mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +02:00
7708490317
This goes back to a discussion about IR canonicalization. We'd like to preserve and convert more IR to 'select' than we currently do because that's likely the best choice in IR: http://lists.llvm.org/pipermail/llvm-dev/2016-September/105335.html ...but that's often not true for codegen, so we need to account for this pattern coming in to the backend and transform it to better DAG ops. Steps in this patch: 1. Add an EVT param to the existing convertSelectOfConstantsToMath() TLI hook to more finely enable this transform. Other targets will probably want that anyway to distinguish scalars from vectors. We're using that here to exclude AVX512 targets, but it may not be necessary. 2. Convert a vselect to ext+add. This eliminates a constant load/materialization, and the vector ext is often free. Implementing a more general fold using xor+and can be a follow-up for targets that don't have a legal vselect. It's also possible that we can remove the TLI hook for the special case fold implemented here because we're eliminating a constant, but it needs to be tested on other targets. Differential Revision: https://reviews.llvm.org/D36840 llvm-svn: 311731
22 lines
768 B
LLVM
22 lines
768 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=X64
|
|
|
|
; compare v2i16
|
|
|
|
define <2 x i16> @compare_v2i64_to_v2i16(<2 x i16>* %src) nounwind {
|
|
; X86-LABEL: compare_v2i64_to_v2i16:
|
|
; X86: # BB#0:
|
|
; X86-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: compare_v2i64_to_v2i16:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%val = load <2 x i16>, <2 x i16>* %src, align 4
|
|
%cmp = icmp uge <2 x i16> %val, %val
|
|
%sel = select <2 x i1> %cmp, <2 x i16> <i16 -1, i16 -1>, <2 x i16> zeroinitializer
|
|
ret <2 x i16> %sel
|
|
}
|