X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FARM%2FARM.td;h=baf051cc23b9e1974777793f701a9eba6a4fa260;hb=8a8d28b0392a27ff8e0c60c04561671023a08dc2;hp=bf95e99d8d724e80ed59e88973edec3ecd24f553;hpb=cb5ce6e62bcc15add9f0d1a79392c0cbb00ba861;p=oota-llvm.git diff --git a/lib/Target/ARM/ARM.td b/lib/Target/ARM/ARM.td index bf95e99d8d7..baf051cc23b 100644 --- a/lib/Target/ARM/ARM.td +++ b/lib/Target/ARM/ARM.td @@ -1,4 +1,4 @@ -//===- ARM.td - Describe the ARM Target Machine -----------------*- C++ -*-===// +//===- ARM.td - Describe the ARM Target Machine ------------*- tablegen -*-===// // // The LLVM Compiler Infrastructure // @@ -16,20 +16,36 @@ include "llvm/Target/Target.td" +//===----------------------------------------------------------------------===// +// ARM Subtarget state. +// + +def ModeThumb : SubtargetFeature<"thumb-mode", "InThumbMode", "true", + "Thumb mode">; + +def ModeNaCl : SubtargetFeature<"nacl-mode", "InNaClMode", "true", + "Native client mode">; + //===----------------------------------------------------------------------===// // ARM Subtarget features. // -def FeatureVFP2 : SubtargetFeature<"vfp2", "ARMFPUType", "VFPv2", +def FeatureVFP2 : SubtargetFeature<"vfp2", "HasVFPv2", "true", "Enable VFP2 instructions">; -def FeatureVFP3 : SubtargetFeature<"vfp3", "ARMFPUType", "VFPv3", - "Enable VFP3 instructions">; -def FeatureNEON : SubtargetFeature<"neon", "ARMFPUType", "NEON", - "Enable NEON instructions">; -def FeatureThumb2 : SubtargetFeature<"thumb2", "ThumbMode", "Thumb2", +def FeatureVFP3 : SubtargetFeature<"vfp3", "HasVFPv3", "true", + "Enable VFP3 instructions", + [FeatureVFP2]>; +def FeatureNEON : SubtargetFeature<"neon", "HasNEON", "true", + "Enable NEON instructions", + [FeatureVFP3]>; +def FeatureThumb2 : SubtargetFeature<"thumb2", "HasThumb2", "true", "Enable Thumb2 instructions">; +def FeatureNoARM : SubtargetFeature<"noarm", "NoARM", "true", + "Does not support ARM mode execution">; def FeatureFP16 : SubtargetFeature<"fp16", "HasFP16", "true", "Enable half-precision floating point">; +def FeatureD16 : SubtargetFeature<"d16", "HasD16", "true", + "Restrict VFP3 to 16 double registers">; def FeatureHWDiv : SubtargetFeature<"hwdiv", "HasHardwareDivide", "true", "Enable divide instructions">; def FeatureT2XtPk : SubtargetFeature<"t2xtpk", "HasT2ExtractPack", "true", @@ -38,47 +54,64 @@ def FeatureDB : SubtargetFeature<"db", "HasDataBarrier", "true", "Has data barrier (dmb / dsb) instructions">; def FeatureSlowFPBrcc : SubtargetFeature<"slow-fp-brcc", "SlowFPBrcc", "true", "FP compare + branch is slow">; +def FeatureVFPOnlySP : SubtargetFeature<"fp-only-sp", "FPOnlySP", "true", + "Floating point unit supports single precision only">; -// Some processors have multiply-accumulate instructions that don't -// play nicely with other VFP instructions, and it's generally better +// Some processors have FP multiply-accumulate instructions that don't +// play nicely with other VFP / NEON instructions, and it's generally better // to just not use them. -// FIXME: Currently, this is only flagged for Cortex-A8. It may be true for -// others as well. We should do more benchmarking and confirm one way or -// the other. -def FeatureHasSlowVMLx : SubtargetFeature<"vmlx", "SlowVMLx", "true", - "Disable VFP MAC instructions">; +def FeatureHasSlowFPVMLx : SubtargetFeature<"slowfpvmlx", "SlowFPVMLx", "true", + "Disable VFP / NEON MAC instructions">; + +// Cortex-A8 / A9 Advanced SIMD has multiplier accumulator forwarding. +def FeatureVMLxForwarding : SubtargetFeature<"vmlx-forwarding", + "HasVMLxForwarding", "true", + "Has multiplier accumulator forwarding">; + // Some processors benefit from using NEON instructions for scalar // single-precision FP operations. -def FeatureNEONForFP : SubtargetFeature<"neonfp", "UseNEONForSinglePrecisionFP", - "true", - "Use NEON for single precision FP">; +def FeatureNEONForFP : SubtargetFeature<"neonfp", "UseNEONForSinglePrecisionFP", + "true", + "Use NEON for single precision FP">; // Disable 32-bit to 16-bit narrowing for experimentation. def FeaturePref32BitThumb : SubtargetFeature<"32bit", "Pref32BitThumb", "true", "Prefer 32-bit Thumb instrs">; - -// ARM architectures. -def ArchV4T : SubtargetFeature<"v4t", "ARMArchVersion", "V4T", - "ARM v4T">; -def ArchV5T : SubtargetFeature<"v5t", "ARMArchVersion", "V5T", - "ARM v5T">; -def ArchV5TE : SubtargetFeature<"v5te", "ARMArchVersion", "V5TE", - "ARM v5TE, v5TEj, v5TExp">; -def ArchV6 : SubtargetFeature<"v6", "ARMArchVersion", "V6", - "ARM v6">; -def ArchV6M : SubtargetFeature<"v6m", "ARMArchVersion", "V6M", - "ARM v6m", - [FeatureDB]>; -def ArchV6T2 : SubtargetFeature<"v6t2", "ARMArchVersion", "V6T2", - "ARM v6t2", - [FeatureThumb2]>; -def ArchV7A : SubtargetFeature<"v7a", "ARMArchVersion", "V7A", - "ARM v7A", - [FeatureThumb2, FeatureNEON, FeatureDB]>; -def ArchV7M : SubtargetFeature<"v7m", "ARMArchVersion", "V7M", - "ARM v7M", - [FeatureThumb2, FeatureDB]>; +/// Some instructions update CPSR partially, which can add false dependency for +/// out-of-order implementation, e.g. Cortex-A9, unless each individual bit is +/// mapped to a separate physical register. Avoid partial CPSR update for these +/// processors. +def FeatureAvoidPartialCPSR : SubtargetFeature<"avoid-partial-cpsr", + "AvoidCPSRPartialUpdate", "true", + "Avoid CPSR partial update for OOO execution">; + +/// Some M architectures don't have the DSP extension (v7E-M vs. v7M) +def FeatureDSPThumb2 : SubtargetFeature<"t2dsp", "Thumb2DSP", "true", + "Supports v7 DSP instructions in Thumb2">; + +// Multiprocessing extension. +def FeatureMP : SubtargetFeature<"mp", "HasMPExtension", "true", + "Supports Multiprocessing extension">; + +// ARM ISAs. +def HasV4TOps : SubtargetFeature<"v4t", "HasV4TOps", "true", + "Support ARM v4T instructions">; +def HasV5TOps : SubtargetFeature<"v5t", "HasV5TOps", "true", + "Support ARM v5T instructions", + [HasV4TOps]>; +def HasV5TEOps : SubtargetFeature<"v5te", "HasV5TEOps", "true", + "Support ARM v5TE, v5TEj, and v5TExp instructions", + [HasV5TOps]>; +def HasV6Ops : SubtargetFeature<"v6", "HasV6Ops", "true", + "Support ARM v6 instructions", + [HasV5TEOps]>; +def HasV6T2Ops : SubtargetFeature<"v6t2", "HasV6T2Ops", "true", + "Support ARM v6t2 instructions", + [HasV6Ops, FeatureThumb2, FeatureDSPThumb2]>; +def HasV7Ops : SubtargetFeature<"v7", "HasV7Ops", "true", + "Support ARM v7 instructions", + [HasV6T2Ops]>; //===----------------------------------------------------------------------===// // ARM Processors supported. @@ -86,6 +119,18 @@ def ArchV7M : SubtargetFeature<"v7m", "ARMArchVersion", "V7M", include "ARMSchedule.td" +// ARM processor families. +def ProcA8 : SubtargetFeature<"a8", "ARMProcFamily", "CortexA8", + "Cortex-A8 ARM processors", + [FeatureSlowFPBrcc, FeatureNEONForFP, + FeatureHasSlowFPVMLx, FeatureVMLxForwarding, + FeatureT2XtPk]>; +def ProcA9 : SubtargetFeature<"a9", "ARMProcFamily", "CortexA9", + "Cortex-A9 ARM processors", + [FeatureVMLxForwarding, + FeatureT2XtPk, FeatureFP16, + FeatureAvoidPartialCPSR]>; + class ProcNoItin Features> : Processor; @@ -99,60 +144,76 @@ def : ProcNoItin<"strongarm1100", []>; def : ProcNoItin<"strongarm1110", []>; // V4T Processors. -def : ProcNoItin<"arm7tdmi", [ArchV4T]>; -def : ProcNoItin<"arm7tdmi-s", [ArchV4T]>; -def : ProcNoItin<"arm710t", [ArchV4T]>; -def : ProcNoItin<"arm720t", [ArchV4T]>; -def : ProcNoItin<"arm9", [ArchV4T]>; -def : ProcNoItin<"arm9tdmi", [ArchV4T]>; -def : ProcNoItin<"arm920", [ArchV4T]>; -def : ProcNoItin<"arm920t", [ArchV4T]>; -def : ProcNoItin<"arm922t", [ArchV4T]>; -def : ProcNoItin<"arm940t", [ArchV4T]>; -def : ProcNoItin<"ep9312", [ArchV4T]>; +def : ProcNoItin<"arm7tdmi", [HasV4TOps]>; +def : ProcNoItin<"arm7tdmi-s", [HasV4TOps]>; +def : ProcNoItin<"arm710t", [HasV4TOps]>; +def : ProcNoItin<"arm720t", [HasV4TOps]>; +def : ProcNoItin<"arm9", [HasV4TOps]>; +def : ProcNoItin<"arm9tdmi", [HasV4TOps]>; +def : ProcNoItin<"arm920", [HasV4TOps]>; +def : ProcNoItin<"arm920t", [HasV4TOps]>; +def : ProcNoItin<"arm922t", [HasV4TOps]>; +def : ProcNoItin<"arm940t", [HasV4TOps]>; +def : ProcNoItin<"ep9312", [HasV4TOps]>; // V5T Processors. -def : ProcNoItin<"arm10tdmi", [ArchV5T]>; -def : ProcNoItin<"arm1020t", [ArchV5T]>; +def : ProcNoItin<"arm10tdmi", [HasV5TOps]>; +def : ProcNoItin<"arm1020t", [HasV5TOps]>; // V5TE Processors. -def : ProcNoItin<"arm9e", [ArchV5TE]>; -def : ProcNoItin<"arm926ej-s", [ArchV5TE]>; -def : ProcNoItin<"arm946e-s", [ArchV5TE]>; -def : ProcNoItin<"arm966e-s", [ArchV5TE]>; -def : ProcNoItin<"arm968e-s", [ArchV5TE]>; -def : ProcNoItin<"arm10e", [ArchV5TE]>; -def : ProcNoItin<"arm1020e", [ArchV5TE]>; -def : ProcNoItin<"arm1022e", [ArchV5TE]>; -def : ProcNoItin<"xscale", [ArchV5TE]>; -def : ProcNoItin<"iwmmxt", [ArchV5TE]>; +def : ProcNoItin<"arm9e", [HasV5TEOps]>; +def : ProcNoItin<"arm926ej-s", [HasV5TEOps]>; +def : ProcNoItin<"arm946e-s", [HasV5TEOps]>; +def : ProcNoItin<"arm966e-s", [HasV5TEOps]>; +def : ProcNoItin<"arm968e-s", [HasV5TEOps]>; +def : ProcNoItin<"arm10e", [HasV5TEOps]>; +def : ProcNoItin<"arm1020e", [HasV5TEOps]>; +def : ProcNoItin<"arm1022e", [HasV5TEOps]>; +def : ProcNoItin<"xscale", [HasV5TEOps]>; +def : ProcNoItin<"iwmmxt", [HasV5TEOps]>; // V6 Processors. -def : Processor<"arm1136j-s", ARMV6Itineraries, [ArchV6]>; -def : Processor<"arm1136jf-s", ARMV6Itineraries, [ArchV6, FeatureVFP2, - FeatureHasSlowVMLx]>; -def : Processor<"arm1176jz-s", ARMV6Itineraries, [ArchV6]>; -def : Processor<"arm1176jzf-s", ARMV6Itineraries, [ArchV6, FeatureVFP2]>; -def : Processor<"mpcorenovfp", ARMV6Itineraries, [ArchV6]>; -def : Processor<"mpcore", ARMV6Itineraries, [ArchV6, FeatureVFP2]>; +def : Processor<"arm1136j-s", ARMV6Itineraries, [HasV6Ops]>; +def : Processor<"arm1136jf-s", ARMV6Itineraries, [HasV6Ops, FeatureVFP2, + FeatureHasSlowFPVMLx]>; +def : Processor<"arm1176jz-s", ARMV6Itineraries, [HasV6Ops]>; +def : Processor<"arm1176jzf-s", ARMV6Itineraries, [HasV6Ops, FeatureVFP2, + FeatureHasSlowFPVMLx]>; +def : Processor<"mpcorenovfp", ARMV6Itineraries, [HasV6Ops]>; +def : Processor<"mpcore", ARMV6Itineraries, [HasV6Ops, FeatureVFP2, + FeatureHasSlowFPVMLx]>; // V6M Processors. -def : Processor<"cortex-m0", ARMV6Itineraries, [ArchV6M]>; +def : Processor<"cortex-m0", ARMV6Itineraries, [HasV6Ops, FeatureNoARM, + FeatureDB]>; // V6T2 Processors. -def : Processor<"arm1156t2-s", ARMV6Itineraries, [ArchV6T2]>; -def : Processor<"arm1156t2f-s", ARMV6Itineraries, [ArchV6T2, FeatureVFP2]>; +def : Processor<"arm1156t2-s", ARMV6Itineraries, [HasV6T2Ops]>; +def : Processor<"arm1156t2f-s", ARMV6Itineraries, [HasV6T2Ops, FeatureVFP2, + FeatureHasSlowFPVMLx]>; -// V7 Processors. +// V7a Processors. def : Processor<"cortex-a8", CortexA8Itineraries, - [ArchV7A, FeatureHasSlowVMLx, - FeatureSlowFPBrcc, FeatureNEONForFP, FeatureT2XtPk]>; + [ProcA8, HasV7Ops, FeatureNEON, FeatureDB, + FeatureDSPThumb2]>; def : Processor<"cortex-a9", CortexA9Itineraries, - [ArchV7A, FeatureT2XtPk]>; + [ProcA9, HasV7Ops, FeatureNEON, FeatureDB, + FeatureDSPThumb2]>; +def : Processor<"cortex-a9-mp", CortexA9Itineraries, + [ProcA9, HasV7Ops, FeatureNEON, FeatureDB, + FeatureDSPThumb2, FeatureMP]>; // V7M Processors. -def : ProcNoItin<"cortex-m3", [ArchV7M, FeatureHWDiv]>; -def : ProcNoItin<"cortex-m4", [ArchV7M, FeatureHWDiv]>; +def : ProcNoItin<"cortex-m3", [HasV7Ops, + FeatureThumb2, FeatureNoARM, FeatureDB, + FeatureHWDiv]>; + +// V7EM Processors. +def : ProcNoItin<"cortex-m4", [HasV7Ops, + FeatureThumb2, FeatureNoARM, FeatureDB, + FeatureHWDiv, FeatureDSPThumb2, + FeatureT2XtPk, FeatureVFP2, + FeatureVFPOnlySP]>; //===----------------------------------------------------------------------===// // Register File Description @@ -170,6 +231,17 @@ include "ARMInstrInfo.td" def ARMInstrInfo : InstrInfo; + +//===----------------------------------------------------------------------===// +// Assembly printer +//===----------------------------------------------------------------------===// +// ARM Uses the MC printer for asm output, so make sure the TableGen +// AsmWriter bits get associated with the correct class. +def ARMAsmWriter : AsmWriter { + string AsmWriterClassName = "InstPrinter"; + bit isMCAsmWriter = 1; +} + //===----------------------------------------------------------------------===// // Declare the target which we are implementing //===----------------------------------------------------------------------===// @@ -177,4 +249,6 @@ def ARMInstrInfo : InstrInfo; def ARM : Target { // Pull in Instruction Info: let InstructionSet = ARMInstrInfo; + + let AssemblyWriters = [ARMAsmWriter]; }