[PATCH] D47443: [X86] Lowering FMA intrinsics to native IR (LLVM part)

Tomasz Krupa via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon May 28 01:23:42 PDT 2018


tkrupa created this revision.
tkrupa added reviewers: craig.topper, sroland, spatel.
Herald added a subscriber: llvm-commits.

Suuport for Clang lowering of fused intrinsics. This patch:

1. Removes bindings to clang fma intrinsics.
2. Introduces new LLVM unmasked intrinsics with rounding mode:

int_x86_avx512_vfmadd_pd_512
int_x86_avx512_vfmadd_ps_512
int_x86_avx512_vfmaddsub_pd_512
int_x86_avx512_vfmaddsub_ps_512
supported with a new intrinsic type (INTR_TYPE_3OP_RM).

3. Introduces new x86 fmaddsub/fmsubadd folding.
4. Introduces new tests for code emitted by sequentions introduced in Clang part.


Repository:
  rL LLVM

https://reviews.llvm.org/D47443

Files:
  include/llvm/IR/IntrinsicsX86.td
  lib/Target/X86/X86ISelLowering.cpp
  lib/Target/X86/X86IntrinsicsInfo.h
  test/CodeGen/X86/avx512-fma-intrinsics.ll
  test/CodeGen/X86/avx512-intrinsics-canonical.ll
  test/CodeGen/X86/avx512vl-intrinsics-canonical.ll
  test/CodeGen/X86/fma-fneg-combine.ll
  test/CodeGen/X86/fma-intrinsics-canonical.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D47443.148787.patch
Type: text/x-patch
Size: 327571 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180528/9f7724d4/attachment-0001.bin>


More information about the llvm-commits mailing list