mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-07-29 10:25:12 +00:00
[InterleavedAccess] Add a pass InterleavedAccess to identify interleaved memory accesses and transform into target specific intrinsics.
E.g. An interleaved load (Factor = 2): %wide.vec = load <8 x i32>, <8 x i32>* %ptr %v0 = shuffle <8 x i32> %wide.vec, <8 x i32> undef, <0, 2, 4, 6> %v1 = shuffle <8 x i32> %wide.vec, <8 x i32> undef, <1, 3, 5, 7> It can be transformed into a ld2 intrinsic in AArch64 backend or a vld2 intrinsic in ARM backend. E.g. An interleaved store (Factor = 3): %i.vec = shuffle <8 x i32> %v0, <8 x i32> %v1, <0, 4, 8, 1, 5, 9, 2, 6, 10, 3, 7, 11> store <12 x i32> %i.vec, <12 x i32>* %ptr It can be transformed into a st3 intrinsic in AArch64 backend or a vst3 intrinsic in ARM backend. Differential Revision: http://reviews.llvm.org/D10533 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240751 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
@@ -1597,6 +1597,35 @@ public:
|
||||
return false;
|
||||
}
|
||||
|
||||
/// \brief Get the maximum supported factor for interleaved memory accesses.
|
||||
/// Default to be the minimum interleave factor: 2.
|
||||
virtual unsigned getMaxSupportedInterleaveFactor() const { return 2; }
|
||||
|
||||
/// \brief Lower an interleaved load to target specific intrinsics. Return
|
||||
/// true on success.
|
||||
///
|
||||
/// \p LI is the vector load instruction.
|
||||
/// \p Shuffles is the shufflevector list to DE-interleave the loaded vector.
|
||||
/// \p Indices is the corresponding indices for each shufflevector.
|
||||
/// \p Factor is the interleave factor.
|
||||
virtual bool lowerInterleavedLoad(LoadInst *LI,
|
||||
ArrayRef<ShuffleVectorInst *> Shuffles,
|
||||
ArrayRef<unsigned> Indices,
|
||||
unsigned Factor) const {
|
||||
return false;
|
||||
}
|
||||
|
||||
/// \brief Lower an interleaved store to target specific intrinsics. Return
|
||||
/// true on success.
|
||||
///
|
||||
/// \p SI is the vector store instruction.
|
||||
/// \p SVI is the shufflevector to RE-interleave the stored vector.
|
||||
/// \p Factor is the interleave factor.
|
||||
virtual bool lowerInterleavedStore(StoreInst *SI, ShuffleVectorInst *SVI,
|
||||
unsigned Factor) const {
|
||||
return false;
|
||||
}
|
||||
|
||||
/// Return true if zero-extending the specific node Val to type VT2 is free
|
||||
/// (either because it's implicitly zero-extended such as ARM ldrb / ldrh or
|
||||
/// because it's folded such as X86 zero-extending loads).
|
||||
|
Reference in New Issue
Block a user