[X86SchedSandyBridge] update cost of COPY to 1 cycle from 0
authorNick Desaulniers <ndesaulniers@google.com>
Thu, 5 May 2022 18:06:09 +0000 (11:06 -0700)
committerNick Desaulniers <ndesaulniers@google.com>
Thu, 5 May 2022 18:14:22 +0000 (11:14 -0700)
commit18fd09ab64b07c45d0373307e37f7c96b3984183
treea7083b505a987209813f4c84ed71ceaa96d35d85
parente1554ac63a903891843b248d611fa8e9fc75d476
[X86SchedSandyBridge] update cost of COPY to 1 cycle from 0

To match the cost of other scheduling models. This is expected to
schedule mov instructions around INLINEASM less frequently for the
default machineschedule (pre-RA scheduling).

Suggested by Craig Topper.

Link: https://github.com/llvm/llvm-project/issues/41914
Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D122350
15 files changed:
llvm/lib/Target/X86/X86SchedSandyBridge.td
llvm/test/CodeGen/X86/2009-03-23-MultiUseSched.ll
llvm/test/CodeGen/X86/fp-load-trunc.ll
llvm/test/CodeGen/X86/fp-trunc.ll
llvm/test/CodeGen/X86/gather-addresses.ll
llvm/test/CodeGen/X86/machine-combiner-int-vec.ll
llvm/test/CodeGen/X86/machine-combiner-int.ll
llvm/test/CodeGen/X86/recip-fastmath.ll
llvm/test/CodeGen/X86/recip-fastmath2.ll
llvm/test/CodeGen/X86/scheduler-asm-moves.mir
llvm/test/CodeGen/X86/sqrt-fastmath-tune.ll
llvm/test/CodeGen/X86/sqrt-fastmath.ll
llvm/test/CodeGen/X86/vector-reduce-fadd-fast.ll
llvm/test/CodeGen/X86/vector-reduce-fmul-fast.ll
llvm/test/CodeGen/X86/vector-shuffle-combining.ll