mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
883c64377d
This change enables tracking i1 values in the PowerPC backend using the condition register bits. These bits can be treated on PowerPC as separate registers; individual bit operations (and, or, xor, etc.) are supported. Tracking booleans in CR bits has several advantages: - Reduction in register pressure (because we no longer need GPRs to store boolean values). - Logical operations on booleans can be handled more efficiently; we used to have to move all results from comparisons into GPRs, perform promoted logical operations in GPRs, and then move the result back into condition register bits to be used by conditional branches. This can be very inefficient, because the throughput of these CR <-> GPR moves have high latency and low throughput (especially when other associated instructions are accounted for). - On the POWER7 and similar cores, we can increase total throughput by using the CR bits. CR bit operations have a dedicated functional unit. Most of this is more-or-less mechanical: Adjustments were needed in the calling-convention code, support was added for spilling/restoring individual condition-register bits, and conditional branch instruction definitions taking specific CR bits were added (plus patterns and code for generating bit-level operations). This is enabled by default when running at -O2 and higher. For -O0 and -O1, where the ability to debug is more important, this feature is disabled by default. Individual CR bits do not have assigned DWARF register numbers, and storing values in CR bits makes them invisible to the debugger. It is critical, however, that we don't move i1 values that have been promoted to larger values (such as those passed as function arguments) into bit registers only to quickly turn around and move the values back into GPRs (such as happens when values are returned by functions). A pair of target-specific DAG combines are added to remove the trunc/extends in: trunc(binary-ops(binary-ops(zext(x), zext(y)), ...) and: zext(binary-ops(binary-ops(trunc(x), trunc(y)), ...) In short, we only want to use CR bits where some of the i1 values come from comparisons or are used by conditional branches or selects. To put it another way, if we can do the entire i1 computation in GPRs, then we probably should (on the POWER7, the GPR-operation throughput is higher, and for all cores, the CR <-> GPR moves are expensive). POWER7 test-suite performance results (from 10 runs in each configuration): SingleSource/Benchmarks/Misc/mandel-2: 35% speedup MultiSource/Benchmarks/Prolangs-C++/city/city: 21% speedup MultiSource/Benchmarks/MiBench/automotive-susan: 23% speedup SingleSource/Benchmarks/CoyoteBench/huffbench: 13% speedup SingleSource/Benchmarks/Misc-C++/Large/sphereflake: 13% speedup SingleSource/Benchmarks/Misc-C++/mandel-text: 10% speedup SingleSource/Benchmarks/Misc-C++-EH/spirit: 10% slowdown MultiSource/Applications/lemon/lemon: 8% slowdown llvm-svn: 202451
313 lines
16 KiB
TableGen
313 lines
16 KiB
TableGen
//===-- PPC.td - Describe the PowerPC Target Machine -------*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This is the top level entry point for the PowerPC target.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Get the target-independent interfaces which we are implementing.
|
|
//
|
|
include "llvm/Target/Target.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PowerPC Subtarget features.
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// CPU Directives //
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def Directive440 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_440", "">;
|
|
def Directive601 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_601", "">;
|
|
def Directive602 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_602", "">;
|
|
def Directive603 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_603", "">;
|
|
def Directive604 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_603", "">;
|
|
def Directive620 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_603", "">;
|
|
def Directive7400: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_7400", "">;
|
|
def Directive750 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_750", "">;
|
|
def Directive970 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_970", "">;
|
|
def Directive32 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_32", "">;
|
|
def Directive64 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_64", "">;
|
|
def DirectiveA2 : SubtargetFeature<"", "DarwinDirective", "PPC::DIR_A2", "">;
|
|
def DirectiveE500mc : SubtargetFeature<"", "DarwinDirective",
|
|
"PPC::DIR_E500mc", "">;
|
|
def DirectiveE5500 : SubtargetFeature<"", "DarwinDirective",
|
|
"PPC::DIR_E5500", "">;
|
|
def DirectivePwr3: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR3", "">;
|
|
def DirectivePwr4: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR4", "">;
|
|
def DirectivePwr5: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR5", "">;
|
|
def DirectivePwr5x: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR5X", "">;
|
|
def DirectivePwr6: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR6", "">;
|
|
def DirectivePwr6x: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR6X", "">;
|
|
def DirectivePwr7: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR7", "">;
|
|
|
|
def Feature64Bit : SubtargetFeature<"64bit","Has64BitSupport", "true",
|
|
"Enable 64-bit instructions">;
|
|
def Feature64BitRegs : SubtargetFeature<"64bitregs","Use64BitRegs", "true",
|
|
"Enable 64-bit registers usage for ppc32 [beta]">;
|
|
def FeatureCRBits : SubtargetFeature<"crbits", "UseCRBits", "true",
|
|
"Use condition-register bits individually">;
|
|
def FeatureAltivec : SubtargetFeature<"altivec","HasAltivec", "true",
|
|
"Enable Altivec instructions">;
|
|
def FeatureMFOCRF : SubtargetFeature<"mfocrf","HasMFOCRF", "true",
|
|
"Enable the MFOCRF instruction">;
|
|
def FeatureFSqrt : SubtargetFeature<"fsqrt","HasFSQRT", "true",
|
|
"Enable the fsqrt instruction">;
|
|
def FeatureFCPSGN : SubtargetFeature<"fcpsgn", "HasFCPSGN", "true",
|
|
"Enable the fcpsgn instruction">;
|
|
def FeatureFRE : SubtargetFeature<"fre", "HasFRE", "true",
|
|
"Enable the fre instruction">;
|
|
def FeatureFRES : SubtargetFeature<"fres", "HasFRES", "true",
|
|
"Enable the fres instruction">;
|
|
def FeatureFRSQRTE : SubtargetFeature<"frsqrte", "HasFRSQRTE", "true",
|
|
"Enable the frsqrte instruction">;
|
|
def FeatureFRSQRTES : SubtargetFeature<"frsqrtes", "HasFRSQRTES", "true",
|
|
"Enable the frsqrtes instruction">;
|
|
def FeatureRecipPrec : SubtargetFeature<"recipprec", "HasRecipPrec", "true",
|
|
"Assume higher precision reciprocal estimates">;
|
|
def FeatureSTFIWX : SubtargetFeature<"stfiwx","HasSTFIWX", "true",
|
|
"Enable the stfiwx instruction">;
|
|
def FeatureLFIWAX : SubtargetFeature<"lfiwax","HasLFIWAX", "true",
|
|
"Enable the lfiwax instruction">;
|
|
def FeatureFPRND : SubtargetFeature<"fprnd", "HasFPRND", "true",
|
|
"Enable the fri[mnpz] instructions">;
|
|
def FeatureFPCVT : SubtargetFeature<"fpcvt", "HasFPCVT", "true",
|
|
"Enable fc[ft]* (unsigned and single-precision) and lfiwzx instructions">;
|
|
def FeatureISEL : SubtargetFeature<"isel","HasISEL", "true",
|
|
"Enable the isel instruction">;
|
|
def FeaturePOPCNTD : SubtargetFeature<"popcntd","HasPOPCNTD", "true",
|
|
"Enable the popcnt[dw] instructions">;
|
|
def FeatureLDBRX : SubtargetFeature<"ldbrx","HasLDBRX", "true",
|
|
"Enable the ldbrx instruction">;
|
|
def FeatureBookE : SubtargetFeature<"booke", "IsBookE", "true",
|
|
"Enable Book E instructions">;
|
|
def FeatureQPX : SubtargetFeature<"qpx","HasQPX", "true",
|
|
"Enable QPX instructions">;
|
|
def FeatureVSX : SubtargetFeature<"vsx","HasVSX", "true",
|
|
"Enable VSX instructions">;
|
|
|
|
def DeprecatedMFTB : SubtargetFeature<"", "DeprecatedMFTB", "true",
|
|
"Treat mftb as deprecated">;
|
|
def DeprecatedDST : SubtargetFeature<"", "DeprecatedDST", "true",
|
|
"Treat vector data stream cache control instructions as deprecated">;
|
|
|
|
// Note: Future features to add when support is extended to more
|
|
// recent ISA levels:
|
|
//
|
|
// CMPB p6, p6x, p7 cmpb
|
|
// DFP p6, p6x, p7 decimal floating-point instructions
|
|
// POPCNTB p5 through p7 popcntb and related instructions
|
|
// VSX p7 vector-scalar instruction set
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Classes used for relation maps.
|
|
//===----------------------------------------------------------------------===//
|
|
// RecFormRel - Filter class used to relate non-record-form instructions with
|
|
// their record-form variants.
|
|
class RecFormRel;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Relation Map Definitions.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def getRecordFormOpcode : InstrMapping {
|
|
let FilterClass = "RecFormRel";
|
|
// Instructions with the same BaseName and Interpretation64Bit values
|
|
// form a row.
|
|
let RowFields = ["BaseName", "Interpretation64Bit"];
|
|
// Instructions with the same RC value form a column.
|
|
let ColFields = ["RC"];
|
|
// The key column are the non-record-form instructions.
|
|
let KeyCol = ["0"];
|
|
// Value columns RC=1
|
|
let ValueCols = [["1"]];
|
|
}
|
|
|
|
def getNonRecordFormOpcode : InstrMapping {
|
|
let FilterClass = "RecFormRel";
|
|
// Instructions with the same BaseName and Interpretation64Bit values
|
|
// form a row.
|
|
let RowFields = ["BaseName", "Interpretation64Bit"];
|
|
// Instructions with the same RC value form a column.
|
|
let ColFields = ["RC"];
|
|
// The key column are the record-form instructions.
|
|
let KeyCol = ["1"];
|
|
// Value columns are RC=0
|
|
let ValueCols = [["0"]];
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Register File Description
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "PPCRegisterInfo.td"
|
|
include "PPCSchedule.td"
|
|
include "PPCInstrInfo.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PowerPC processors supported.
|
|
//
|
|
|
|
def : Processor<"generic", G3Itineraries, [Directive32]>;
|
|
def : ProcessorModel<"440", PPC440Model, [Directive440, FeatureISEL,
|
|
FeatureFRES, FeatureFRSQRTE,
|
|
FeatureBookE, DeprecatedMFTB]>;
|
|
def : ProcessorModel<"450", PPC440Model, [Directive440, FeatureISEL,
|
|
FeatureFRES, FeatureFRSQRTE,
|
|
FeatureBookE, DeprecatedMFTB]>;
|
|
def : Processor<"601", G3Itineraries, [Directive601]>;
|
|
def : Processor<"602", G3Itineraries, [Directive602]>;
|
|
def : Processor<"603", G3Itineraries, [Directive603,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"603e", G3Itineraries, [Directive603,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"603ev", G3Itineraries, [Directive603,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"604", G3Itineraries, [Directive604,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"604e", G3Itineraries, [Directive604,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"620", G3Itineraries, [Directive620,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"750", G4Itineraries, [Directive750,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"g3", G3Itineraries, [Directive750,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"7400", G4Itineraries, [Directive7400, FeatureAltivec,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"g4", G4Itineraries, [Directive7400, FeatureAltivec,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"7450", G4PlusItineraries, [Directive7400, FeatureAltivec,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : Processor<"g4+", G4PlusItineraries, [Directive7400, FeatureAltivec,
|
|
FeatureFRES, FeatureFRSQRTE]>;
|
|
def : ProcessorModel<"970", G5Model,
|
|
[Directive970, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFSqrt,
|
|
FeatureFRES, FeatureFRSQRTE, FeatureSTFIWX,
|
|
Feature64Bit /*, Feature64BitRegs */]>;
|
|
def : ProcessorModel<"g5", G5Model,
|
|
[Directive970, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFSqrt, FeatureSTFIWX,
|
|
FeatureFRES, FeatureFRSQRTE,
|
|
Feature64Bit /*, Feature64BitRegs */,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : ProcessorModel<"e500mc", PPCE500mcModel,
|
|
[DirectiveE500mc, FeatureMFOCRF,
|
|
FeatureSTFIWX, FeatureBookE, FeatureISEL,
|
|
DeprecatedMFTB]>;
|
|
def : ProcessorModel<"e5500", PPCE5500Model,
|
|
[DirectiveE5500, FeatureMFOCRF, Feature64Bit,
|
|
FeatureSTFIWX, FeatureBookE, FeatureISEL,
|
|
DeprecatedMFTB]>;
|
|
def : ProcessorModel<"a2", PPCA2Model,
|
|
[DirectiveA2, FeatureBookE, FeatureMFOCRF,
|
|
FeatureFCPSGN, FeatureFSqrt, FeatureFRE, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureFRSQRTES, FeatureRecipPrec,
|
|
FeatureSTFIWX, FeatureLFIWAX,
|
|
FeatureFPRND, FeatureFPCVT, FeatureISEL,
|
|
FeaturePOPCNTD, FeatureLDBRX, Feature64Bit
|
|
/*, Feature64BitRegs */, DeprecatedMFTB]>;
|
|
def : ProcessorModel<"a2q", PPCA2Model,
|
|
[DirectiveA2, FeatureBookE, FeatureMFOCRF,
|
|
FeatureFCPSGN, FeatureFSqrt, FeatureFRE, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureFRSQRTES, FeatureRecipPrec,
|
|
FeatureSTFIWX, FeatureLFIWAX,
|
|
FeatureFPRND, FeatureFPCVT, FeatureISEL,
|
|
FeaturePOPCNTD, FeatureLDBRX, Feature64Bit
|
|
/*, Feature64BitRegs */, FeatureQPX, DeprecatedMFTB]>;
|
|
def : ProcessorModel<"pwr3", G5Model,
|
|
[DirectivePwr3, FeatureAltivec,
|
|
FeatureFRES, FeatureFRSQRTE, FeatureMFOCRF,
|
|
FeatureSTFIWX, Feature64Bit]>;
|
|
def : ProcessorModel<"pwr4", G5Model,
|
|
[DirectivePwr4, FeatureAltivec, FeatureMFOCRF,
|
|
FeatureFSqrt, FeatureFRES, FeatureFRSQRTE,
|
|
FeatureSTFIWX, Feature64Bit]>;
|
|
def : ProcessorModel<"pwr5", G5Model,
|
|
[DirectivePwr5, FeatureAltivec, FeatureMFOCRF,
|
|
FeatureFSqrt, FeatureFRE, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureFRSQRTES,
|
|
FeatureSTFIWX, Feature64Bit,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : ProcessorModel<"pwr5x", G5Model,
|
|
[DirectivePwr5x, FeatureAltivec, FeatureMFOCRF,
|
|
FeatureFSqrt, FeatureFRE, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureFRSQRTES,
|
|
FeatureSTFIWX, FeatureFPRND, Feature64Bit,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : ProcessorModel<"pwr6", G5Model,
|
|
[DirectivePwr6, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFCPSGN, FeatureFSqrt, FeatureFRE,
|
|
FeatureFRES, FeatureFRSQRTE, FeatureFRSQRTES,
|
|
FeatureRecipPrec, FeatureSTFIWX, FeatureLFIWAX,
|
|
FeatureFPRND, Feature64Bit /*, Feature64BitRegs */,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : ProcessorModel<"pwr6x", G5Model,
|
|
[DirectivePwr5x, FeatureAltivec, FeatureMFOCRF,
|
|
FeatureFCPSGN, FeatureFSqrt, FeatureFRE, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureFRSQRTES, FeatureRecipPrec,
|
|
FeatureSTFIWX, FeatureLFIWAX,
|
|
FeatureFPRND, Feature64Bit,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : ProcessorModel<"pwr7", P7Model,
|
|
[DirectivePwr7, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFCPSGN, FeatureFSqrt, FeatureFRE,
|
|
FeatureFRES, FeatureFRSQRTE, FeatureFRSQRTES,
|
|
FeatureRecipPrec, FeatureSTFIWX, FeatureLFIWAX,
|
|
FeatureFPRND, FeatureFPCVT, FeatureISEL,
|
|
FeaturePOPCNTD, FeatureLDBRX,
|
|
Feature64Bit /*, Feature64BitRegs */,
|
|
DeprecatedMFTB, DeprecatedDST]>;
|
|
def : Processor<"ppc", G3Itineraries, [Directive32]>;
|
|
def : ProcessorModel<"ppc64", G5Model,
|
|
[Directive64, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFSqrt, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureSTFIWX,
|
|
Feature64Bit /*, Feature64BitRegs */]>;
|
|
def : ProcessorModel<"ppc64le", G5Model,
|
|
[Directive64, FeatureAltivec,
|
|
FeatureMFOCRF, FeatureFSqrt, FeatureFRES,
|
|
FeatureFRSQRTE, FeatureSTFIWX,
|
|
Feature64Bit /*, Feature64BitRegs */]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Calling Conventions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "PPCCallingConv.td"
|
|
|
|
def PPCInstrInfo : InstrInfo {
|
|
let isLittleEndianEncoding = 1;
|
|
|
|
// FIXME: Unset this when no longer needed!
|
|
let decodePositionallyEncodedOperands = 1;
|
|
}
|
|
|
|
def PPCAsmParser : AsmParser {
|
|
let ShouldEmitMatchRegisterName = 0;
|
|
}
|
|
|
|
def PPCAsmParserVariant : AsmParserVariant {
|
|
int Variant = 0;
|
|
|
|
// We do not use hard coded registers in asm strings. However, some
|
|
// InstAlias definitions use immediate literals. Set RegisterPrefix
|
|
// so that those are not misinterpreted as registers.
|
|
string RegisterPrefix = "%";
|
|
}
|
|
|
|
def PPC : Target {
|
|
// Information about the instructions.
|
|
let InstructionSet = PPCInstrInfo;
|
|
|
|
let AssemblyParsers = [PPCAsmParser];
|
|
let AssemblyParserVariants = [PPCAsmParserVariant];
|
|
}
|