[PATCH] D75748: [X86] Replace (most) X86ISD::SHLD/SHRD usage with ISD::FSHL/FSHR generic opcodes (PR39467)

Fri Mar 6 08:14:03 PST 2020

RKSimon marked an inline comment as done.
RKSimon added inline comments.

================
Comment at: llvm/test/CodeGen/X86/clear-highbits.ll:6
 ; RUN: llc -mtriple=i686-unknown-linux-gnu -mattr=+bmi,+tbm,+bmi2 < %s | FileCheck %s --check-prefixes=CHECK,X86,BMI2,X86-BMI2,FALLBACK3,X86-FALLBACK3
 ; RUN: llc -mtriple=i686-unknown-linux-gnu -mattr=+bmi,-tbm,+bmi2 < %s | FileCheck %s --check-prefixes=CHECK,X86,BMI2,X86-BMI2,FALLBACK4,X86-FALLBACK4
 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=-bmi,-tbm,-bmi2 < %s | FileCheck %s --check-prefixes=CHECK,X64,NOBMI2,X64-NOBMI2,FALLBACK0,X64-FALLBACK0
----------------
@lebedev.ri Apart from the X86-FALLBACK0 case, can't we enable +cmov on these x86 targets? I can't think of a target that would support any BMI/TBM level without CMOV support.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D75748/new/

https://reviews.llvm.org/D75748