[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
//===- PPCInstrQPX.td - The PowerPC QPX Extension --*- tablegen -*-===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file describes the QPX extension to the PowerPC instruction set.
|
|
|
|
// Reference:
|
|
|
|
// Book Q: QPX Architecture Definition. IBM (as updated in) 2011.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
def PPCRegQFRCAsmOperand : AsmOperandClass {
|
|
|
|
let Name = "RegQFRC"; let PredicateMethod = "isRegNumber";
|
|
|
|
}
|
|
|
|
def qfrc : RegisterOperand<QFRC> {
|
|
|
|
let ParserMatchClass = PPCRegQFRCAsmOperand;
|
|
|
|
}
|
|
|
|
def PPCRegQSRCAsmOperand : AsmOperandClass {
|
|
|
|
let Name = "RegQSRC"; let PredicateMethod = "isRegNumber";
|
|
|
|
}
|
|
|
|
def qsrc : RegisterOperand<QSRC> {
|
|
|
|
let ParserMatchClass = PPCRegQSRCAsmOperand;
|
|
|
|
}
|
|
|
|
def PPCRegQBRCAsmOperand : AsmOperandClass {
|
|
|
|
let Name = "RegQBRC"; let PredicateMethod = "isRegNumber";
|
|
|
|
}
|
|
|
|
def qbrc : RegisterOperand<QBRC> {
|
|
|
|
let ParserMatchClass = PPCRegQBRCAsmOperand;
|
|
|
|
}
|
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Helpers for defining instructions that directly correspond to intrinsics.
|
|
|
|
|
|
|
|
// QPXA1_Int - A AForm_1 intrinsic definition.
|
|
|
|
class QPXA1_Int<bits<6> opcode, bits<5> xo, string opc, Intrinsic IntID>
|
|
|
|
: AForm_1<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
!strconcat(opc, " $FRT, $FRA, $FRC, $FRB"), IIC_FPFused,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRA, v4f64:$FRB, v4f64:$FRC))]>;
|
|
|
|
// QPXA1s_Int - A AForm_1 intrinsic definition (simple instructions).
|
|
|
|
class QPXA1s_Int<bits<6> opcode, bits<5> xo, string opc, Intrinsic IntID>
|
|
|
|
: AForm_1<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
!strconcat(opc, " $FRT, $FRA, $FRC, $FRB"), IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRA, v4f64:$FRB, v4f64:$FRC))]>;
|
|
|
|
// QPXA2_Int - A AForm_2 intrinsic definition.
|
|
|
|
class QPXA2_Int<bits<6> opcode, bits<5> xo, string opc, Intrinsic IntID>
|
|
|
|
: AForm_2<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
!strconcat(opc, " $FRT, $FRA, $FRB"), IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRA, v4f64:$FRB))]>;
|
|
|
|
// QPXA3_Int - A AForm_3 intrinsic definition.
|
|
|
|
class QPXA3_Int<bits<6> opcode, bits<5> xo, string opc, Intrinsic IntID>
|
|
|
|
: AForm_3<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRC),
|
|
|
|
!strconcat(opc, " $FRT, $FRA, $FRC"), IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRA, v4f64:$FRC))]>;
|
|
|
|
// QPXA4_Int - A AForm_4a intrinsic definition.
|
|
|
|
class QPXA4_Int<bits<6> opcode, bits<5> xo, string opc, Intrinsic IntID>
|
|
|
|
: AForm_4a<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
!strconcat(opc, " $FRT, $FRB"), IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRB))]>;
|
|
|
|
// QPXX18_Int - A XForm_18 intrinsic definition.
|
|
|
|
class QPXX18_Int<bits<6> opcode, bits<10> xo, string opc, Intrinsic IntID>
|
|
|
|
: XForm_18<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
!strconcat(opc, " $FRT, $FRA, $FRB"), IIC_FPCompare,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRA, v4f64:$FRB))]>;
|
|
|
|
// QPXX19_Int - A XForm_19 intrinsic definition.
|
|
|
|
class QPXX19_Int<bits<6> opcode, bits<10> xo, string opc, Intrinsic IntID>
|
|
|
|
: XForm_19<opcode, xo, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
!strconcat(opc, " $FRT, $FRB"), IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (IntID v4f64:$FRB))]>;
|
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Pattern Frags.
|
|
|
|
|
|
|
|
def extloadv4f32 : PatFrag<(ops node:$ptr), (extload node:$ptr), [{
|
|
|
|
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::v4f32;
|
|
|
|
}]>;
|
|
|
|
|
|
|
|
def truncstorev4f32 : PatFrag<(ops node:$val, node:$ptr),
|
|
|
|
(truncstore node:$val, node:$ptr), [{
|
|
|
|
return cast<StoreSDNode>(N)->getMemoryVT() == MVT::v4f32;
|
|
|
|
}]>;
|
|
|
|
def pre_truncstv4f32 : PatFrag<(ops node:$val, node:$base, node:$offset),
|
|
|
|
(pre_truncst node:$val,
|
|
|
|
node:$base, node:$offset), [{
|
|
|
|
return cast<StoreSDNode>(N)->getMemoryVT() == MVT::v4f32;
|
|
|
|
}]>;
|
|
|
|
|
2016-08-19 04:08:15 +08:00
|
|
|
def fround_inexact : PatFrag<(ops node:$val), (fpround node:$val), [{
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
return cast<ConstantSDNode>(N->getOperand(1))->getZExtValue() == 0;
|
|
|
|
}]>;
|
|
|
|
|
2016-08-19 04:08:15 +08:00
|
|
|
def fround_exact : PatFrag<(ops node:$val), (fpround node:$val), [{
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
return cast<ConstantSDNode>(N->getOperand(1))->getZExtValue() == 1;
|
|
|
|
}]>;
|
|
|
|
|
|
|
|
let FastIselShouldIgnore = 1 in // FastIsel should ignore all u12 instrs.
|
|
|
|
def u12 : ImmLeaf<i32, [{ return (Imm & 0xFFF) == Imm; }]>;
|
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Instruction Definitions.
|
|
|
|
|
|
|
|
def HasQPX : Predicate<"PPCSubTarget->hasQPX()">;
|
|
|
|
let Predicates = [HasQPX] in {
|
|
|
|
let DecoderNamespace = "QPX" in {
|
|
|
|
let hasSideEffects = 0 in { // QPX instructions don't have side effects.
|
|
|
|
let Uses = [RM] in {
|
|
|
|
// Add Instructions
|
|
|
|
let isCommutable = 1 in {
|
|
|
|
def QVFADD : AForm_2<4, 21,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfadd $FRT, $FRA, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (fadd v4f64:$FRA, v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFADDS : QPXA2_Int<0, 21, "qvfadds", int_ppc_qpx_qvfadds>;
|
|
|
|
def QVFADDSs : AForm_2<0, 21,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfadds $FRT, $FRA, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (fadd v4f32:$FRA, v4f32:$FRB))]>;
|
|
|
|
}
|
|
|
|
def QVFSUB : AForm_2<4, 20,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfsub $FRT, $FRA, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (fsub v4f64:$FRA, v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFSUBS : QPXA2_Int<0, 20, "qvfsubs", int_ppc_qpx_qvfsubs>;
|
|
|
|
def QVFSUBSs : AForm_2<0, 20,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfsubs $FRT, $FRA, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (fsub v4f32:$FRA, v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
// Estimate Instructions
|
|
|
|
def QVFRE : AForm_4a<4, 24, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfre $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (PPCfre v4f64:$FRB))]>;
|
|
|
|
def QVFRES : QPXA4_Int<0, 24, "qvfres", int_ppc_qpx_qvfres>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRESs : AForm_4a<0, 24, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfres $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (PPCfre v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
def QVFRSQRTE : AForm_4a<4, 26, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfrsqrte $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (PPCfrsqrte v4f64:$FRB))]>;
|
|
|
|
def QVFRSQRTES : QPXA4_Int<0, 26, "qvfrsqrtes", int_ppc_qpx_qvfrsqrtes>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRSQRTESs : AForm_4a<0, 26, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfrsqrtes $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (PPCfrsqrte v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
// Multiply Instructions
|
|
|
|
let isCommutable = 1 in {
|
|
|
|
def QVFMUL : AForm_3<4, 25,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRC),
|
|
|
|
"qvfmul $FRT, $FRA, $FRC", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (fmul v4f64:$FRA, v4f64:$FRC))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFMULS : QPXA3_Int<0, 25, "qvfmuls", int_ppc_qpx_qvfmuls>;
|
|
|
|
def QVFMULSs : AForm_3<0, 25,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRC),
|
|
|
|
"qvfmuls $FRT, $FRA, $FRC", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (fmul v4f32:$FRA, v4f32:$FRC))]>;
|
|
|
|
}
|
|
|
|
def QVFXMUL : QPXA3_Int<4, 17, "qvfxmul", int_ppc_qpx_qvfxmul>;
|
|
|
|
def QVFXMULS : QPXA3_Int<0, 17, "qvfxmuls", int_ppc_qpx_qvfxmuls>;
|
|
|
|
|
|
|
|
// Multiply-add instructions
|
|
|
|
def QVFMADD : AForm_1<4, 29,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfmadd $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f64:$FRT, (fma v4f64:$FRA, v4f64:$FRC, v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFMADDS : QPXA1_Int<0, 29, "qvfmadds", int_ppc_qpx_qvfmadds>;
|
|
|
|
def QVFMADDSs : AForm_1<0, 29,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, qsrc:$FRC),
|
|
|
|
"qvfmadds $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f32:$FRT, (fma v4f32:$FRA, v4f32:$FRC, v4f32:$FRB))]>;
|
|
|
|
def QVFNMADD : AForm_1<4, 31,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfnmadd $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f64:$FRT, (fneg (fma v4f64:$FRA, v4f64:$FRC,
|
|
|
|
v4f64:$FRB)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFNMADDS : QPXA1_Int<0, 31, "qvfnmadds", int_ppc_qpx_qvfnmadds>;
|
|
|
|
def QVFNMADDSs : AForm_1<0, 31,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, qsrc:$FRC),
|
|
|
|
"qvfnmadds $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f32:$FRT, (fneg (fma v4f32:$FRA, v4f32:$FRC,
|
|
|
|
v4f32:$FRB)))]>;
|
|
|
|
def QVFMSUB : AForm_1<4, 28,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfmsub $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f64:$FRT, (fma v4f64:$FRA, v4f64:$FRC,
|
|
|
|
(fneg v4f64:$FRB)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFMSUBS : QPXA1_Int<0, 28, "qvfmsubs", int_ppc_qpx_qvfmsubs>;
|
|
|
|
def QVFMSUBSs : AForm_1<0, 28,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, qsrc:$FRC),
|
|
|
|
"qvfmsubs $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f32:$FRT, (fma v4f32:$FRA, v4f32:$FRC,
|
|
|
|
(fneg v4f32:$FRB)))]>;
|
|
|
|
def QVFNMSUB : AForm_1<4, 30,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfnmsub $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f64:$FRT, (fneg (fma v4f64:$FRA, v4f64:$FRC,
|
|
|
|
(fneg v4f64:$FRB))))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFNMSUBS : QPXA1_Int<0, 30, "qvfnmsubs", int_ppc_qpx_qvfnmsubs>;
|
|
|
|
def QVFNMSUBSs : AForm_1<0, 30,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, qsrc:$FRC),
|
|
|
|
"qvfnmsubs $FRT, $FRA, $FRC, $FRB", IIC_FPFused,
|
|
|
|
[(set v4f32:$FRT, (fneg (fma v4f32:$FRA, v4f32:$FRC,
|
|
|
|
(fneg v4f32:$FRB))))]>;
|
|
|
|
def QVFXMADD : QPXA1_Int<4, 9, "qvfxmadd", int_ppc_qpx_qvfxmadd>;
|
|
|
|
def QVFXMADDS : QPXA1_Int<0, 9, "qvfxmadds", int_ppc_qpx_qvfxmadds>;
|
|
|
|
def QVFXXNPMADD : QPXA1_Int<4, 11, "qvfxxnpmadd", int_ppc_qpx_qvfxxnpmadd>;
|
|
|
|
def QVFXXNPMADDS : QPXA1_Int<0, 11, "qvfxxnpmadds", int_ppc_qpx_qvfxxnpmadds>;
|
|
|
|
def QVFXXCPNMADD : QPXA1_Int<4, 3, "qvfxxcpnmadd", int_ppc_qpx_qvfxxcpnmadd>;
|
|
|
|
def QVFXXCPNMADDS : QPXA1_Int<0, 3, "qvfxxcpnmadds", int_ppc_qpx_qvfxxcpnmadds>;
|
|
|
|
def QVFXXMADD : QPXA1_Int<4, 1, "qvfxxmadd", int_ppc_qpx_qvfxxmadd>;
|
|
|
|
def QVFXXMADDS : QPXA1_Int<0, 1, "qvfxxmadds", int_ppc_qpx_qvfxxmadds>;
|
|
|
|
|
|
|
|
// Select Instruction
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFSEL : QPXA1s_Int<4, 23, "qvfsel", int_ppc_qpx_qvfsel>;
|
|
|
|
def QVFSELb : AForm_1<4, 23, (outs qfrc:$FRT),
|
|
|
|
(ins qbrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfsel $FRT, $FRA, $FRC, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (vselect v4i1:$FRA,
|
|
|
|
v4f64:$FRC, v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFSELbs : AForm_1<4, 23, (outs qsrc:$FRT),
|
|
|
|
(ins qbrc:$FRA, qsrc:$FRB, qsrc:$FRC),
|
|
|
|
"qvfsel $FRT, $FRA, $FRC, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT, (vselect v4i1:$FRA,
|
|
|
|
v4f32:$FRC, v4f32:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFSELbb: AForm_1<4, 23, (outs qbrc:$FRT),
|
|
|
|
(ins qbrc:$FRA, qbrc:$FRB, qbrc:$FRC),
|
|
|
|
"qvfsel $FRT, $FRA, $FRC, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4i1:$FRT, (vselect v4i1:$FRA,
|
|
|
|
v4i1:$FRC, v4i1:$FRB))]>;
|
|
|
|
|
|
|
|
// SELECT_CC_* - Used to implement the SELECT_CC DAG operation. Expanded after
|
|
|
|
// instruction selection into a branch sequence.
|
|
|
|
let usesCustomInserter = 1 in {
|
|
|
|
def SELECT_CC_QFRC: Pseudo<(outs qfrc:$dst), (ins crrc:$cond, qfrc:$T, qfrc:$F,
|
|
|
|
i32imm:$BROPC), "#SELECT_CC_QFRC",
|
|
|
|
[]>;
|
|
|
|
def SELECT_CC_QSRC: Pseudo<(outs qsrc:$dst), (ins crrc:$cond, qsrc:$T, qsrc:$F,
|
|
|
|
i32imm:$BROPC), "#SELECT_CC_QSRC",
|
|
|
|
[]>;
|
|
|
|
def SELECT_CC_QBRC: Pseudo<(outs qbrc:$dst), (ins crrc:$cond, qbrc:$T, qbrc:$F,
|
|
|
|
i32imm:$BROPC), "#SELECT_CC_QBRC",
|
|
|
|
[]>;
|
|
|
|
|
|
|
|
// SELECT_* pseudo instructions, like SELECT_CC_* but taking condition
|
|
|
|
// register bit directly.
|
|
|
|
def SELECT_QFRC: Pseudo<(outs qfrc:$dst), (ins crbitrc:$cond,
|
|
|
|
qfrc:$T, qfrc:$F), "#SELECT_QFRC",
|
|
|
|
[(set v4f64:$dst,
|
|
|
|
(select i1:$cond, v4f64:$T, v4f64:$F))]>;
|
|
|
|
def SELECT_QSRC: Pseudo<(outs qsrc:$dst), (ins crbitrc:$cond,
|
|
|
|
qsrc:$T, qsrc:$F), "#SELECT_QSRC",
|
|
|
|
[(set v4f32:$dst,
|
|
|
|
(select i1:$cond, v4f32:$T, v4f32:$F))]>;
|
|
|
|
def SELECT_QBRC: Pseudo<(outs qbrc:$dst), (ins crbitrc:$cond,
|
|
|
|
qbrc:$T, qbrc:$F), "#SELECT_QBRC",
|
|
|
|
[(set v4i1:$dst,
|
|
|
|
(select i1:$cond, v4i1:$T, v4i1:$F))]>;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Convert and Round Instructions
|
|
|
|
def QVFCTID : QPXX19_Int<4, 814, "qvfctid", int_ppc_qpx_qvfctid>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCTIDb : XForm_19<4, 814, (outs qbrc:$FRT), (ins qbrc:$FRB),
|
|
|
|
"qvfctid $FRT, $FRB", IIC_FPGeneral, []>;
|
|
|
|
|
|
|
|
def QVFCTIDU : QPXX19_Int<4, 942, "qvfctidu", int_ppc_qpx_qvfctidu>;
|
|
|
|
def QVFCTIDZ : QPXX19_Int<4, 815, "qvfctidz", int_ppc_qpx_qvfctidz>;
|
|
|
|
def QVFCTIDUZ : QPXX19_Int<4, 943, "qvfctiduz", int_ppc_qpx_qvfctiduz>;
|
|
|
|
def QVFCTIW : QPXX19_Int<4, 14, "qvfctiw", int_ppc_qpx_qvfctiw>;
|
|
|
|
def QVFCTIWU : QPXX19_Int<4, 142, "qvfctiwu", int_ppc_qpx_qvfctiwu>;
|
|
|
|
def QVFCTIWZ : QPXX19_Int<4, 15, "qvfctiwz", int_ppc_qpx_qvfctiwz>;
|
|
|
|
def QVFCTIWUZ : QPXX19_Int<4, 143, "qvfctiwuz", int_ppc_qpx_qvfctiwuz>;
|
|
|
|
def QVFCFID : QPXX19_Int<4, 846, "qvfcfid", int_ppc_qpx_qvfcfid>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCFIDb : XForm_19<4, 846, (outs qbrc:$FRT), (ins qbrc:$FRB),
|
|
|
|
"qvfcfid $FRT, $FRB", IIC_FPGeneral, []>;
|
|
|
|
|
|
|
|
def QVFCFIDU : QPXX19_Int<4, 974, "qvfcfidu", int_ppc_qpx_qvfcfidu>;
|
|
|
|
def QVFCFIDS : QPXX19_Int<0, 846, "qvfcfids", int_ppc_qpx_qvfcfids>;
|
|
|
|
def QVFCFIDUS : QPXX19_Int<0, 974, "qvfcfidus", int_ppc_qpx_qvfcfidus>;
|
|
|
|
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRSP : QPXX19_Int<4, 12, "qvfrsp", int_ppc_qpx_qvfrsp>;
|
|
|
|
def QVFRSPs : XForm_19<4, 12,
|
|
|
|
(outs qsrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfrsp $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (fround_inexact v4f64:$FRB))]>;
|
|
|
|
|
|
|
|
def QVFRIZ : XForm_19<4, 424, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfriz $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (ftrunc v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRIZs : XForm_19<4, 424, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfriz $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (ftrunc v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
def QVFRIN : XForm_19<4, 392, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfrin $FRT, $FRB", IIC_FPGeneral,
|
2016-08-19 04:08:15 +08:00
|
|
|
[(set v4f64:$FRT, (fround v4f64:$FRB))]>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRINs : XForm_19<4, 392, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfrin $FRT, $FRB", IIC_FPGeneral,
|
2016-08-19 04:08:15 +08:00
|
|
|
[(set v4f32:$FRT, (fround v4f32:$FRB))]>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
|
|
|
|
def QVFRIP : XForm_19<4, 456, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfrip $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (fceil v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRIPs : XForm_19<4, 456, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfrip $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (fceil v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
def QVFRIM : XForm_19<4, 488, (outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfrim $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f64:$FRT, (ffloor v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFRIMs : XForm_19<4, 488, (outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfrim $FRT, $FRB", IIC_FPGeneral,
|
|
|
|
[(set v4f32:$FRT, (ffloor v4f32:$FRB))]>;
|
|
|
|
|
|
|
|
// Move Instructions
|
|
|
|
def QVFMR : XForm_19<4, 72,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfmr $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[/* (set v4f64:$FRT, v4f64:$FRB) */]>;
|
|
|
|
let isCodeGenOnly = 1 in {
|
|
|
|
def QVFMRs : XForm_19<4, 72,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfmr $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[/* (set v4f32:$FRT, v4f32:$FRB) */]>;
|
|
|
|
def QVFMRb : XForm_19<4, 72,
|
|
|
|
(outs qbrc:$FRT), (ins qbrc:$FRB),
|
|
|
|
"qvfmr $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[/* (set v4i1:$FRT, v4i1:$FRB) */]>;
|
|
|
|
}
|
|
|
|
def QVFNEG : XForm_19<4, 40,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfneg $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (fneg v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFNEGs : XForm_19<4, 40,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfneg $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT, (fneg v4f32:$FRB))]>;
|
|
|
|
def QVFABS : XForm_19<4, 264,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfabs $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (fabs v4f64:$FRB))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFABSs : XForm_19<4, 264,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfabs $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT, (fabs v4f32:$FRB))]>;
|
|
|
|
def QVFNABS : XForm_19<4, 136,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRB),
|
|
|
|
"qvfnabs $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (fneg (fabs v4f64:$FRB)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFNABSs : XForm_19<4, 136,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRB),
|
|
|
|
"qvfnabs $FRT, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT, (fneg (fabs v4f32:$FRB)))]>;
|
|
|
|
def QVFCPSGN : XForm_18<4, 8,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfcpsgn $FRT, $FRA, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (fcopysign v4f64:$FRB, v4f64:$FRA))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCPSGNs : XForm_18<4, 8,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfcpsgn $FRT, $FRA, $FRB", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT, (fcopysign v4f32:$FRB, v4f32:$FRA))]>;
|
|
|
|
|
|
|
|
def QVALIGNI : Z23Form_1<4, 5,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, u2imm:$idx),
|
|
|
|
"qvaligni $FRT, $FRA, $FRB, $idx", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT,
|
|
|
|
(PPCqvaligni v4f64:$FRA, v4f64:$FRB,
|
|
|
|
(i32 imm:$idx)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVALIGNIs : Z23Form_1<4, 5,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, u2imm:$idx),
|
|
|
|
"qvaligni $FRT, $FRA, $FRB, $idx", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT,
|
|
|
|
(PPCqvaligni v4f32:$FRA, v4f32:$FRB,
|
|
|
|
(i32 imm:$idx)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVALIGNIb : Z23Form_1<4, 5,
|
|
|
|
(outs qbrc:$FRT), (ins qbrc:$FRA, qbrc:$FRB, u2imm:$idx),
|
|
|
|
"qvaligni $FRT, $FRA, $FRB, $idx", IIC_VecPerm,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(PPCqvaligni v4i1:$FRA, v4i1:$FRB,
|
|
|
|
(i32 imm:$idx)))]>;
|
|
|
|
|
|
|
|
def QVESPLATI : Z23Form_2<4, 37,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, u2imm:$idx),
|
|
|
|
"qvesplati $FRT, $FRA, $idx", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT,
|
|
|
|
(PPCqvesplati v4f64:$FRA, (i32 imm:$idx)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVESPLATIs : Z23Form_2<4, 37,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, u2imm:$idx),
|
|
|
|
"qvesplati $FRT, $FRA, $idx", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT,
|
|
|
|
(PPCqvesplati v4f32:$FRA, (i32 imm:$idx)))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVESPLATIb : Z23Form_2<4, 37,
|
|
|
|
(outs qbrc:$FRT), (ins qbrc:$FRA, u2imm:$idx),
|
|
|
|
"qvesplati $FRT, $FRA, $idx", IIC_VecPerm,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(PPCqvesplati v4i1:$FRA, (i32 imm:$idx)))]>;
|
|
|
|
|
|
|
|
def QVFPERM : AForm_1<4, 6,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfperm $FRT, $FRA, $FRB, $FRC", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT,
|
|
|
|
(PPCqvfperm v4f64:$FRA, v4f64:$FRB, v4f64:$FRC))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFPERMs : AForm_1<4, 6,
|
|
|
|
(outs qsrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB, qfrc:$FRC),
|
|
|
|
"qvfperm $FRT, $FRA, $FRB, $FRC", IIC_VecPerm,
|
|
|
|
[(set v4f32:$FRT,
|
|
|
|
(PPCqvfperm v4f32:$FRA, v4f32:$FRB, v4f64:$FRC))]>;
|
|
|
|
|
|
|
|
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
|
|
|
|
def QVGPCI : Z23Form_3<4, 133,
|
|
|
|
(outs qfrc:$FRT), (ins u12imm:$idx),
|
|
|
|
"qvgpci $FRT, $idx", IIC_VecPerm,
|
|
|
|
[(set v4f64:$FRT, (PPCqvgpci (u12:$idx)))]>;
|
|
|
|
|
|
|
|
// Compare Instruction
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFTSTNAN : QPXX18_Int<4, 64, "qvftstnan", int_ppc_qpx_qvftstnan>;
|
|
|
|
def QVFTSTNANb : XForm_18<4, 64, (outs qbrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvftstnan $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f64:$FRA, v4f64:$FRB, SETUO))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFTSTNANbs : XForm_18<4, 64, (outs qbrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvftstnan $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f32:$FRA, v4f32:$FRB, SETUO))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPLT : QPXX18_Int<4, 96, "qvfcmplt", int_ppc_qpx_qvfcmplt>;
|
|
|
|
def QVFCMPLTb : XForm_18<4, 96, (outs qbrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfcmplt $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f64:$FRA, v4f64:$FRB, SETOLT))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPLTbs : XForm_18<4, 96, (outs qbrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfcmplt $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f32:$FRA, v4f32:$FRB, SETOLT))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPGT : QPXX18_Int<4, 32, "qvfcmpgt", int_ppc_qpx_qvfcmpgt>;
|
|
|
|
def QVFCMPGTb : XForm_18<4, 32, (outs qbrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfcmpgt $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f64:$FRA, v4f64:$FRB, SETOGT))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPGTbs : XForm_18<4, 32, (outs qbrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfcmpgt $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f32:$FRA, v4f32:$FRB, SETOGT))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPEQ : QPXX18_Int<4, 0, "qvfcmpeq", int_ppc_qpx_qvfcmpeq>;
|
|
|
|
def QVFCMPEQb : XForm_18<4, 0, (outs qbrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB),
|
|
|
|
"qvfcmpeq $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f64:$FRA, v4f64:$FRB, SETOEQ))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFCMPEQbs : XForm_18<4, 0, (outs qbrc:$FRT), (ins qsrc:$FRA, qsrc:$FRB),
|
|
|
|
"qvfcmpeq $FRT, $FRA, $FRB", IIC_FPCompare,
|
|
|
|
[(set v4i1:$FRT,
|
|
|
|
(setcc v4f32:$FRA, v4f32:$FRB, SETOEQ))]>;
|
|
|
|
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFLOGICAL : XForm_20<4, 4,
|
|
|
|
(outs qfrc:$FRT), (ins qfrc:$FRA, qfrc:$FRB, u12imm:$tttt),
|
|
|
|
"qvflogical $FRT, $FRA, $FRB, $tttt", IIC_VecPerm, []>;
|
|
|
|
def QVFLOGICALb : XForm_20<4, 4,
|
|
|
|
(outs qbrc:$FRT), (ins qbrc:$FRA, qbrc:$FRB, u12imm:$tttt),
|
|
|
|
"qvflogical $FRT, $FRA, $FRB, $tttt", IIC_VecPerm, []>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVFLOGICALs : XForm_20<4, 4,
|
|
|
|
(outs qbrc:$FRT), (ins qbrc:$FRA, qbrc:$FRB, u12imm:$tttt),
|
|
|
|
"qvflogical $FRT, $FRA, $FRB, $tttt", IIC_VecPerm, []>;
|
|
|
|
|
|
|
|
// Load indexed instructions
|
2015-03-12 07:28:38 +08:00
|
|
|
let mayLoad = 1 in {
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVLFDX : XForm_1_memOp<31, 583,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfdx $FRT, $src", IIC_LdStLFD,
|
|
|
|
[(set v4f64:$FRT, (load xoaddr:$src))]>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
let isCodeGenOnly = 1 in
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVLFDXb : XForm_1_memOp<31, 583,
|
|
|
|
(outs qbrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfdx $FRT, $src", IIC_LdStLFD, []>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFDXA : XForm_1<31, 583,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfdxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFDUX : XForm_1<31, 615,
|
|
|
|
(outs qfrc:$FRT, ptr_rc_nor0:$ea_result),
|
|
|
|
(ins memrr:$src),
|
|
|
|
"qvlfdux $FRT, $src", IIC_LdStLFDU, []>,
|
|
|
|
RegConstraint<"$src.ptrreg = $ea_result">,
|
|
|
|
NoEncode<"$ea_result">;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFDUXA : XForm_1<31, 615,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfduxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVLFSX : XForm_1_memOp<31, 519,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfsx $FRT, $src", IIC_LdStLFD,
|
|
|
|
[(set v4f64:$FRT, (extloadv4f32 xoaddr:$src))]>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVLFSXb : XForm_1<31, 519,
|
|
|
|
(outs qbrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfsx $FRT, $src", IIC_LdStLFD,
|
|
|
|
[(set v4i1:$FRT, (PPCqvlfsb xoaddr:$src))]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVLFSXs : XForm_1_memOp<31, 519,
|
|
|
|
(outs qsrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfsx $FRT, $src", IIC_LdStLFD,
|
|
|
|
[(set v4f32:$FRT, (load xoaddr:$src))]>;
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFSXA : XForm_1<31, 519,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfsxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFSUX : XForm_1<31, 551,
|
|
|
|
(outs qsrc:$FRT, ptr_rc_nor0:$ea_result),
|
|
|
|
(ins memrr:$src),
|
|
|
|
"qvlfsux $FRT, $src", IIC_LdStLFDU, []>,
|
|
|
|
RegConstraint<"$src.ptrreg = $ea_result">,
|
|
|
|
NoEncode<"$ea_result">;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFSUXA : XForm_1<31, 551,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfsuxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFCDX : XForm_1<31, 71,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcdx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFCDXA : XForm_1<31, 71,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcdxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFCDUX : XForm_1<31, 103,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcdux $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFCDUXA : XForm_1<31, 103,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcduxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFCSX : XForm_1<31, 7,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcsx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVLFCSXs : XForm_1<31, 7,
|
|
|
|
(outs qsrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcsx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFCSXA : XForm_1<31, 7,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcsxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFCSUX : XForm_1<31, 39,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcsux $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFCSUXA : XForm_1<31, 39,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfcsuxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFIWAX : XForm_1<31, 871,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfiwax $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFIWAXA : XForm_1<31, 871,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfiwaxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
def QVLFIWZX : XForm_1<31, 839,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfiwzx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVLFIWZXA : XForm_1<31, 839,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlfiwzxa $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def QVLPCLDX : XForm_1<31, 582,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlpcldx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
def QVLPCLSX : XForm_1<31, 518,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlpclsx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVLPCLSXint : XForm_11<31, 518,
|
|
|
|
(outs qfrc:$FRT), (ins G8RC:$src),
|
|
|
|
"qvlpclsx $FRT, 0, $src", IIC_LdStLFD, []>;
|
|
|
|
def QVLPCRDX : XForm_1<31, 70,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlpcrdx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
def QVLPCRSX : XForm_1<31, 6,
|
|
|
|
(outs qfrc:$FRT), (ins memrr:$src),
|
|
|
|
"qvlpcrsx $FRT, $src", IIC_LdStLFD, []>;
|
|
|
|
|
|
|
|
// Store indexed instructions
|
|
|
|
let mayStore = 1 in {
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVSTFDX : XForm_8_memOp<31, 711,
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdx $FRT, $dst", IIC_LdStSTFD,
|
|
|
|
[(store qfrc:$FRT, xoaddr:$dst)]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVSTFDXb : XForm_8_memOp<31, 711,
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(outs), (ins qbrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdx $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFDXA : XForm_8<31, 711,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFDUX : XForm_8<31, 743, (outs ptr_rc_nor0:$ea_res),
|
|
|
|
(ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdux $FRT, $dst", IIC_LdStSTFDU, []>,
|
|
|
|
RegConstraint<"$dst.ptrreg = $ea_res">,
|
|
|
|
NoEncode<"$ea_res">;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFDUXA : XForm_8<31, 743,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfduxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFDXI : XForm_8<31, 709,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFDXIA : XForm_8<31, 709,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfdxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFDUXI : XForm_8<31, 741,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfduxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFDUXIA : XForm_8<31, 741,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfduxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVSTFSX : XForm_8_memOp<31, 647,
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsx $FRT, $dst", IIC_LdStSTFD,
|
|
|
|
[(truncstorev4f32 qfrc:$FRT, xoaddr:$dst)]>;
|
|
|
|
let isCodeGenOnly = 1 in
|
2018-03-27 01:39:18 +08:00
|
|
|
def QVSTFSXs : XForm_8_memOp<31, 647,
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(outs), (ins qsrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsx $FRT, $dst", IIC_LdStSTFD,
|
|
|
|
[(store qsrc:$FRT, xoaddr:$dst)]>;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFSXA : XForm_8<31, 647,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFSUX : XForm_8<31, 679, (outs ptr_rc_nor0:$ea_res),
|
|
|
|
(ins qsrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsux $FRT, $dst", IIC_LdStSTFDU, []>,
|
|
|
|
RegConstraint<"$dst.ptrreg = $ea_res">,
|
|
|
|
NoEncode<"$ea_res">;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVSTFSUXs: XForm_8<31, 679, (outs ptr_rc_nor0:$ea_res),
|
|
|
|
(ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsux $FRT, $dst", IIC_LdStSTFDU, []>,
|
|
|
|
RegConstraint<"$dst.ptrreg = $ea_res">,
|
|
|
|
NoEncode<"$ea_res">;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFSUXA : XForm_8<31, 679,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsuxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFSXI : XForm_8<31, 645,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFSXIA : XForm_8<31, 645,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFSUXI : XForm_8<31, 677,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsuxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFSUXIA : XForm_8<31, 677,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfsuxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCDX : XForm_8<31, 199,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcdx $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCDXA : XForm_8<31, 199,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcdxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCSX : XForm_8<31, 135,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsx $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let isCodeGenOnly = 1 in
|
|
|
|
def QVSTFCSXs : XForm_8<31, 135,
|
|
|
|
(outs), (ins qsrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsx $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCSXA : XForm_8<31, 135,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCDUX : XForm_8<31, 231,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcdux $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCDUXA : XForm_8<31, 231,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcduxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCSUX : XForm_8<31, 167,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsux $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCSUXA : XForm_8<31, 167,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsuxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCDXI : XForm_8<31, 197,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcdxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCDXIA : XForm_8<31, 197,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcdxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCSXI : XForm_8<31, 133,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCSXIA : XForm_8<31, 133,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCDUXI : XForm_8<31, 229,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcduxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCDUXIA : XForm_8<31, 229,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcduxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFCSUXI : XForm_8<31, 165,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsuxi $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFCSUXIA : XForm_8<31, 165,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfcsuxia $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
|
|
|
|
def QVSTFIWX : XForm_8<31, 967,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfiwx $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
let RC = 1 in
|
|
|
|
def QVSTFIWXA : XForm_8<31, 967,
|
|
|
|
(outs), (ins qfrc:$FRT, memrr:$dst),
|
|
|
|
"qvstfiwxa $FRT, $dst", IIC_LdStSTFD, []>;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
} // neverHasSideEffects
|
|
|
|
}
|
|
|
|
|
|
|
|
def : InstAlias<"qvfclr $FRT",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRT, qbrc:$FRT, 0)>;
|
|
|
|
def : InstAlias<"qvfand $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 1)>;
|
|
|
|
def : InstAlias<"qvfandc $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 4)>;
|
|
|
|
def : InstAlias<"qvfctfb $FRT, $FRA",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRA, 5)>;
|
|
|
|
def : InstAlias<"qvfxor $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 6)>;
|
|
|
|
def : InstAlias<"qvfor $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 7)>;
|
|
|
|
def : InstAlias<"qvfnor $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 8)>;
|
|
|
|
def : InstAlias<"qvfequ $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 9)>;
|
|
|
|
def : InstAlias<"qvfnot $FRT, $FRA",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRA, 10)>;
|
|
|
|
def : InstAlias<"qvforc $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 13)>;
|
|
|
|
def : InstAlias<"qvfnand $FRT, $FRA, $FRB",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRA, qbrc:$FRB, 14)>;
|
|
|
|
def : InstAlias<"qvfset $FRT",
|
|
|
|
(QVFLOGICALb qbrc:$FRT, qbrc:$FRT, qbrc:$FRT, 15)>;
|
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Additional QPX Patterns
|
|
|
|
//
|
|
|
|
|
|
|
|
def : Pat<(v4f64 (scalar_to_vector f64:$A)),
|
|
|
|
(INSERT_SUBREG (v4f64 (IMPLICIT_DEF)), $A, sub_64)>;
|
|
|
|
def : Pat<(v4f32 (scalar_to_vector f32:$A)),
|
|
|
|
(INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), $A, sub_64)>;
|
|
|
|
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f64 (extractelt v4f64:$S, 0)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG $S, sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f32 (extractelt v4f32:$S, 0)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG $S, sub_64)>;
|
|
|
|
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f64 (extractelt v4f64:$S, 1)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATI $S, 1), sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f64 (extractelt v4f64:$S, 2)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATI $S, 2), sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f64 (extractelt v4f64:$S, 3)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATI $S, 3), sub_64)>;
|
|
|
|
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f32 (extractelt v4f32:$S, 1)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATIs $S, 1), sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f32 (extractelt v4f32:$S, 2)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATIs $S, 2), sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f32 (extractelt v4f32:$S, 3)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVESPLATIs $S, 3), sub_64)>;
|
|
|
|
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f64 (extractelt v4f64:$S, i64:$F)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVFPERM $S, $S,
|
|
|
|
(QVLPCLSXint (RLDICR $F, 2,
|
|
|
|
/* 63-2 = */ 61))),
|
|
|
|
sub_64)>;
|
2015-12-12 03:20:16 +08:00
|
|
|
def : Pat<(f32 (extractelt v4f32:$S, i64:$F)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(EXTRACT_SUBREG (QVFPERMs $S, $S,
|
|
|
|
(QVLPCLSXint (RLDICR $F, 2,
|
|
|
|
/* 63-2 = */ 61))),
|
|
|
|
sub_64)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfperm v4f64:$A, v4f64:$B, v4f64:$C),
|
|
|
|
(QVFPERM $A, $B, $C)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfcpsgn v4f64:$A, v4f64:$B),
|
|
|
|
(QVFCPSGN $A, $B)>;
|
|
|
|
|
|
|
|
// FCOPYSIGN's operand types need not agree.
|
|
|
|
def : Pat<(fcopysign v4f64:$frB, v4f32:$frA),
|
|
|
|
(QVFCPSGN (COPY_TO_REGCLASS $frA, QFRC), $frB)>;
|
|
|
|
def : Pat<(fcopysign QSRC:$frB, QFRC:$frA),
|
|
|
|
(QVFCPSGNs (COPY_TO_REGCLASS $frA, QSRC), $frB)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfneg v4f64:$A), (QVFNEG $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfabs v4f64:$A), (QVFABS $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfnabs v4f64:$A), (QVFNABS $A)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfriz v4f64:$A), (QVFRIZ $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfrin v4f64:$A), (QVFRIN $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfrip v4f64:$A), (QVFRIP $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfrim v4f64:$A), (QVFRIM $A)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfre v4f64:$A), (QVFRE $A)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfrsqrte v4f64:$A), (QVFRSQRTE $A)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfadd v4f64:$A, v4f64:$B),
|
|
|
|
(QVFADD $A, $B)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfsub v4f64:$A, v4f64:$B),
|
|
|
|
(QVFSUB $A, $B)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfmul v4f64:$A, v4f64:$B),
|
|
|
|
(QVFMUL $A, $B)>;
|
|
|
|
|
|
|
|
// Additional QVFNMSUB patterns: -a*c + b == -(a*c - b)
|
|
|
|
def : Pat<(fma (fneg v4f64:$A), v4f64:$C, v4f64:$B),
|
|
|
|
(QVFNMSUB $A, $B, $C)>;
|
|
|
|
def : Pat<(fma v4f64:$A, (fneg v4f64:$C), v4f64:$B),
|
|
|
|
(QVFNMSUB $A, $B, $C)>;
|
|
|
|
def : Pat<(fma (fneg v4f32:$A), v4f32:$C, v4f32:$B),
|
|
|
|
(QVFNMSUBSs $A, $B, $C)>;
|
|
|
|
def : Pat<(fma v4f32:$A, (fneg v4f32:$C), v4f32:$B),
|
|
|
|
(QVFNMSUBSs $A, $B, $C)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvfmadd v4f64:$A, v4f64:$B, v4f64:$C),
|
|
|
|
(QVFMADD $A, $B, $C)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfnmadd v4f64:$A, v4f64:$B, v4f64:$C),
|
|
|
|
(QVFNMADD $A, $B, $C)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfmsub v4f64:$A, v4f64:$B, v4f64:$C),
|
|
|
|
(QVFMSUB $A, $B, $C)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvfnmsub v4f64:$A, v4f64:$B, v4f64:$C),
|
|
|
|
(QVFNMSUB $A, $B, $C)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfd xoaddr:$src),
|
|
|
|
(QVLFDX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfda xoaddr:$src),
|
|
|
|
(QVLFDXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfs xoaddr:$src),
|
|
|
|
(QVLFSX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfsa xoaddr:$src),
|
|
|
|
(QVLFSXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfcda xoaddr:$src),
|
|
|
|
(QVLFCDXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfcd xoaddr:$src),
|
|
|
|
(QVLFCDX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfcsa xoaddr:$src),
|
|
|
|
(QVLFCSXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfcs xoaddr:$src),
|
|
|
|
(QVLFCSX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfda xoaddr:$src),
|
|
|
|
(QVLFDXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfiwaa xoaddr:$src),
|
|
|
|
(QVLFIWAXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfiwa xoaddr:$src),
|
|
|
|
(QVLFIWAX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfiwza xoaddr:$src),
|
|
|
|
(QVLFIWZXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfiwz xoaddr:$src),
|
|
|
|
(QVLFIWZX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlfsa xoaddr:$src),
|
|
|
|
(QVLFSXA xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlpcld xoaddr:$src),
|
|
|
|
(QVLPCLDX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlpcls xoaddr:$src),
|
|
|
|
(QVLPCLSX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlpcrd xoaddr:$src),
|
|
|
|
(QVLPCRDX xoaddr:$src)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvlpcrs xoaddr:$src),
|
|
|
|
(QVLPCRSX xoaddr:$src)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfd v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFDX $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfs v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFSX $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfcda v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFCDXA $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfcd v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFCDX $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfcsa v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFCSXA $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfcs v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFCSX $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfda v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFDXA $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfiwa v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFIWXA $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfiw v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFIWX $T, xoaddr:$dst)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvstfsa v4f64:$T, xoaddr:$dst),
|
|
|
|
(QVSTFSXA $T, xoaddr:$dst)>;
|
|
|
|
|
|
|
|
def : Pat<(pre_store v4f64:$rS, iPTR:$ptrreg, iPTR:$ptroff),
|
|
|
|
(QVSTFDUX $rS, $ptrreg, $ptroff)>;
|
|
|
|
def : Pat<(pre_store v4f32:$rS, iPTR:$ptrreg, iPTR:$ptroff),
|
|
|
|
(QVSTFSUX $rS, $ptrreg, $ptroff)>;
|
|
|
|
def : Pat<(pre_truncstv4f32 v4f64:$rS, iPTR:$ptrreg, iPTR:$ptroff),
|
|
|
|
(QVSTFSUXs $rS, $ptrreg, $ptroff)>;
|
|
|
|
|
|
|
|
def : Pat<(int_ppc_qpx_qvflogical v4f64:$A, v4f64:$B, (i32 imm:$idx)),
|
|
|
|
(QVFLOGICAL $A, $B, imm:$idx)>;
|
|
|
|
def : Pat<(int_ppc_qpx_qvgpci (u12:$idx)),
|
|
|
|
(QVGPCI imm:$idx)>;
|
|
|
|
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETOGE),
|
|
|
|
(QVFLOGICALb (QVFCMPLTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETOLE),
|
|
|
|
(QVFLOGICALb (QVFCMPGTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETONE),
|
|
|
|
(QVFLOGICALb (QVFCMPEQb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETO),
|
|
|
|
(QVFLOGICALb (QVFTSTNANb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETUEQ),
|
|
|
|
(QVFLOGICALb (QVFCMPEQb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETUGT),
|
|
|
|
(QVFLOGICALb (QVFCMPGTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETUGE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANb $FRA, $FRB),
|
|
|
|
(QVFCMPLTb $FRA, $FRB), (i32 13))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETULT),
|
|
|
|
(QVFLOGICALb (QVFCMPLTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETULE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANb $FRA, $FRB),
|
|
|
|
(QVFCMPGTb $FRA, $FRB), (i32 13))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETUNE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANb $FRA, $FRB),
|
|
|
|
(QVFCMPEQb $FRA, $FRB), (i32 13))>;
|
|
|
|
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETEQ),
|
|
|
|
(QVFCMPEQb $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETGT),
|
|
|
|
(QVFCMPGTb $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETGE),
|
|
|
|
(QVFLOGICALb (QVFCMPLTb $FRA, $FRB),
|
|
|
|
(QVFCMPLTb $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETLT),
|
|
|
|
(QVFCMPLTb $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETLE),
|
|
|
|
(QVFLOGICALb (QVFCMPGTb $FRA, $FRB),
|
|
|
|
(QVFCMPGTb $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f64:$FRA, v4f64:$FRB, SETNE),
|
|
|
|
(QVFLOGICALb (QVFCMPEQb $FRA, $FRB),
|
|
|
|
(QVFCMPEQb $FRA, $FRB), (i32 10))>;
|
|
|
|
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETOGE),
|
|
|
|
(QVFLOGICALb (QVFCMPLTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETOLE),
|
|
|
|
(QVFLOGICALb (QVFCMPGTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETONE),
|
|
|
|
(QVFLOGICALb (QVFCMPEQbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 8))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETO),
|
|
|
|
(QVFLOGICALb (QVFTSTNANbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETUEQ),
|
|
|
|
(QVFLOGICALb (QVFCMPEQbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETUGT),
|
|
|
|
(QVFLOGICALb (QVFCMPGTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETUGE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANbs $FRA, $FRB),
|
|
|
|
(QVFCMPLTbs $FRA, $FRB), (i32 13))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETULT),
|
|
|
|
(QVFLOGICALb (QVFCMPLTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRA, $FRB), (i32 7))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETULE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANbs $FRA, $FRB),
|
|
|
|
(QVFCMPGTbs $FRA, $FRB), (i32 13))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETUNE),
|
|
|
|
(QVFLOGICALb (QVFTSTNANbs $FRA, $FRB),
|
|
|
|
(QVFCMPEQbs $FRA, $FRB), (i32 13))>;
|
|
|
|
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETEQ),
|
|
|
|
(QVFCMPEQbs $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETGT),
|
|
|
|
(QVFCMPGTbs $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETGE),
|
|
|
|
(QVFLOGICALb (QVFCMPLTbs $FRA, $FRB),
|
|
|
|
(QVFCMPLTbs $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETLT),
|
|
|
|
(QVFCMPLTbs $FRA, $FRB)>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETLE),
|
|
|
|
(QVFLOGICALb (QVFCMPGTbs $FRA, $FRB),
|
|
|
|
(QVFCMPGTbs $FRA, $FRB), (i32 10))>;
|
|
|
|
def : Pat<(setcc v4f32:$FRA, v4f32:$FRB, SETNE),
|
|
|
|
(QVFLOGICALb (QVFCMPEQbs $FRA, $FRB),
|
|
|
|
(QVFCMPEQbs $FRA, $FRB), (i32 10))>;
|
|
|
|
|
|
|
|
def : Pat<(and v4i1:$FRA, (not v4i1:$FRB)),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 4))>;
|
|
|
|
def : Pat<(not (or v4i1:$FRA, v4i1:$FRB)),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 8))>;
|
|
|
|
def : Pat<(not (xor v4i1:$FRA, v4i1:$FRB)),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 9))>;
|
|
|
|
def : Pat<(or v4i1:$FRA, (not v4i1:$FRB)),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 13))>;
|
|
|
|
def : Pat<(not (and v4i1:$FRA, v4i1:$FRB)),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 14))>;
|
|
|
|
|
|
|
|
def : Pat<(and v4i1:$FRA, v4i1:$FRB),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 1))>;
|
|
|
|
def : Pat<(or v4i1:$FRA, v4i1:$FRB),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 7))>;
|
|
|
|
def : Pat<(xor v4i1:$FRA, v4i1:$FRB),
|
|
|
|
(QVFLOGICALb $FRA, $FRB, (i32 6))>;
|
|
|
|
def : Pat<(not v4i1:$FRA),
|
|
|
|
(QVFLOGICALb $FRA, $FRA, (i32 10))>;
|
|
|
|
|
2016-08-19 04:08:15 +08:00
|
|
|
def : Pat<(v4f64 (fpextend v4f32:$src)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(COPY_TO_REGCLASS $src, QFRC)>;
|
|
|
|
|
|
|
|
def : Pat<(v4f32 (fround_exact v4f64:$src)),
|
|
|
|
(COPY_TO_REGCLASS $src, QSRC)>;
|
|
|
|
|
|
|
|
// Extract the underlying floating-point values from the
|
|
|
|
// QPX (-1.0, 1.0) boolean representation.
|
|
|
|
def : Pat<(v4f64 (PPCqbflt v4i1:$src)),
|
|
|
|
(COPY_TO_REGCLASS $src, QFRC)>;
|
|
|
|
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETLT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETULT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETLE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QFRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETULE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QFRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETEQ)),
|
|
|
|
(SELECT_QFRC (CREQV $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETGE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QFRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETUGE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QFRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETGT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QFRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETUGT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QFRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f64 (selectcc i1:$lhs, i1:$rhs, v4f64:$tval, v4f64:$fval, SETNE)),
|
|
|
|
(SELECT_QFRC (CRXOR $lhs, $rhs), $tval, $fval)>;
|
|
|
|
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETLT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETULT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETLE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QSRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETULE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QSRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETEQ)),
|
|
|
|
(SELECT_QSRC (CREQV $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETGE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QSRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETUGE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QSRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETGT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETUGT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4f32 (selectcc i1:$lhs, i1:$rhs, v4f32:$tval, v4f32:$fval, SETNE)),
|
|
|
|
(SELECT_QSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
|
|
|
|
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETLT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QBRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETULT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QBRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETLE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QBRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETULE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QBRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETEQ)),
|
|
|
|
(SELECT_QBRC (CREQV $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETGE)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QBRC (CRORC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETUGE)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QBRC (CRORC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETGT)),
|
2015-08-31 06:12:50 +08:00
|
|
|
(SELECT_QBRC (CRANDC $rhs, $lhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETUGT)),
|
[PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
2015-02-25 09:06:45 +08:00
|
|
|
(SELECT_QBRC (CRANDC $lhs, $rhs), $tval, $fval)>;
|
|
|
|
def : Pat<(v4i1 (selectcc i1:$lhs, i1:$rhs, v4i1:$tval, v4i1:$fval, SETNE)),
|
|
|
|
(SELECT_QBRC (CRXOR $lhs, $rhs), $tval, $fval)>;
|
|
|
|
|
|
|
|
} // end HasQPX
|
|
|
|
|
|
|
|
let Predicates = [HasQPX, NoNaNsFPMath] in {
|
|
|
|
def : Pat<(fminnum v4f64:$FRA, v4f64:$FRB),
|
|
|
|
(QVFSELb (QVFCMPLTb $FRA, $FRB), $FRB, $FRA)>;
|
|
|
|
def : Pat<(fmaxnum v4f64:$FRA, v4f64:$FRB),
|
|
|
|
(QVFSELb (QVFCMPGTb $FRA, $FRB), $FRB, $FRA)>;
|
|
|
|
|
|
|
|
def : Pat<(fminnum v4f32:$FRA, v4f32:$FRB),
|
|
|
|
(QVFSELbs (QVFCMPLTbs $FRA, $FRB), $FRB, $FRA)>;
|
|
|
|
def : Pat<(fmaxnum v4f32:$FRA, v4f32:$FRB),
|
|
|
|
(QVFSELbs (QVFCMPGTbs $FRA, $FRB), $FRB, $FRA)>;
|
|
|
|
}
|
|
|
|
|
|
|
|
let Predicates = [HasQPX, NaNsFPMath] in {
|
|
|
|
// When either of these operands is NaN, we should return the other operand.
|
|
|
|
// QVFCMPLT/QVFCMPGT return false is either operand is NaN, which means we need
|
|
|
|
// to explicitly or with a NaN test on the second operand.
|
|
|
|
def : Pat<(fminnum v4f64:$FRA, v4f64:$FRB),
|
|
|
|
(QVFSELb (QVFLOGICALb (QVFCMPLTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRB, $FRB), (i32 7)),
|
|
|
|
$FRB, $FRA)>;
|
|
|
|
def : Pat<(fmaxnum v4f64:$FRA, v4f64:$FRB),
|
|
|
|
(QVFSELb (QVFLOGICALb (QVFCMPGTb $FRA, $FRB),
|
|
|
|
(QVFTSTNANb $FRB, $FRB), (i32 7)),
|
|
|
|
$FRB, $FRA)>;
|
|
|
|
|
|
|
|
def : Pat<(fminnum v4f32:$FRA, v4f32:$FRB),
|
|
|
|
(QVFSELbs (QVFLOGICALb (QVFCMPLTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRB, $FRB), (i32 7)),
|
|
|
|
$FRB, $FRA)>;
|
|
|
|
def : Pat<(fmaxnum v4f32:$FRA, v4f32:$FRB),
|
|
|
|
(QVFSELbs (QVFLOGICALb (QVFCMPGTbs $FRA, $FRB),
|
|
|
|
(QVFTSTNANbs $FRB, $FRB), (i32 7)),
|
|
|
|
$FRB, $FRA)>;
|
|
|
|
}
|
|
|
|
|