maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Mark XOP vpmac* and vpmadc intrinsics as being commutative so that tablegen will generate patterns with the load in operand 0. 

This allows loads to be folded during isel without the peephole pass.

llvm-svn: 325548
This commit is contained in:
Craig Topper 2018-02-20 03:58:14 +00:00
parent a05ed17316
commit 41f64c3204
2 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
llvm/include/llvm/IR/IntrinsicsX86.td
View File

@ -3056,62 +3056,62 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
GCCBuiltin<"__builtin_ia32_vpmacsdd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacsdqh :
GCCBuiltin<"__builtin_ia32_vpmacsdqh">,
Intrinsic<[llvm_v2i64_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v2i64_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacsdql :
GCCBuiltin<"__builtin_ia32_vpmacsdql">,
Intrinsic<[llvm_v2i64_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v2i64_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacssdd :
GCCBuiltin<"__builtin_ia32_vpmacssdd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacssdqh :
GCCBuiltin<"__builtin_ia32_vpmacssdqh">,
Intrinsic<[llvm_v2i64_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v2i64_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacssdql :
GCCBuiltin<"__builtin_ia32_vpmacssdql">,
Intrinsic<[llvm_v2i64_ty],
[llvm_v4i32_ty, llvm_v4i32_ty, llvm_v2i64_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacsswd :
GCCBuiltin<"__builtin_ia32_vpmacsswd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacssww :
GCCBuiltin<"__builtin_ia32_vpmacssww">,
Intrinsic<[llvm_v8i16_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v8i16_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacswd :
GCCBuiltin<"__builtin_ia32_vpmacswd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmacsww :
GCCBuiltin<"__builtin_ia32_vpmacsww">,
Intrinsic<[llvm_v8i16_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v8i16_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmadcsswd :
GCCBuiltin<"__builtin_ia32_vpmadcsswd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpmadcswd :
GCCBuiltin<"__builtin_ia32_vpmadcswd">,
Intrinsic<[llvm_v4i32_ty],
[llvm_v8i16_ty, llvm_v8i16_ty, llvm_v4i32_ty],
[IntrNoMem]>;
[IntrNoMem, Commutative]>;
def int_x86_xop_vpperm :
GCCBuiltin<"__builtin_ia32_vpperm">,
Intrinsic<[llvm_v16i8_ty],

4
llvm/test/CodeGen/X86/commute-xop.ll
View File

@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=X64
; RUN: llc < %s -disable-peephole -mtriple=i686-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=X32
; RUN: llc < %s -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=X64
define <16 x i8> @commute_fold_vpcomb(<16 x i8>* %a0, <16 x i8> %a1) {
; X32-LABEL: commute_fold_vpcomb: