def SDT_ZTBegin : SDTypeProfile<0, 2,
[SDTCisPtrTy<0>,
SDTCisVT<1, i32>]>;
+def SDT_ZInsertVectorElt : SDTypeProfile<1, 3,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisVT<3, i32>]>;
+def SDT_ZExtractVectorElt : SDTypeProfile<1, 2,
+ [SDTCisVec<1>,
+ SDTCisVT<2, i32>]>;
+def SDT_ZReplicate : SDTypeProfile<1, 1,
+ [SDTCisVec<0>]>;
+def SDT_ZVecUnaryConv : SDTypeProfile<1, 1,
+ [SDTCisVec<0>,
+ SDTCisVec<1>]>;
+def SDT_ZVecUnary : SDTypeProfile<1, 1,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>]>;
+def SDT_ZVecBinary : SDTypeProfile<1, 2,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisSameAs<0, 2>]>;
+def SDT_ZVecBinaryInt : SDTypeProfile<1, 2,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisVT<2, i32>]>;
+def SDT_ZVecBinaryConv : SDTypeProfile<1, 2,
+ [SDTCisVec<0>,
+ SDTCisVec<1>,
+ SDTCisSameAs<1, 2>]>;
+def SDT_ZVecBinaryConvInt : SDTypeProfile<1, 2,
+ [SDTCisVec<0>,
+ SDTCisVec<1>,
+ SDTCisVT<2, i32>]>;
+def SDT_ZRotateMask : SDTypeProfile<1, 2,
+ [SDTCisVec<0>,
+ SDTCisVT<1, i32>,
+ SDTCisVT<2, i32>]>;
+def SDT_ZJoinDwords : SDTypeProfile<1, 2,
+ [SDTCisVT<0, v2i64>,
+ SDTCisVT<1, i64>,
+ SDTCisVT<2, i64>]>;
+def SDT_ZVecTernary : SDTypeProfile<1, 3,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisSameAs<0, 2>,
+ SDTCisSameAs<0, 3>]>;
+def SDT_ZVecTernaryInt : SDTypeProfile<1, 3,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisSameAs<0, 2>,
+ SDTCisVT<3, i32>]>;
+def SDT_ZVecQuaternaryInt : SDTypeProfile<1, 4,
+ [SDTCisVec<0>,
+ SDTCisSameAs<0, 1>,
+ SDTCisSameAs<0, 2>,
+ SDTCisSameAs<0, 3>,
+ SDTCisVT<4, i32>]>;
//===----------------------------------------------------------------------===//
// Node definitions
def z_serialize : SDNode<"SystemZISD::SERIALIZE", SDTNone,
[SDNPHasChain, SDNPMayStore]>;
+// Defined because the index is an i32 rather than a pointer.
+def z_vector_insert : SDNode<"ISD::INSERT_VECTOR_ELT",
+ SDT_ZInsertVectorElt>;
+def z_vector_extract : SDNode<"ISD::EXTRACT_VECTOR_ELT",
+ SDT_ZExtractVectorElt>;
+def z_byte_mask : SDNode<"SystemZISD::BYTE_MASK", SDT_ZReplicate>;
+def z_rotate_mask : SDNode<"SystemZISD::ROTATE_MASK", SDT_ZRotateMask>;
+def z_replicate : SDNode<"SystemZISD::REPLICATE", SDT_ZReplicate>;
+def z_join_dwords : SDNode<"SystemZISD::JOIN_DWORDS", SDT_ZJoinDwords>;
+def z_splat : SDNode<"SystemZISD::SPLAT", SDT_ZVecBinaryInt>;
+def z_merge_high : SDNode<"SystemZISD::MERGE_HIGH", SDT_ZVecBinary>;
+def z_merge_low : SDNode<"SystemZISD::MERGE_LOW", SDT_ZVecBinary>;
+def z_shl_double : SDNode<"SystemZISD::SHL_DOUBLE", SDT_ZVecTernaryInt>;
+def z_permute_dwords : SDNode<"SystemZISD::PERMUTE_DWORDS",
+ SDT_ZVecTernaryInt>;
+def z_permute : SDNode<"SystemZISD::PERMUTE", SDT_ZVecTernary>;
+def z_pack : SDNode<"SystemZISD::PACK", SDT_ZVecBinaryConv>;
+def z_packs_cc : SDNode<"SystemZISD::PACKS_CC", SDT_ZVecBinaryConv,
+ [SDNPOutGlue]>;
+def z_packls_cc : SDNode<"SystemZISD::PACKLS_CC", SDT_ZVecBinaryConv,
+ [SDNPOutGlue]>;
+def z_unpack_high : SDNode<"SystemZISD::UNPACK_HIGH", SDT_ZVecUnaryConv>;
+def z_unpackl_high : SDNode<"SystemZISD::UNPACKL_HIGH", SDT_ZVecUnaryConv>;
+def z_unpack_low : SDNode<"SystemZISD::UNPACK_LOW", SDT_ZVecUnaryConv>;
+def z_unpackl_low : SDNode<"SystemZISD::UNPACKL_LOW", SDT_ZVecUnaryConv>;
+def z_vshl_by_scalar : SDNode<"SystemZISD::VSHL_BY_SCALAR",
+ SDT_ZVecBinaryInt>;
+def z_vsrl_by_scalar : SDNode<"SystemZISD::VSRL_BY_SCALAR",
+ SDT_ZVecBinaryInt>;
+def z_vsra_by_scalar : SDNode<"SystemZISD::VSRA_BY_SCALAR",
+ SDT_ZVecBinaryInt>;
+def z_vsum : SDNode<"SystemZISD::VSUM", SDT_ZVecBinaryConv>;
+def z_vicmpe : SDNode<"SystemZISD::VICMPE", SDT_ZVecBinary>;
+def z_vicmph : SDNode<"SystemZISD::VICMPH", SDT_ZVecBinary>;
+def z_vicmphl : SDNode<"SystemZISD::VICMPHL", SDT_ZVecBinary>;
+def z_vicmpes : SDNode<"SystemZISD::VICMPES", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vicmphs : SDNode<"SystemZISD::VICMPHS", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vicmphls : SDNode<"SystemZISD::VICMPHLS", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vfcmpe : SDNode<"SystemZISD::VFCMPE", SDT_ZVecBinaryConv>;
+def z_vfcmph : SDNode<"SystemZISD::VFCMPH", SDT_ZVecBinaryConv>;
+def z_vfcmphe : SDNode<"SystemZISD::VFCMPHE", SDT_ZVecBinaryConv>;
+def z_vfcmpes : SDNode<"SystemZISD::VFCMPES", SDT_ZVecBinaryConv,
+ [SDNPOutGlue]>;
+def z_vfcmphs : SDNode<"SystemZISD::VFCMPHS", SDT_ZVecBinaryConv,
+ [SDNPOutGlue]>;
+def z_vfcmphes : SDNode<"SystemZISD::VFCMPHES", SDT_ZVecBinaryConv,
+ [SDNPOutGlue]>;
+def z_vextend : SDNode<"SystemZISD::VEXTEND", SDT_ZVecUnaryConv>;
+def z_vround : SDNode<"SystemZISD::VROUND", SDT_ZVecUnaryConv>;
+def z_vtm : SDNode<"SystemZISD::VTM", SDT_ZCmp, [SDNPOutGlue]>;
+def z_vfae_cc : SDNode<"SystemZISD::VFAE_CC", SDT_ZVecTernaryInt,
+ [SDNPOutGlue]>;
+def z_vfaez_cc : SDNode<"SystemZISD::VFAEZ_CC", SDT_ZVecTernaryInt,
+ [SDNPOutGlue]>;
+def z_vfee_cc : SDNode<"SystemZISD::VFEE_CC", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vfeez_cc : SDNode<"SystemZISD::VFEEZ_CC", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vfene_cc : SDNode<"SystemZISD::VFENE_CC", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vfenez_cc : SDNode<"SystemZISD::VFENEZ_CC", SDT_ZVecBinary,
+ [SDNPOutGlue]>;
+def z_vistr_cc : SDNode<"SystemZISD::VISTR_CC", SDT_ZVecUnary,
+ [SDNPOutGlue]>;
+def z_vstrc_cc : SDNode<"SystemZISD::VSTRC_CC", SDT_ZVecQuaternaryInt,
+ [SDNPOutGlue]>;
+def z_vstrcz_cc : SDNode<"SystemZISD::VSTRCZ_CC",
+ SDT_ZVecQuaternaryInt, [SDNPOutGlue]>;
+def z_vftci : SDNode<"SystemZISD::VFTCI", SDT_ZVecBinaryConvInt,
+ [SDNPOutGlue]>;
+
class AtomicWOp<string name, SDTypeProfile profile = SDT_ZAtomicLoadBinaryW>
: SDNode<"SystemZISD::"##name, profile,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand]>;
def z_tend : SDNode<"SystemZISD::TEND", SDTNone,
[SDNPHasChain, SDNPOutGlue, SDNPSideEffect]>;
+def z_vshl : SDNode<"ISD::SHL", SDT_ZVecBinary>;
+def z_vsra : SDNode<"ISD::SRA", SDT_ZVecBinary>;
+def z_vsrl : SDNode<"ISD::SRL", SDT_ZVecBinary>;
+
//===----------------------------------------------------------------------===//
// Pattern fragments
//===----------------------------------------------------------------------===//
def sext16 : PatFrag<(ops node:$src), (sext_inreg node:$src, i16)>;
def sext32 : PatFrag<(ops node:$src), (sext (i32 node:$src))>;
+// Match extensions of an i32 to an i64, followed by an in-register sign
+// extension from a sub-i32 value.
+def sext8dbl : PatFrag<(ops node:$src), (sext8 (anyext node:$src))>;
+def sext16dbl : PatFrag<(ops node:$src), (sext16 (anyext node:$src))>;
+
// Register zero-extend operations. Sub-32-bit values are represented as i32s.
def zext8 : PatFrag<(ops node:$src), (and node:$src, 0xff)>;
def zext16 : PatFrag<(ops node:$src), (and node:$src, 0xffff)>;
def zext32 : PatFrag<(ops node:$src), (zext (i32 node:$src))>;
+// Match extensions of an i32 to an i64, followed by an AND of the low
+// i8 or i16 part.
+def zext8dbl : PatFrag<(ops node:$src), (zext8 (anyext node:$src))>;
+def zext16dbl : PatFrag<(ops node:$src), (zext16 (anyext node:$src))>;
+
// Typed floating-point loads.
def loadf32 : PatFrag<(ops node:$src), (f32 (load node:$src))>;
def loadf64 : PatFrag<(ops node:$src), (f64 (load node:$src))>;
def z_inegabs32 : PatFrag<(ops node:$src), (ineg (z_iabs32 node:$src))>;
def z_inegabs64 : PatFrag<(ops node:$src), (ineg (z_iabs64 node:$src))>;
+// Integer multiply-and-add
+def z_muladd : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+ (add (mul node:$src1, node:$src2), node:$src3)>;
+
+// Fused multiply-subtract, using the natural operand order.
+def fms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+ (fma node:$src1, node:$src2, (fneg node:$src3))>;
+
// Fused multiply-add and multiply-subtract, but with the order of the
// operands matching SystemZ's MA and MS instructions.
def z_fma : PatFrag<(ops node:$src1, node:$src2, node:$src3),
class storeu<SDPatternOperator operator, SDPatternOperator store = store>
: PatFrag<(ops node:$value, node:$addr),
(store (operator node:$value), node:$addr)>;
+
+// Vector representation of all-zeros and all-ones.
+def z_vzero : PatFrag<(ops), (bitconvert (v16i8 (z_byte_mask (i32 0))))>;
+def z_vones : PatFrag<(ops), (bitconvert (v16i8 (z_byte_mask (i32 65535))))>;
+
+// Load a scalar and replicate it in all elements of a vector.
+class z_replicate_load<ValueType scalartype, SDPatternOperator load>
+ : PatFrag<(ops node:$addr),
+ (z_replicate (scalartype (load node:$addr)))>;
+def z_replicate_loadi8 : z_replicate_load<i32, anyextloadi8>;
+def z_replicate_loadi16 : z_replicate_load<i32, anyextloadi16>;
+def z_replicate_loadi32 : z_replicate_load<i32, load>;
+def z_replicate_loadi64 : z_replicate_load<i64, load>;
+def z_replicate_loadf32 : z_replicate_load<f32, load>;
+def z_replicate_loadf64 : z_replicate_load<f64, load>;
+
+// Load a scalar and insert it into a single element of a vector.
+class z_vle<ValueType scalartype, SDPatternOperator load>
+ : PatFrag<(ops node:$vec, node:$addr, node:$index),
+ (z_vector_insert node:$vec, (scalartype (load node:$addr)),
+ node:$index)>;
+def z_vlei8 : z_vle<i32, anyextloadi8>;
+def z_vlei16 : z_vle<i32, anyextloadi16>;
+def z_vlei32 : z_vle<i32, load>;
+def z_vlei64 : z_vle<i64, load>;
+def z_vlef32 : z_vle<f32, load>;
+def z_vlef64 : z_vle<f64, load>;
+
+// Load a scalar and insert it into the low element of the high i64 of a
+// zeroed vector.
+class z_vllez<ValueType scalartype, SDPatternOperator load, int index>
+ : PatFrag<(ops node:$addr),
+ (z_vector_insert (z_vzero),
+ (scalartype (load node:$addr)), (i32 index))>;
+def z_vllezi8 : z_vllez<i32, anyextloadi8, 7>;
+def z_vllezi16 : z_vllez<i32, anyextloadi16, 3>;
+def z_vllezi32 : z_vllez<i32, load, 1>;
+def z_vllezi64 : PatFrag<(ops node:$addr),
+ (z_join_dwords (i64 (load node:$addr)), (i64 0))>;
+// We use high merges to form a v4f32 from four f32s. Propagating zero
+// into all elements but index 1 gives this expression.
+def z_vllezf32 : PatFrag<(ops node:$addr),
+ (bitconvert
+ (z_merge_high
+ (v2i64
+ (z_unpackl_high
+ (v4i32
+ (bitconvert
+ (v4f32 (scalar_to_vector
+ (f32 (load node:$addr)))))))),
+ (v2i64 (z_vzero))))>;
+def z_vllezf64 : PatFrag<(ops node:$addr),
+ (z_merge_high
+ (scalar_to_vector (f64 (load node:$addr))),
+ (z_vzero))>;
+
+// Store one element of a vector.
+class z_vste<ValueType scalartype, SDPatternOperator store>
+ : PatFrag<(ops node:$vec, node:$addr, node:$index),
+ (store (scalartype (z_vector_extract node:$vec, node:$index)),
+ node:$addr)>;
+def z_vstei8 : z_vste<i32, truncstorei8>;
+def z_vstei16 : z_vste<i32, truncstorei16>;
+def z_vstei32 : z_vste<i32, store>;
+def z_vstei64 : z_vste<i64, store>;
+def z_vstef32 : z_vste<f32, store>;
+def z_vstef64 : z_vste<f64, store>;
+
+// Arithmetic negation on vectors.
+def z_vneg : PatFrag<(ops node:$x), (sub (z_vzero), node:$x)>;
+
+// Bitwise negation on vectors.
+def z_vnot : PatFrag<(ops node:$x), (xor node:$x, (z_vones))>;
+
+// Signed "integer greater than zero" on vectors.
+def z_vicmph_zero : PatFrag<(ops node:$x), (z_vicmph node:$x, (z_vzero))>;
+
+// Signed "integer less than zero" on vectors.
+def z_vicmpl_zero : PatFrag<(ops node:$x), (z_vicmph (z_vzero), node:$x)>;
+
+// Integer absolute on vectors.
+class z_viabs<int shift>
+ : PatFrag<(ops node:$src),
+ (xor (add node:$src, (z_vsra_by_scalar node:$src, (i32 shift))),
+ (z_vsra_by_scalar node:$src, (i32 shift)))>;
+def z_viabs8 : z_viabs<7>;
+def z_viabs16 : z_viabs<15>;
+def z_viabs32 : z_viabs<31>;
+def z_viabs64 : z_viabs<63>;
+
+// Sign-extend the i64 elements of a vector.
+class z_vse<int shift>
+ : PatFrag<(ops node:$src),
+ (z_vsra_by_scalar (z_vshl_by_scalar node:$src, shift), shift)>;
+def z_vsei8 : z_vse<56>;
+def z_vsei16 : z_vse<48>;
+def z_vsei32 : z_vse<32>;
+
+// ...and again with the extensions being done on individual i64 scalars.
+class z_vse_by_parts<SDPatternOperator operator, int index1, int index2>
+ : PatFrag<(ops node:$src),
+ (z_join_dwords
+ (operator (z_vector_extract node:$src, index1)),
+ (operator (z_vector_extract node:$src, index2)))>;
+def z_vsei8_by_parts : z_vse_by_parts<sext8dbl, 7, 15>;
+def z_vsei16_by_parts : z_vse_by_parts<sext16dbl, 3, 7>;
+def z_vsei32_by_parts : z_vse_by_parts<sext32, 1, 3>;
projects / oota-llvm.git / blobdiff