llvm-6502/lib/Target/SystemZ/SystemZOperators.td
Richard Sandiford aff1c6427c [SystemZ] Tweak integer comparison code
The architecture has many comparison instructions, including some that
extend one of the operands.  The signed comparison instructions use sign
extensions and the unsigned comparison instructions use zero extensions.
In cases where we had a free choice between signed or unsigned comparisons,
we were trying to decide at lowering time which would best fit the available
instructions, taking things like extension type into account.  The code
to do that was getting increasingly hairy and was also making some bad
decisions.  E.g. when comparing the result of two LLCs, it is better to use
CR rather than CLR, since CR can be fused with a branch while CLR can't.

This patch removes the lowering code and instead adds an operand to
integer comparisons to say whether signed comparison is required,
whether unsigned comparison is required, or whether either is OK.
We can then leave the choice of instruction up to the normal isel code.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190138 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-06 11:51:39 +00:00

339 lines
18 KiB
TableGen

//===-- SystemZOperators.td - SystemZ-specific operators ------*- tblgen-*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Type profiles
//===----------------------------------------------------------------------===//
def SDT_CallSeqStart : SDCallSeqStart<[SDTCisVT<0, i64>]>;
def SDT_CallSeqEnd : SDCallSeqEnd<[SDTCisVT<0, i64>,
SDTCisVT<1, i64>]>;
def SDT_ZCall : SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>;
def SDT_ZCmp : SDTypeProfile<0, 2, [SDTCisSameAs<0, 1>]>;
def SDT_ZICmp : SDTypeProfile<0, 3,
[SDTCisSameAs<0, 1>,
SDTCisVT<2, i32>]>;
def SDT_ZBRCCMask : SDTypeProfile<0, 3,
[SDTCisVT<0, i8>,
SDTCisVT<1, i8>,
SDTCisVT<2, OtherVT>]>;
def SDT_ZSelectCCMask : SDTypeProfile<1, 4,
[SDTCisSameAs<0, 1>,
SDTCisSameAs<1, 2>,
SDTCisVT<3, i8>,
SDTCisVT<4, i8>]>;
def SDT_ZWrapPtr : SDTypeProfile<1, 1,
[SDTCisSameAs<0, 1>,
SDTCisPtrTy<0>]>;
def SDT_ZAdjDynAlloc : SDTypeProfile<1, 0, [SDTCisVT<0, i64>]>;
def SDT_ZExtractAccess : SDTypeProfile<1, 1,
[SDTCisVT<0, i32>,
SDTCisVT<1, i8>]>;
def SDT_ZGR128Binary32 : SDTypeProfile<1, 2,
[SDTCisVT<0, untyped>,
SDTCisVT<1, untyped>,
SDTCisVT<2, i32>]>;
def SDT_ZGR128Binary64 : SDTypeProfile<1, 2,
[SDTCisVT<0, untyped>,
SDTCisVT<1, untyped>,
SDTCisVT<2, i64>]>;
def SDT_ZAtomicLoadBinaryW : SDTypeProfile<1, 5,
[SDTCisVT<0, i32>,
SDTCisPtrTy<1>,
SDTCisVT<2, i32>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>,
SDTCisVT<5, i32>]>;
def SDT_ZAtomicCmpSwapW : SDTypeProfile<1, 6,
[SDTCisVT<0, i32>,
SDTCisPtrTy<1>,
SDTCisVT<2, i32>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>,
SDTCisVT<5, i32>,
SDTCisVT<6, i32>]>;
def SDT_ZMemMemLength : SDTypeProfile<0, 3,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisVT<2, i64>]>;
def SDT_ZMemMemLoop : SDTypeProfile<0, 4,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisVT<2, i64>,
SDTCisVT<3, i64>]>;
def SDT_ZString : SDTypeProfile<1, 3,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisPtrTy<2>,
SDTCisVT<3, i32>]>;
def SDT_ZI32Intrinsic : SDTypeProfile<1, 0, [SDTCisVT<0, i32>]>;
def SDT_ZPrefetch : SDTypeProfile<0, 2,
[SDTCisVT<0, i8>,
SDTCisPtrTy<1>]>;
//===----------------------------------------------------------------------===//
// Node definitions
//===----------------------------------------------------------------------===//
// These are target-independent nodes, but have target-specific formats.
def callseq_start : SDNode<"ISD::CALLSEQ_START", SDT_CallSeqStart,
[SDNPHasChain, SDNPSideEffect, SDNPOutGlue]>;
def callseq_end : SDNode<"ISD::CALLSEQ_END", SDT_CallSeqEnd,
[SDNPHasChain, SDNPSideEffect, SDNPOptInGlue,
SDNPOutGlue]>;
// Nodes for SystemZISD::*. See SystemZISelLowering.h for more details.
def z_retflag : SDNode<"SystemZISD::RET_FLAG", SDTNone,
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
def z_call : SDNode<"SystemZISD::CALL", SDT_ZCall,
[SDNPHasChain, SDNPOutGlue, SDNPOptInGlue,
SDNPVariadic]>;
def z_sibcall : SDNode<"SystemZISD::SIBCALL", SDT_ZCall,
[SDNPHasChain, SDNPOutGlue, SDNPOptInGlue,
SDNPVariadic]>;
def z_pcrel_wrapper : SDNode<"SystemZISD::PCREL_WRAPPER", SDT_ZWrapPtr, []>;
def z_icmp : SDNode<"SystemZISD::ICMP", SDT_ZICmp, [SDNPOutGlue]>;
def z_fcmp : SDNode<"SystemZISD::FCMP", SDT_ZCmp, [SDNPOutGlue]>;
def z_tm : SDNode<"SystemZISD::TM", SDT_ZCmp, [SDNPOutGlue]>;
def z_br_ccmask : SDNode<"SystemZISD::BR_CCMASK", SDT_ZBRCCMask,
[SDNPHasChain, SDNPInGlue]>;
def z_select_ccmask : SDNode<"SystemZISD::SELECT_CCMASK", SDT_ZSelectCCMask,
[SDNPInGlue]>;
def z_adjdynalloc : SDNode<"SystemZISD::ADJDYNALLOC", SDT_ZAdjDynAlloc>;
def z_extract_access : SDNode<"SystemZISD::EXTRACT_ACCESS",
SDT_ZExtractAccess>;
def z_umul_lohi64 : SDNode<"SystemZISD::UMUL_LOHI64", SDT_ZGR128Binary64>;
def z_sdivrem32 : SDNode<"SystemZISD::SDIVREM32", SDT_ZGR128Binary32>;
def z_sdivrem64 : SDNode<"SystemZISD::SDIVREM64", SDT_ZGR128Binary64>;
def z_udivrem32 : SDNode<"SystemZISD::UDIVREM32", SDT_ZGR128Binary32>;
def z_udivrem64 : SDNode<"SystemZISD::UDIVREM64", SDT_ZGR128Binary64>;
class AtomicWOp<string name, SDTypeProfile profile = SDT_ZAtomicLoadBinaryW>
: SDNode<"SystemZISD::"##name, profile,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand]>;
def z_atomic_swapw : AtomicWOp<"ATOMIC_SWAPW">;
def z_atomic_loadw_add : AtomicWOp<"ATOMIC_LOADW_ADD">;
def z_atomic_loadw_sub : AtomicWOp<"ATOMIC_LOADW_SUB">;
def z_atomic_loadw_and : AtomicWOp<"ATOMIC_LOADW_AND">;
def z_atomic_loadw_or : AtomicWOp<"ATOMIC_LOADW_OR">;
def z_atomic_loadw_xor : AtomicWOp<"ATOMIC_LOADW_XOR">;
def z_atomic_loadw_nand : AtomicWOp<"ATOMIC_LOADW_NAND">;
def z_atomic_loadw_min : AtomicWOp<"ATOMIC_LOADW_MIN">;
def z_atomic_loadw_max : AtomicWOp<"ATOMIC_LOADW_MAX">;
def z_atomic_loadw_umin : AtomicWOp<"ATOMIC_LOADW_UMIN">;
def z_atomic_loadw_umax : AtomicWOp<"ATOMIC_LOADW_UMAX">;
def z_atomic_cmp_swapw : AtomicWOp<"ATOMIC_CMP_SWAPW", SDT_ZAtomicCmpSwapW>;
def z_mvc : SDNode<"SystemZISD::MVC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_mvc_loop : SDNode<"SystemZISD::MVC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_nc : SDNode<"SystemZISD::NC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_nc_loop : SDNode<"SystemZISD::NC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_oc : SDNode<"SystemZISD::OC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_oc_loop : SDNode<"SystemZISD::OC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_xc : SDNode<"SystemZISD::XC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_xc_loop : SDNode<"SystemZISD::XC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_clc : SDNode<"SystemZISD::CLC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_clc_loop : SDNode<"SystemZISD::CLC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_strcmp : SDNode<"SystemZISD::STRCMP", SDT_ZString,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_stpcpy : SDNode<"SystemZISD::STPCPY", SDT_ZString,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_search_string : SDNode<"SystemZISD::SEARCH_STRING", SDT_ZString,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_ipm : SDNode<"SystemZISD::IPM", SDT_ZI32Intrinsic,
[SDNPInGlue]>;
def z_prefetch : SDNode<"SystemZISD::PREFETCH", SDT_ZPrefetch,
[SDNPHasChain, SDNPMayLoad, SDNPMayStore,
SDNPMemOperand]>;
//===----------------------------------------------------------------------===//
// Pattern fragments
//===----------------------------------------------------------------------===//
// Signed and unsigned comparisons.
def z_scmp : PatFrag<(ops node:$a, node:$b), (z_icmp node:$a, node:$b, imm), [{
unsigned Type = cast<ConstantSDNode>(N->getOperand(2))->getZExtValue();
return Type != SystemZICMP::UnsignedOnly;
}]>;
def z_ucmp : PatFrag<(ops node:$a, node:$b), (z_icmp node:$a, node:$b, imm), [{
unsigned Type = cast<ConstantSDNode>(N->getOperand(2))->getZExtValue();
return Type != SystemZICMP::SignedOnly;
}]>;
// Register sign-extend operations. Sub-32-bit values are represented as i32s.
def sext8 : PatFrag<(ops node:$src), (sext_inreg node:$src, i8)>;
def sext16 : PatFrag<(ops node:$src), (sext_inreg node:$src, i16)>;
def sext32 : PatFrag<(ops node:$src), (sext (i32 node:$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))>;
// Typed floating-point loads.
def loadf32 : PatFrag<(ops node:$src), (f32 (load node:$src))>;
def loadf64 : PatFrag<(ops node:$src), (f64 (load node:$src))>;
// Extending loads in which the extension type doesn't matter.
def anyextload : PatFrag<(ops node:$ptr), (unindexedload node:$ptr), [{
return cast<LoadSDNode>(N)->getExtensionType() != ISD::NON_EXTLOAD;
}]>;
def anyextloadi8 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def anyextloadi16 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def anyextloadi32 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i32;
}]>;
// Aligned loads.
class AlignedLoad<SDPatternOperator load>
: PatFrag<(ops node:$addr), (load node:$addr), [{
LoadSDNode *Load = cast<LoadSDNode>(N);
return Load->getAlignment() >= Load->getMemoryVT().getStoreSize();
}]>;
def aligned_load : AlignedLoad<load>;
def aligned_sextloadi16 : AlignedLoad<sextloadi16>;
def aligned_sextloadi32 : AlignedLoad<sextloadi32>;
def aligned_zextloadi16 : AlignedLoad<zextloadi16>;
def aligned_zextloadi32 : AlignedLoad<zextloadi32>;
// Aligned stores.
class AlignedStore<SDPatternOperator store>
: PatFrag<(ops node:$src, node:$addr), (store node:$src, node:$addr), [{
StoreSDNode *Store = cast<StoreSDNode>(N);
return Store->getAlignment() >= Store->getMemoryVT().getStoreSize();
}]>;
def aligned_store : AlignedStore<store>;
def aligned_truncstorei16 : AlignedStore<truncstorei16>;
def aligned_truncstorei32 : AlignedStore<truncstorei32>;
// Non-volatile loads. Used for instructions that might access the storage
// location multiple times.
class NonvolatileLoad<SDPatternOperator load>
: PatFrag<(ops node:$addr), (load node:$addr), [{
LoadSDNode *Load = cast<LoadSDNode>(N);
return !Load->isVolatile();
}]>;
def nonvolatile_load : NonvolatileLoad<load>;
def nonvolatile_anyextloadi8 : NonvolatileLoad<anyextloadi8>;
def nonvolatile_anyextloadi16 : NonvolatileLoad<anyextloadi16>;
def nonvolatile_anyextloadi32 : NonvolatileLoad<anyextloadi32>;
// Non-volatile stores.
class NonvolatileStore<SDPatternOperator store>
: PatFrag<(ops node:$src, node:$addr), (store node:$src, node:$addr), [{
StoreSDNode *Store = cast<StoreSDNode>(N);
return !Store->isVolatile();
}]>;
def nonvolatile_store : NonvolatileStore<store>;
def nonvolatile_truncstorei8 : NonvolatileStore<truncstorei8>;
def nonvolatile_truncstorei16 : NonvolatileStore<truncstorei16>;
def nonvolatile_truncstorei32 : NonvolatileStore<truncstorei32>;
// A store of a load that can be implemented using MVC.
def mvc_store : PatFrag<(ops node:$value, node:$addr),
(unindexedstore node:$value, node:$addr),
[{ return storeLoadCanUseMVC(N); }]>;
// Binary read-modify-write operations on memory in which the other
// operand is also memory and for which block operations like NC can
// be used. There are two patterns for each operator, depending on
// which operand contains the "other" load.
multiclass block_op<SDPatternOperator operator> {
def "1" : PatFrag<(ops node:$value, node:$addr),
(unindexedstore (operator node:$value,
(unindexedload node:$addr)),
node:$addr),
[{ return storeLoadCanUseBlockBinary(N, 0); }]>;
def "2" : PatFrag<(ops node:$value, node:$addr),
(unindexedstore (operator (unindexedload node:$addr),
node:$value),
node:$addr),
[{ return storeLoadCanUseBlockBinary(N, 1); }]>;
}
defm block_and : block_op<and>;
defm block_or : block_op<or>;
defm block_xor : block_op<xor>;
// Insertions.
def inserti8 : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, -256), node:$src2)>;
def insertll : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffffffff0000), node:$src2)>;
def insertlh : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffff0000ffff), node:$src2)>;
def inserthl : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffff0000ffffffff), node:$src2)>;
def inserthh : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0x0000ffffffffffff), node:$src2)>;
def insertlf : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffff00000000), node:$src2)>;
def inserthf : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0x00000000ffffffff), node:$src2)>;
// ORs that can be treated as insertions.
def or_as_inserti8 : PatFrag<(ops node:$src1, node:$src2),
(or node:$src1, node:$src2), [{
unsigned BitWidth = N->getValueType(0).getScalarType().getSizeInBits();
return CurDAG->MaskedValueIsZero(N->getOperand(0),
APInt::getLowBitsSet(BitWidth, 8));
}]>;
// ORs that can be treated as reversed insertions.
def or_as_revinserti8 : PatFrag<(ops node:$src1, node:$src2),
(or node:$src1, node:$src2), [{
unsigned BitWidth = N->getValueType(0).getScalarType().getSizeInBits();
return CurDAG->MaskedValueIsZero(N->getOperand(1),
APInt::getLowBitsSet(BitWidth, 8));
}]>;
// Integer absolute, matching the canonical form generated by DAGCombiner.
def z_iabs32 : PatFrag<(ops node:$src),
(xor (add node:$src, (sra node:$src, (i32 31))),
(sra node:$src, (i32 31)))>;
def z_iabs64 : PatFrag<(ops node:$src),
(xor (add node:$src, (sra node:$src, (i32 63))),
(sra node:$src, (i32 63)))>;
def z_inegabs32 : PatFrag<(ops node:$src), (ineg (z_iabs32 node:$src))>;
def z_inegabs64 : PatFrag<(ops node:$src), (ineg (z_iabs64 node:$src))>;
// 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:$src3),
(fma node:$src2, node:$src3, node:$src1)>;
def z_fms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(fma node:$src2, node:$src3, (fneg node:$src1))>;
// Floating-point negative absolute.
def fnabs : PatFrag<(ops node:$ptr), (fneg (fabs node:$ptr))>;
// Create a unary operator that loads from memory and then performs
// the given operation on it.
class loadu<SDPatternOperator operator, SDPatternOperator load = load>
: PatFrag<(ops node:$addr), (operator (load node:$addr))>;
// Create a store operator that performs the given unary operation
// on the value before storing it.
class storeu<SDPatternOperator operator, SDPatternOperator store = store>
: PatFrag<(ops node:$value, node:$addr),
(store (operator node:$value), node:$addr)>;