i8(i8* %A, <16 x i8> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -52,7 +52,7 @@ define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
|
|||
;CHECK: vst1Qi16:
|
||||
;CHECK: vst1.16
|
||||
%tmp1 = load <8 x i16>* %B
|
||||
call void @llvm.arm.neon.vst1i.v8i16(i16* %A, <8 x i16> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v8i16(i16* %A, <8 x i16> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -60,7 +60,7 @@ define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind {
|
|||
;CHECK: vst1Qi32:
|
||||
;CHECK: vst1.32
|
||||
%tmp1 = load <4 x i32>* %B
|
||||
call void @llvm.arm.neon.vst1i.v4i32(i32* %A, <4 x i32> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v4i32(i32* %A, <4 x i32> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -68,7 +68,7 @@ define void @vst1Qf(float* %A, <4 x float>* %B) nounwind {
|
|||
;CHECK: vst1Qf:
|
||||
;CHECK: vst1.32
|
||||
%tmp1 = load <4 x float>* %B
|
||||
call void @llvm.arm.neon.vst1f.v4f32(float* %A, <4 x float> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v4f32(float* %A, <4 x float> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -76,18 +76,18 @@ define void @vst1Qi64(i64* %A, <2 x i64>* %B) nounwind {
|
|||
;CHECK: vst1Qi64:
|
||||
;CHECK: vst1.64
|
||||
%tmp1 = load <2 x i64>* %B
|
||||
call void @llvm.arm.neon.vst1i.v2i64(i64* %A, <2 x i64> %tmp1)
|
||||
call void @llvm.arm.neon.vst1.v2i64(i64* %A, <2 x i64> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.arm.neon.vst1i.v8i8(i8*, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v4i16(i8*, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v2i32(i8*, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst1f.v2f32(i8*, <2 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v1i64(i8*, <1 x i64>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v8i8(i8*, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v4i16(i8*, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v2i32(i8*, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v2f32(i8*, <2 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v1i64(i8*, <1 x i64>) nounwind
|
||||
|
||||
declare void @llvm.arm.neon.vst1i.v16i8(i8*, <16 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v8i16(i8*, <8 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v4i32(i8*, <4 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst1f.v4f32(i8*, <4 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst1i.v2i64(i8*, <2 x i64>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v16i8(i8*, <16 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst1.v2i64(i8*, <2 x i64>) nounwind
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ define void @vst2i8(i8* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vst2i8:
|
||||
;CHECK: vst2.8
|
||||
%tmp1 = load <8 x i8>* %B
|
||||
call void @llvm.arm.neon.vst2i.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
call void @llvm.arm.neon.vst2.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -12,7 +12,7 @@ define void @vst2i16(i16* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vst2i16:
|
||||
;CHECK: vst2.16
|
||||
%tmp1 = load <4 x i16>* %B
|
||||
call void @llvm.arm.neon.vst2i.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
call void @llvm.arm.neon.vst2.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ define void @vst2i32(i32* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vst2i32:
|
||||
;CHECK: vst2.32
|
||||
%tmp1 = load <2 x i32>* %B
|
||||
call void @llvm.arm.neon.vst2i.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
call void @llvm.arm.neon.vst2.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -28,11 +28,11 @@ define void @vst2f(float* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vst2f:
|
||||
;CHECK: vst2.32
|
||||
%tmp1 = load <2 x float>* %B
|
||||
call void @llvm.arm.neon.vst2f.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
call void @llvm.arm.neon.vst2.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.arm.neon.vst2i.v8i8(i8*, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst2i.v4i16(i8*, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst2i.v2i32(i8*, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst2f.v2f32(i8*, <2 x float>, <2 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst2.v8i8(i8*, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst2.v4i16(i8*, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst2.v2i32(i8*, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst2.v2f32(i8*, <2 x float>, <2 x float>) nounwind
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vst3i8:
|
||||
;CHECK: vst3.8
|
||||
%tmp1 = load <8 x i8>* %B
|
||||
call void @llvm.arm.neon.vst3i.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -12,7 +12,7 @@ define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vst3i16:
|
||||
;CHECK: vst3.16
|
||||
%tmp1 = load <4 x i16>* %B
|
||||
call void @llvm.arm.neon.vst3i.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
call void @llvm.arm.neon.vst3.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vst3i32:
|
||||
;CHECK: vst3.32
|
||||
%tmp1 = load <2 x i32>* %B
|
||||
call void @llvm.arm.neon.vst3i.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
call void @llvm.arm.neon.vst3.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -28,11 +28,11 @@ define void @vst3f(float* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vst3f:
|
||||
;CHECK: vst3.32
|
||||
%tmp1 = load <2 x float>* %B
|
||||
call void @llvm.arm.neon.vst3f.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
call void @llvm.arm.neon.vst3.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.arm.neon.vst3i.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst3i.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst3i.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst3f.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vst4i8:
|
||||
;CHECK: vst4.8
|
||||
%tmp1 = load <8 x i8>* %B
|
||||
call void @llvm.arm.neon.vst4i.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -12,7 +12,7 @@ define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vst4i16:
|
||||
;CHECK: vst4.16
|
||||
%tmp1 = load <4 x i16>* %B
|
||||
call void @llvm.arm.neon.vst4i.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
call void @llvm.arm.neon.vst4.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vst4i32:
|
||||
;CHECK: vst4.32
|
||||
%tmp1 = load <2 x i32>* %B
|
||||
call void @llvm.arm.neon.vst4i.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
call void @llvm.arm.neon.vst4.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -28,11 +28,11 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vst4f:
|
||||
;CHECK: vst4.32
|
||||
%tmp1 = load <2 x float>* %B
|
||||
call void @llvm.arm.neon.vst4f.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
call void @llvm.arm.neon.vst4.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @llvm.arm.neon.vst4i.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst4i.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst4i.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst4f.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind
|
||||
declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
|
||||
declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
|
||||
declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
|
||||
declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ define <8 x i8> @vtrni8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vtrn.8
|
||||
%tmp1 = load <8 x i8>* %A
|
||||
%tmp2 = load <8 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vtrni.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vtrn.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i8> %tmp4, %tmp5
|
||||
|
|
@ -27,7 +27,7 @@ define <4 x i16> @vtrni16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vtrn.16
|
||||
%tmp1 = load <4 x i16>* %A
|
||||
%tmp2 = load <4 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vtrni.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vtrn.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 1
|
||||
%tmp6 = add <4 x i16> %tmp4, %tmp5
|
||||
|
|
@ -39,7 +39,7 @@ define <2 x i32> @vtrni32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vtrn.32
|
||||
%tmp1 = load <2 x i32>* %A
|
||||
%tmp2 = load <2 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vtrni.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vtrn.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 1
|
||||
%tmp6 = add <2 x i32> %tmp4, %tmp5
|
||||
|
|
@ -51,7 +51,7 @@ define <2 x float> @vtrnf(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vtrn.32
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vtrnf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vtrn.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 1
|
||||
%tmp6 = add <2 x float> %tmp4, %tmp5
|
||||
|
|
@ -63,7 +63,7 @@ define <16 x i8> @vtrnQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|||
;CHECK: vtrn.8
|
||||
%tmp1 = load <16 x i8>* %A
|
||||
%tmp2 = load <16 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vtrni.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vtrn.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 1
|
||||
%tmp6 = add <16 x i8> %tmp4, %tmp5
|
||||
|
|
@ -75,7 +75,7 @@ define <8 x i16> @vtrnQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|||
;CHECK: vtrn.16
|
||||
%tmp1 = load <8 x i16>* %A
|
||||
%tmp2 = load <8 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vtrni.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vtrn.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i16> %tmp4, %tmp5
|
||||
|
|
@ -87,7 +87,7 @@ define <4 x i32> @vtrnQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|||
;CHECK: vtrn.32
|
||||
%tmp1 = load <4 x i32>* %A
|
||||
%tmp2 = load <4 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vtrni.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vtrn.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 1
|
||||
%tmp6 = add <4 x i32> %tmp4, %tmp5
|
||||
|
|
@ -99,19 +99,19 @@ define <4 x float> @vtrnQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|||
;CHECK: vtrn.32
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vtrnf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vtrn.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 1
|
||||
%tmp6 = add <4 x float> %tmp4, %tmp5
|
||||
ret <4 x float> %tmp6
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vtrni.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vtrni.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vtrni.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vtrnf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vtrn.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vtrn.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vtrn.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vtrn.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vtrni.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vtrni.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vtrni.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vtrnf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vtrn.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vtrn.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vtrn.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vtrn.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ define <8 x i8> @vuzpi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vuzp.8
|
||||
%tmp1 = load <8 x i8>* %A
|
||||
%tmp2 = load <8 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vuzpi.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vuzp.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i8> %tmp4, %tmp5
|
||||
|
|
@ -27,7 +27,7 @@ define <4 x i16> @vuzpi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vuzp.16
|
||||
%tmp1 = load <4 x i16>* %A
|
||||
%tmp2 = load <4 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vuzpi.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vuzp.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 1
|
||||
%tmp6 = add <4 x i16> %tmp4, %tmp5
|
||||
|
|
@ -39,7 +39,7 @@ define <2 x i32> @vuzpi32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vuzp.32
|
||||
%tmp1 = load <2 x i32>* %A
|
||||
%tmp2 = load <2 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vuzpi.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vuzp.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 1
|
||||
%tmp6 = add <2 x i32> %tmp4, %tmp5
|
||||
|
|
@ -51,7 +51,7 @@ define <2 x float> @vuzpf(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vuzp.32
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vuzpf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vuzp.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 1
|
||||
%tmp6 = add <2 x float> %tmp4, %tmp5
|
||||
|
|
@ -63,7 +63,7 @@ define <16 x i8> @vuzpQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|||
;CHECK: vuzp.8
|
||||
%tmp1 = load <16 x i8>* %A
|
||||
%tmp2 = load <16 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vuzpi.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vuzp.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 1
|
||||
%tmp6 = add <16 x i8> %tmp4, %tmp5
|
||||
|
|
@ -75,7 +75,7 @@ define <8 x i16> @vuzpQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|||
;CHECK: vuzp.16
|
||||
%tmp1 = load <8 x i16>* %A
|
||||
%tmp2 = load <8 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vuzpi.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vuzp.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i16> %tmp4, %tmp5
|
||||
|
|
@ -87,7 +87,7 @@ define <4 x i32> @vuzpQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|||
;CHECK: vuzp.32
|
||||
%tmp1 = load <4 x i32>* %A
|
||||
%tmp2 = load <4 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vuzpi.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vuzp.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 1
|
||||
%tmp6 = add <4 x i32> %tmp4, %tmp5
|
||||
|
|
@ -99,19 +99,19 @@ define <4 x float> @vuzpQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|||
;CHECK: vuzp.32
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vuzpf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vuzp.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 1
|
||||
%tmp6 = add <4 x float> %tmp4, %tmp5
|
||||
ret <4 x float> %tmp6
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vuzpi.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vuzpi.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vuzpi.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vuzpf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vuzp.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vuzp.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vuzp.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vuzp.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vuzpi.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vuzpi.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vuzpi.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vuzpf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vuzp.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vuzp.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vuzp.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vuzp.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|||
;CHECK: vzip.8
|
||||
%tmp1 = load <8 x i8>* %A
|
||||
%tmp2 = load <8 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vzipi.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vzip.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8qi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i8> %tmp4, %tmp5
|
||||
|
|
@ -27,7 +27,7 @@ define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|||
;CHECK: vzip.16
|
||||
%tmp1 = load <4 x i16>* %A
|
||||
%tmp2 = load <4 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vzipi.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vzip.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4hi2 %tmp3, 1
|
||||
%tmp6 = add <4 x i16> %tmp4, %tmp5
|
||||
|
|
@ -39,7 +39,7 @@ define <2 x i32> @vzipi32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|||
;CHECK: vzip.32
|
||||
%tmp1 = load <2 x i32>* %A
|
||||
%tmp2 = load <2 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vzipi.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2si2 @llvm.arm.neon.vzip.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2si2 %tmp3, 1
|
||||
%tmp6 = add <2 x i32> %tmp4, %tmp5
|
||||
|
|
@ -51,7 +51,7 @@ define <2 x float> @vzipf(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|||
;CHECK: vzip.32
|
||||
%tmp1 = load <2 x float>* %A
|
||||
%tmp2 = load <2 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vzipf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vzip.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v2sf2 %tmp3, 1
|
||||
%tmp6 = add <2 x float> %tmp4, %tmp5
|
||||
|
|
@ -63,7 +63,7 @@ define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|||
;CHECK: vzip.8
|
||||
%tmp1 = load <16 x i8>* %A
|
||||
%tmp2 = load <16 x i8>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vzipi.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vzip.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v16qi2 %tmp3, 1
|
||||
%tmp6 = add <16 x i8> %tmp4, %tmp5
|
||||
|
|
@ -75,7 +75,7 @@ define <8 x i16> @vzipQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|||
;CHECK: vzip.16
|
||||
%tmp1 = load <8 x i16>* %A
|
||||
%tmp2 = load <8 x i16>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vzipi.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vzip.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v8hi2 %tmp3, 1
|
||||
%tmp6 = add <8 x i16> %tmp4, %tmp5
|
||||
|
|
@ -87,7 +87,7 @@ define <4 x i32> @vzipQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|||
;CHECK: vzip.32
|
||||
%tmp1 = load <4 x i32>* %A
|
||||
%tmp2 = load <4 x i32>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vzipi.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4si2 @llvm.arm.neon.vzip.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4si2 %tmp3, 1
|
||||
%tmp6 = add <4 x i32> %tmp4, %tmp5
|
||||
|
|
@ -99,19 +99,19 @@ define <4 x float> @vzipQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|||
;CHECK: vzip.32
|
||||
%tmp1 = load <4 x float>* %A
|
||||
%tmp2 = load <4 x float>* %B
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vzipf.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp3 = call %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vzip.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
||||
%tmp4 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 0
|
||||
%tmp5 = extractvalue %struct.__builtin_neon_v4sf2 %tmp3, 1
|
||||
%tmp6 = add <4 x float> %tmp4, %tmp5
|
||||
ret <4 x float> %tmp6
|
||||
}
|
||||
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vzipi.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vzipi.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vzipi.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vzipf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8qi2 @llvm.arm.neon.vzip.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4hi2 @llvm.arm.neon.vzip.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2si2 @llvm.arm.neon.vzip.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v2sf2 @llvm.arm.neon.vzip.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
||||
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vzipi.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vzipi.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vzipi.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vzipf.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v16qi2 @llvm.arm.neon.vzip.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v8hi2 @llvm.arm.neon.vzip.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4si2 @llvm.arm.neon.vzip.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
||||
declare %struct.__builtin_neon_v4sf2 @llvm.arm.neon.vzip.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
||||
|
|
|
|||
Loading…
Reference in New Issue