switch the use-vml[as] instructions flag to a subtarget 'feature'

llvm-svn: 99565
This commit is contained in:
Jim Grosbach 2010-03-25 23:11:16 +00:00
parent c78d720f02
commit a43386ba8f
3 changed files with 15 additions and 16 deletions

View File

@ -43,6 +43,15 @@ def FeatureThumb2 : SubtargetFeature<"thumb2", "ThumbMode", "Thumb2",
def FeatureFP16 : SubtargetFeature<"fp16", "HasFP16", "true", def FeatureFP16 : SubtargetFeature<"fp16", "HasFP16", "true",
"Enable half-precision floating point">; "Enable half-precision floating point">;
// Some processors have multiply-accumulate instructions that don't
// play nicely with other VFP 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 HasSlowVMLx : SubtargetFeature<"vmlx", "SlowVMLx", "true",
"Disable VFP MAC instructions">;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
// ARM Processors supported. // ARM Processors supported.
// //
@ -106,7 +115,7 @@ def : Processor<"arm1156t2f-s", ARMV6Itineraries,
// V7 Processors. // V7 Processors.
def : Processor<"cortex-a8", CortexA8Itineraries, def : Processor<"cortex-a8", CortexA8Itineraries,
[ArchV7A, FeatureThumb2, FeatureNEON]>; [ArchV7A, FeatureThumb2, FeatureNEON, HasSlowVMLx]>;
def : ProcNoItin<"cortex-a9", [ArchV7A, FeatureThumb2, FeatureNEON]>; def : ProcNoItin<"cortex-a9", [ArchV7A, FeatureThumb2, FeatureNEON]>;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//

View File

@ -26,10 +26,6 @@ static cl::opt<bool>
UseNEONFP("arm-use-neon-fp", UseNEONFP("arm-use-neon-fp",
cl::desc("Use NEON for single-precision FP"), cl::desc("Use NEON for single-precision FP"),
cl::init(false), cl::Hidden); cl::init(false), cl::Hidden);
static cl::opt<bool>
UseVMLxInstructions("arm-use-vmlx",
cl::desc("Use VFP vmla and vmls instructions"),
cl::init(true), cl::Hidden);
static cl::opt<bool> static cl::opt<bool>
UseMOVT("arm-use-movt", UseMOVT("arm-use-movt",
@ -40,7 +36,7 @@ ARMSubtarget::ARMSubtarget(const std::string &TT, const std::string &FS,
: ARMArchVersion(V4) : ARMArchVersion(V4)
, ARMFPUType(None) , ARMFPUType(None)
, UseNEONForSinglePrecisionFP(UseNEONFP) , UseNEONForSinglePrecisionFP(UseNEONFP)
, UseVMLx(UseVMLxInstructions) , SlowVMLx(false)
, IsThumb(isT) , IsThumb(isT)
, ThumbMode(Thumb1) , ThumbMode(Thumb1)
, PostRAScheduler(false) , PostRAScheduler(false)
@ -127,12 +123,6 @@ ARMSubtarget::ARMSubtarget(const std::string &TT, const std::string &FS,
// operations with NEON instructions. // operations with NEON instructions.
if (UseNEONFP.getPosition() == 0) if (UseNEONFP.getPosition() == 0)
UseNEONForSinglePrecisionFP = true; UseNEONForSinglePrecisionFP = true;
// The VFP vlma and vlms instructions don't play nicely with others;
// disable them.
// FIXME: This may be true for other variants as well. Get benchmark
// numbers and add them if determined that's the case.
if (UseVMLxInstructions.getPosition() == 0)
UseVMLx = false;
} }
} }

View File

@ -50,9 +50,9 @@ protected:
/// determine if NEON should actually be used. /// determine if NEON should actually be used.
bool UseNEONForSinglePrecisionFP; bool UseNEONForSinglePrecisionFP;
/// UseVMLx - If the VFP2 instructions are available, indicates whether /// SlowVMLx - If the VFP2 instructions are available, indicates whether
/// the VML[AS] instructions should be used. /// the VML[AS] instructions are slow (if so, don't use them).
bool UseVMLx; bool SlowVMLx;
/// IsThumb - True if we are in thumb mode, false if in ARM mode. /// IsThumb - True if we are in thumb mode, false if in ARM mode.
bool IsThumb; bool IsThumb;
@ -123,7 +123,7 @@ protected:
bool hasNEON() const { return ARMFPUType >= NEON; } bool hasNEON() const { return ARMFPUType >= NEON; }
bool useNEONForSinglePrecisionFP() const { bool useNEONForSinglePrecisionFP() const {
return hasNEON() && UseNEONForSinglePrecisionFP; } return hasNEON() && UseNEONForSinglePrecisionFP; }
bool useVMLx() const {return hasVFP2() && UseVMLx; } bool useVMLx() const {return hasVFP2() && !SlowVMLx; }
bool hasFP16() const { return HasFP16; } bool hasFP16() const { return HasFP16; }