Files
clang-p2996/llvm/test/Transforms/LICM
Mingming Liu 8aa800614b [AArch64][CostModel] Detects that {extract,insert}-element at lane 0 has the same cost as the other lane for vector instructions in the IR.
Currently, {extract,insert}-element has zero cost at lane 0 [1]. However, there is a cost (by fmov instruction [2], or ext/ins instruction) to move values from SIMD registers to GPR registers, when the element is used explicitly as integers.

See https://godbolt.org/z/faPE1nTn8, when fmov is generated for d* register -> x* register conversion.

Implementation-wise, add a private method `AArch64TTIImpl::getVectorInstrCostHelper` as a helper function. This way, instruction-based method could share the core logic (e.g.,
returning zero cost if type is legalized to scalar).

[1] 2cf320d41e/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (L1853)
[2] 2cf320d41e/llvm/lib/Target/AArch64/AArch64InstrInfo.td (L8150-L8157)

Differential Revision: https://reviews.llvm.org/D128302
2022-09-09 09:47:30 -07:00
..
2022-04-08 09:49:44 +02:00
2022-05-24 17:22:16 +07:00