MSA.txt revision e8eafdb67685d4f5d52ab0dce2339c37e39cdc44
1Code Generation Notes for MSA 2============================= 3 4Intrinsics are lowered to SelectionDAG nodes where possible in order to enable 5optimisation, reduce the size of the ISel matcher, and reduce repetition in 6the implementation. In a small number of cases, this can cause different 7(semantically equivalent) instructions to be used in place of the requested 8instruction, even when no optimisation has taken place. 9 10Instructions 11============ 12 13This section describes any quirks of instruction selection for MSA. For 14example, two instructions might be equally valid for some given IR and one is 15chosen in preference to the other. 16 17vshf.w: 18 It is not possible to emit vshf.w when the shuffle description is 19 constant since shf.w covers exactly the same cases. shf.w is used 20 instead. It is also impossible for the shuffle description to be 21 unknown at compile-time due to the definition of shufflevector in 22 LLVM IR. 23 24ilvl.d, pckev.d: 25 It is not possible to emit ilvl.d, or pckev.d since ilvev.d covers the 26 same shuffle. ilvev.d will be emitted instead. 27 28ilvr.d, ilvod.d, pckod.d: 29 It is not possible to emit ilvr.d, or pckod.d since ilvod.d covers the 30 same shuffle. ilvod.d will be emitted instead. 31 32splati.w: 33 It is not possible to emit splati.w since shf.w covers the same cases. 34 shf.w will be emitted instead. 35 36copy_s.w 37 On MIPS32, the copy_u.d intrinsic will emit this instruction instead of 38 copy_u.w. This is semantically equivalent since the general-purpose 39 register file is 32-bits wide. 40