maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/BBVectorize/search-limit.ll

47 lines
2.2 KiB
LLVM
Raw Normal View History

Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
Switch BBVectorize to directly depend on having a TTI analysis. This could be simplified further, but Hal has a specific feature for ignoring TTI, and so I preserved that. Also, I needed to use it because a number of tests fail when switching from a null TTI to the NoTTI nonce implementation. That seems suspicious to me and so may be something that you need to look into Hal. I worked it by preserving the old behavior for these tests with the flag that ignores all target info. llvm-svn: 171722
2013-01-07 18:22:36 +08:00
; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s
; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-search-limit=4 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-SL4
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
define double @test1(double %A1, double %A2, double %B1, double %B2) {
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test1(
; CHECK-SL4-LABEL: @test1(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK-SL4-NOT: <2 x double>
; CHECK: %X1.v.i1.1 = insertelement <2 x double> undef, double %B1, i32 0
; CHECK: %X1.v.i1.2 = insertelement <2 x double> %X1.v.i1.1, double %B2, i32 1
BBVectorize: Choose pair ordering to minimize shuffles BBVectorize would, except for loads and stores, always fuse instructions so that the first instruction (in the current source order) would always represent the low part of the input vectors and the second instruction would always represent the high part. This lead to too many shuffles being produced because sometimes the opposite order produces fewer of them. With this change, BBVectorize tracks the kind of pair connections that form the DAG of candidate pairs, and uses that information to reorder the pairs to avoid excess shuffles. Using this information, a future commit will be able to add VTTI-based shuffle costs to the pair selection procedure. Importantly, the number of remaining shuffles can now be estimated during pair selection. There are some trivial instruction reorderings in the test cases, and one simple additional test where we certainly want to do a reordering to avoid an unnecessary shuffle. llvm-svn: 167122
2012-10-31 23:17:07 +08:00
; CHECK: %X1.v.i0.1 = insertelement <2 x double> undef, double %A1, i32 0
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK: %X1.v.i0.2 = insertelement <2 x double> %X1.v.i0.1, double %A2, i32 1
%X1 = fsub double %A1, %B1
%X2 = fsub double %A2, %B2
; CHECK: %X1 = fsub <2 x double> %X1.v.i0.2, %X1.v.i1.2
%Y1 = fmul double %X1, %A1
%Y2 = fmul double %X2, %A2
; CHECK: %Y1 = fmul <2 x double> %X1, %X1.v.i0.2
%Z1 = fadd double %Y1, %B1
; Here we have a dependency chain: the short search limit will not
; see past this chain and so will not see the second part of the
; pair to vectorize.
%mul41 = fmul double %Z1, %Y2
%sub48 = fsub double %Z1, %mul41
%mul62 = fmul double %Z1, %sub48
%sub69 = fsub double %Z1, %mul62
%mul83 = fmul double %Z1, %sub69
%sub90 = fsub double %Z1, %mul83
%mul104 = fmul double %Z1, %sub90
%sub111 = fsub double %Z1, %mul104
%mul125 = fmul double %Z1, %sub111
%sub132 = fsub double %Z1, %mul125
%mul146 = fmul double %Z1, %sub132
%sub153 = fsub double %Z1, %mul146
; end of chain.
%Z2 = fadd double %Y2, %B2
; CHECK: %Z1 = fadd <2 x double> %Y1, %X1.v.i1.2
%R1 = fdiv double %Z1, %Z2
%R = fmul double %R1, %sub153
; CHECK: %Z1.v.r1 = extractelement <2 x double> %Z1, i32 0
; CHECK: %Z1.v.r2 = extractelement <2 x double> %Z1, i32 1
; CHECK: %R1 = fdiv double %Z1.v.r1, %Z1.v.r2
ret double %R
; CHECK: ret double %R
}