search for: hasneon

...inclination would be to just always set OPUS_CPU_ARM_NEON on iOS/arm. That said, if we do want to support runtime Neon detection on iOS, rather than checking hardware models I believe the semantically-correct way to do this is to check ?hw.optional.neon? using sysctlbyname(), as in: unsigned int hasNeon; size_t length = sizeof(hasNeon); if (sysctlbyname("hw.optional.neon", &hasNeon, &length, NULL, 0) != 0) hasNeon = 0; -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.xiph.org/pipermail/opus/attachments/20150108/4ab7c6ad/attachment.htm

This adds run-time CPU detection for iOS devices. I found this page useful for CPU support and models: http://iossupportmatrix.com/ The patch could be simplified to just set the OPUS_CPU_ARM_NEON flag if you think it's unlikely that anyone would be running on the really old devices that don't support NEON. Tom -------------- next part -------------- An HTML attachment was scrubbed...

...========================================= --- lib/Target/ARM/ARMAsmPrinter.cpp (revision 123053) +++ lib/Target/ARM/ARMAsmPrinter.cpp (working copy) @@ -458,7 +458,13 @@ AttrEmitter->EmitAttribute(ARMBuildAttrs::THUMB_ISA_use, 1); } - // FIXME: Emit FPU type + if (Subtarget->hasNEON()) + OutStreamer.EmitRawText(StringRef("\t.fpu neon")); + else if (Subtarget->hasVFP3()) + OutStreamer.EmitRawText(StringRef("\t.fpu vfpv3")); + else if (Subtarget->hasVFP2()) + OutStreamer.EmitRawText(StringRef("\t.fpu vfpv2")); + if (Subtarget-&gt...

On Fri, Feb 25, 2011 at 12:16 PM, Siarhei Siamashka <siarhei.siamashka at gmail.com> wrote: > On Thursday 03 February 2011 14:14:28 Renato Golin wrote: >> On 3 February 2011 10:25, Siarhei Siamashka <siarhei.siamashka at gmail.com> > wrote: >> > I have submitted a bug some time ago to LLVM bugtracker: >> > http://llvm.org/bugs/show_bug.cgi?id=8931 >>

...We need to increase the cost of insert/extract vector. It should be easy to model and we have all of the hooks already. We can use the Subtarget when we implement the hooks. This is an example from the ARMTTI unsigned getNumberOfRegisters(bool Vector) const { if (Vector) { if (ST->hasNEON()) return 16; return 0; } if (ST->isThumb1Only()) return 8; return 16; } unsigned getMaximumUnrollFactor() const { // These are out of order CPUs: if (ST->isCortexA15() || ST->isSwift()) return 2; return 1; } > Thanks, Na...

On Thursday 03 February 2011 14:14:28 Renato Golin wrote: > On 3 February 2011 10:25, Siarhei Siamashka <siarhei.siamashka at gmail.com> wrote: > > I have submitted a bug some time ago to LLVM bugtracker: > > http://llvm.org/bugs/show_bug.cgi?id=8931 > > Hi Siarhei, > > This is a really silly bug with a simple fix. > > We have a similar patch here

Hi Nadav, I'm interested in knowing how you'll work up the ARM cost model and how easy it'd be to split the work. As far as I can see, LoopVectorizationCostModel is the class that does all the work, with assistance from the target transform info. Do you think that updating ARMTTI would be the best course of action now, and inspect the differences in the CostModel later? I also

...btarget.h +++ b/lib/Target/AArch64/AArch64Subtarget.h @@ -47,6 +47,7 @@ public: bool isTargetELF() const { return TargetTriple.isOSBinFormatELF(); } bool isTargetLinux() const { return TargetTriple.isOSLinux(); } + bool isTargetDarwin() const { return TargetTriple.isOSDarwin(); } bool hasNEON() const { return HasNEON; } diff --git a/lib/Target/AArch64/AArch64TargetObjectFile.cpp b/lib/Target/AArch64/AArch64TargetObjectFile.cpp index b4452f5..954cad6 100644 --- a/lib/Target/AArch64/AArch64TargetObjectFile.cpp +++ b/lib/Target/AArch64/AArch64TargetObjectFile.cpp @@ -13,6 +13,14 @@...