[CostModel][X86] Improve i16 and vXi16 MUL costs
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Fri, 21 Apr 2023 09:31:24 +0000 (10:31 +0100)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Fri, 21 Apr 2023 14:42:40 +0000 (15:42 +0100)
commit3e9d046bfcfa06da2e4fc3bea2141ac709d9b493
treef8da8c50514be6ea0eccf74e8c6310c2adbca8c7
parent70d8c01e45741ca70f1da16f1ad61112d90b6474
[CostModel][X86] Improve i16 and vXi16 MUL costs

Use a modified version of the D103695 script to determine more accurate throughput/latency/codesize/size-latency cost estimates
13 files changed:
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/X86/arith-fix.ll
llvm/test/Analysis/CostModel/X86/arith-int-latency.ll
llvm/test/Analysis/CostModel/X86/arith-int-sizelatency.ll
llvm/test/Analysis/CostModel/X86/arith-int.ll
llvm/test/Analysis/CostModel/X86/fshl-sizelatency.ll
llvm/test/Analysis/CostModel/X86/fshr-sizelatency.ll
llvm/test/Analysis/CostModel/X86/mul-sizelatency.ll
llvm/test/Analysis/CostModel/X86/rem-latency.ll
llvm/test/Analysis/CostModel/X86/rem-sizelatency.ll
llvm/test/Analysis/CostModel/X86/rem.ll
llvm/test/Analysis/CostModel/X86/slm-arith-costs.ll
llvm/test/Analysis/CostModel/X86/vshift-shl-sizelatency.ll