Home
last modified time | relevance | path

Searched refs:subvector (Results 1 – 10 of 10) sorted by relevance

/freebsd/contrib/llvm-project/llvm/lib/Target/X86/
H A DX86InstrVecCompiler.td75 // A 128-bit subvector extract from the first 256-bit vector position is a
76 // subregister copy that needs no instruction. Likewise, a 128-bit subvector
88 // A 128-bit subvector extract from the first 512-bit vector position is a
89 // subregister copy that needs no instruction. Likewise, a 128-bit subvector
101 // A 128-bit subvector extract from the first 512-bit vector position is a
102 // subregister copy that needs no instruction. Likewise, a 128-bit subvector
H A DX86InstrFormats.td133 // The tuple (subvector) forms.
H A DX86InstrUtils.td286 // 8-bit compressed displacement tuple/subvector format. This is only
/freebsd/contrib/llvm-project/llvm/lib/Target/Hexagon/
H A DHexagonVectorCombine.cpp136 Value *subvector(IRBuilderBase &Builder, Value *Val, unsigned Start,
1789 ChopOp.X.Val = HVC.subvector(Builder, X, V * ChopLen, ChopLen); in processFxpMul()
1790 ChopOp.Y.Val = HVC.subvector(Builder, Y, V * ChopLen, ChopLen); in processFxpMul()
2521 auto HexagonVectorCombine::subvector(IRBuilderBase &Builder, Value *Val, in subvector() function in HexagonVectorCombine
2532 return subvector(Builder, Val, 0, Len / 2); in sublo()
2539 return subvector(Builder, Val, Len / 2, Len / 2); in subhi()
/freebsd/contrib/llvm-project/llvm/include/llvm/Support/
H A DTargetOpcodes.def745 /// Generic insert subvector.
748 /// Generic extract subvector.
/freebsd/contrib/llvm-project/llvm/include/llvm/Target/
H A DTargetSelectionDAG.td302 def SDTSubVecExtract : SDTypeProfile<1, 2, [// subvector extract
305 def SDTSubVecInsert : SDTypeProfile<1, 3, [ // subvector insert
800 // This operator does not do subvector type checking. The ARM
809 // This operator does subvector type checking.
H A DGenericOpcodes.td1520 // Generic insert subvector.
1527 // Generic extract subvector.
/freebsd/contrib/llvm-project/llvm/include/llvm/IR/
H A DIntrinsics.td2658 //===---------- Intrinsics to perform subvector insertion/extraction ------===//
/freebsd/contrib/llvm-project/llvm/lib/Target/AArch64/
H A DAArch64InstrInfo.td8839 // Multiply high patterns which multiply the lower subvector using smull/umull
8840 // and the upper subvector with smull2/umull2. Then shuffle the high the high
9515 // A 64-bit subvector insert to the first 128-bit vector position
/freebsd/contrib/llvm-project/llvm/lib/Target/ARM/
H A DARMInstrNEON.td1096 // A 64-bit subvector insert to the first 128-bit vector position