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

[ARM][MVE] Tail-Predication: recognise (again) active lanes IR pattern 

A small IR change in calculating the active lanes resulted in no longer
recognising tail-predication. Now recognise both an 'add' and 'or' in
the expression that calculates the active lanes.

Differential Revision: https://reviews.llvm.org/D74394
This commit is contained in:
Sjoerd Meijer 2020-02-11 15:14:54 +00:00
parent faace36508
commit 6b0ed508fa
2 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Target/ARM/MVETailPredication.cpp
View File

@ -260,13 +260,18 @@ bool MVETailPredication::isTailPredicate(TripCountPattern &TCP) {
// %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert,
// <4 x i32> undef,
// <4 x i32> zeroinitializer
// %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
// %induction = [add|or] <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
// %pred = icmp ule <4 x i32> %induction, %broadcast.splat11
//
// Please note that the 'or' is equivalent to the 'and' here, this relies on
// BroadcastSplat being the IV which we know is a phi with 0 start and Lanes
// increment, which is all being checked below.
Instruction *BroadcastSplat = nullptr;
Constant *Const = nullptr;
if (!match(TCP.Induction,
m_Add(m_Instruction(BroadcastSplat), m_Constant(Const))))
m_Add(m_Instruction(BroadcastSplat), m_Constant(Const))) &&
!match(TCP.Induction,
m_Or(m_Instruction(BroadcastSplat), m_Constant(Const))))
return false;
// Check that we're adding <0, 1, 2, 3...

4
llvm/test/CodeGen/Thumb2/LowOverheadLoops/basic-tail-pred.ll
View File

@ -32,7 +32,7 @@ vector.body: ; preds = %vector.body, %vecto
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <16 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <16 x i32> %broadcast.splatinsert, <16 x i32> undef, <16 x i32> zeroinitializer
%induction = add <16 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%induction = or <16 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%tmp = getelementptr inbounds i8, i8* %a, i32 %index
%tmp1 = icmp ule <16 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i8* %tmp to <16 x i8>*
@ -137,7 +137,7 @@ vector.body: ; preds = %vector.body, %vecto
%tmp14 = phi i32 [ %tmp13, %vector.ph ], [ %tmp15, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%induction = or <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%tmp = getelementptr inbounds i32, i32* %a, i32 %index
%tmp1 = icmp ule <4 x i32> %induction, %broadcast.splat11
%tmp2 = bitcast i32* %tmp to <4 x i32>*