[X86] Lower the cost of v4i64->v4i32 truncate with avx512.
authorCraig Topper <craig.topper@intel.com>
Fri, 1 May 2020 17:38:33 +0000 (10:38 -0700)
committerCraig Topper <craig.topper@intel.com>
Fri, 1 May 2020 18:09:37 +0000 (11:09 -0700)
commitb938168aef995f8d9b6695a0dc0ef71c25b71968
tree99314c48d132b105311048f2dacbf10253ae9315
parentdbc601e25b6da8d6dd83c8fa6ac8865bb84394a2
[X86] Lower the cost of v4i64->v4i32 truncate with avx512.

We use the vpmovqd instruction which is a single uop. So
the cost should be 1.
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/X86/arith-fix.ll
llvm/test/Analysis/CostModel/X86/arith-overflow.ll
llvm/test/Analysis/CostModel/X86/cast.ll
llvm/test/Analysis/CostModel/X86/trunc.ll