[PATCH] D22106: [X86][SSE] Reimplement SSE fp2si conversion intrinsics instead of using generic IR

[Simon Pilgrim via llvm-commits]

RKSimon updated this revision to Diff 64317.
RKSimon added a comment.

Updated the non-truncating conversion constant folding not to accept inexact conversions


Repository:
  rL LLVM

https://reviews.llvm.org/D22106

Files:
  include/llvm/IR/IntrinsicsX86.td
  lib/Analysis/ConstantFolding.cpp
  lib/IR/AutoUpgrade.cpp
  lib/Target/X86/X86InstrSSE.td
  test/CodeGen/X86/avx-intrinsics-fast-isel.ll
  test/CodeGen/X86/avx-intrinsics-x86-upgrade.ll
  test/CodeGen/X86/avx-intrinsics-x86.ll
  test/CodeGen/X86/sse-intrinsics-fast-isel-x86_64.ll
  test/CodeGen/X86/sse-intrinsics-fast-isel.ll
  test/CodeGen/X86/sse2-intrinsics-fast-isel-x86_64.ll
  test/CodeGen/X86/sse2-intrinsics-fast-isel.ll
  test/CodeGen/X86/sse2-intrinsics-x86-upgrade.ll
  test/CodeGen/X86/sse2-intrinsics-x86.ll
  test/Transforms/ConstProp/calls.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D22106.64317.patch
Type: text/x-patch
Size: 23902 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160718/d466b519/attachment.bin>