forked from OSchip/llvm-project
switch the use-vml[as] instructions flag to a subtarget 'feature'
llvm-svn: 99565
This commit is contained in:
parent
c78d720f02
commit
a43386ba8f
|
@ -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]>;
|
||||||
|
|
||||||
//===----------------------------------------------------------------------===//
|
//===----------------------------------------------------------------------===//
|
||||||
|
|
|
@ -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;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -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; }
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue