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/simple-ldstr.ll

171 lines
6.8 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-n8:16:32:64-S128"
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-aligned-only -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-AO
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
; Simple 3-pair chain with loads and stores
define void @test1(double* %a, double* %b, double* %c) nounwind uwtable readonly {
entry:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
store double %mul, double* %c, align 8
%arrayidx5 = getelementptr inbounds double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
ret void
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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test1(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK: %i0.v.i0 = bitcast double* %a to <2 x double>*
; CHECK: %i1.v.i0 = bitcast double* %b to <2 x double>*
; CHECK: %i0 = load <2 x double>* %i0.v.i0, align 8
; CHECK: %i1 = load <2 x double>* %i1.v.i0, align 8
; CHECK: %mul = fmul <2 x double> %i0, %i1
; CHECK: %0 = bitcast double* %c to <2 x double>*
; CHECK: store <2 x double> %mul, <2 x double>* %0, align 8
; CHECK: ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-AO-LABEL: @test1(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK-AO-NOT: <2 x double>
}
; Simple chain with extending loads and stores
define void @test2(float* %a, float* %b, double* %c) nounwind uwtable readonly {
entry:
%i0f = load float* %a, align 4
%i0 = fpext float %i0f to double
%i1f = load float* %b, align 4
%i1 = fpext float %i1f to double
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds float* %a, i64 1
%i3f = load float* %arrayidx3, align 4
%i3 = fpext float %i3f to double
%arrayidx4 = getelementptr inbounds float* %b, i64 1
%i4f = load float* %arrayidx4, align 4
%i4 = fpext float %i4f to double
%mul5 = fmul double %i3, %i4
store double %mul, double* %c, align 8
%arrayidx5 = getelementptr inbounds double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test2(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK: %i0f.v.i0 = bitcast float* %a to <2 x float>*
; CHECK: %i1f.v.i0 = bitcast float* %b to <2 x float>*
; CHECK: %i0f = load <2 x float>* %i0f.v.i0, align 4
; CHECK: %i0 = fpext <2 x float> %i0f to <2 x double>
; CHECK: %i1f = load <2 x float>* %i1f.v.i0, align 4
; CHECK: %i1 = fpext <2 x float> %i1f to <2 x double>
; CHECK: %mul = fmul <2 x double> %i0, %i1
; CHECK: %0 = bitcast double* %c to <2 x double>*
; CHECK: store <2 x double> %mul, <2 x double>* %0, align 8
; CHECK: ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-AO-LABEL: @test2(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK-AO-NOT: <2 x double>
}
; Simple chain with loads and truncating stores
define void @test3(double* %a, double* %b, float* %c) nounwind uwtable readonly {
entry:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%mulf = fptrunc double %mul to float
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
%mul5f = fptrunc double %mul5 to float
store float %mulf, float* %c, align 8
%arrayidx5 = getelementptr inbounds float* %c, i64 1
store float %mul5f, float* %arrayidx5, align 4
ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test3(
Add a basic-block autovectorization pass. This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure. Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser). llvm-svn: 149468
2012-02-01 11:51:43 +08:00
; CHECK: %i0.v.i0 = bitcast double* %a to <2 x double>*
; CHECK: %i1.v.i0 = bitcast double* %b to <2 x double>*
; CHECK: %i0 = load <2 x double>* %i0.v.i0, align 8
; CHECK: %i1 = load <2 x double>* %i1.v.i0, align 8
; CHECK: %mul = fmul <2 x double> %i0, %i1
; CHECK: %mulf = fptrunc <2 x double> %mul to <2 x float>
; CHECK: %0 = bitcast float* %c to <2 x float>*
; CHECK: store <2 x float> %mulf, <2 x float>* %0, align 8
; CHECK: ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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-AO-LABEL: @test3(
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-AO: %i0 = load double* %a, align 8
; CHECK-AO: %i1 = load double* %b, align 8
; CHECK-AO: %arrayidx3 = getelementptr inbounds double* %a, i64 1
; CHECK-AO: %i3 = load double* %arrayidx3, align 8
; CHECK-AO: %arrayidx4 = getelementptr inbounds double* %b, i64 1
; CHECK-AO: %i4 = load double* %arrayidx4, align 8
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-AO: %mul.v.i1.1 = insertelement <2 x double> undef, double %i1, 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-AO: %mul.v.i1.2 = insertelement <2 x double> %mul.v.i1.1, double %i4, 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-AO: %mul.v.i0.1 = insertelement <2 x double> undef, double %i0, 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-AO: %mul.v.i0.2 = insertelement <2 x double> %mul.v.i0.1, double %i3, i32 1
; CHECK-AO: %mul = fmul <2 x double> %mul.v.i0.2, %mul.v.i1.2
; CHECK-AO: %mulf = fptrunc <2 x double> %mul to <2 x float>
; CHECK-AO: %0 = bitcast float* %c to <2 x float>*
; CHECK-AO: store <2 x float> %mulf, <2 x float>* %0, align 8
; CHECK-AO: ret void
}
BBVectorize should ignore unreachable blocks. Unreachable blocks can have invalid instructions. For example, jump threading can produce self-referential instructions in unreachable blocks. Also, we should not be spending time optimizing unreachable code. Fixes PR14133. llvm-svn: 166423
2012-10-23 02:00:55 +08:00
; Simple 3-pair chain with loads and stores (unreachable)
define void @test4(i1 %bool, double* %a, double* %b, double* %c) nounwind uwtable readonly {
entry:
br i1 %bool, label %if.then1, label %if.end
if.then1:
unreachable
br label %if.then
if.then:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
store double %mul, double* %c, align 8
%arrayidx5 = getelementptr inbounds double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
br label %if.end
if.end:
ret void
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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test4(
BBVectorize should ignore unreachable blocks. Unreachable blocks can have invalid instructions. For example, jump threading can produce self-referential instructions in unreachable blocks. Also, we should not be spending time optimizing unreachable code. Fixes PR14133. llvm-svn: 166423
2012-10-23 02:00:55 +08:00
; CHECK-NOT: <2 x double>
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-AO-LABEL: @test4(
BBVectorize should ignore unreachable blocks. Unreachable blocks can have invalid instructions. For example, jump threading can produce self-referential instructions in unreachable blocks. Also, we should not be spending time optimizing unreachable code. Fixes PR14133. llvm-svn: 166423
2012-10-23 02:00:55 +08:00
; CHECK-AO-NOT: <2 x double>
}
BBVectorize: Fix a small bug introduced in r167042. We need to make sure that we take the correct load/store alignment when the inputs are flipped. llvm-svn: 167044
2012-10-31 03:47:37 +08:00
; Simple 3-pair chain with loads and stores
define void @test5(double* %a, double* %b, double* %c) nounwind uwtable readonly {
entry:
%i0 = load double* %a, align 8
%i1 = load double* %b, align 8
%mul = fmul double %i0, %i1
%arrayidx3 = getelementptr inbounds double* %a, i64 1
%i3 = load double* %arrayidx3, align 8
%arrayidx4 = getelementptr inbounds double* %b, i64 1
%i4 = load double* %arrayidx4, align 8
%mul5 = fmul double %i3, %i4
%arrayidx5 = getelementptr inbounds double* %c, i64 1
store double %mul5, double* %arrayidx5, align 8
store double %mul, double* %c, align 4
ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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 $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @test5(
BBVectorize: Fix a small bug introduced in r167042. We need to make sure that we take the correct load/store alignment when the inputs are flipped. llvm-svn: 167044
2012-10-31 03:47:37 +08:00
; CHECK: %i0.v.i0 = bitcast double* %a to <2 x double>*
; CHECK: %i1.v.i0 = bitcast double* %b to <2 x double>*
; CHECK: %i0 = load <2 x double>* %i0.v.i0, align 8
; CHECK: %i1 = load <2 x double>* %i1.v.i0, align 8
; CHECK: %mul = fmul <2 x double> %i0, %i1
; CHECK: %0 = bitcast double* %c to <2 x double>*
; CHECK: store <2 x double> %mul, <2 x double>* %0, align 4
; CHECK: ret void
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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-AO-LABEL: @test5(
BBVectorize: Fix a small bug introduced in r167042. We need to make sure that we take the correct load/store alignment when the inputs are flipped. llvm-svn: 167044
2012-10-31 03:47:37 +08:00
; CHECK-AO-NOT: <2 x double>
}