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/LoopVectorize/reduction.ll

497 lines
18 KiB
LLVM
Raw Normal View History

Remove the -licm pass from the loop vectorizer test because the loop vectorizer does it now. llvm-svn: 171930
2013-01-09 09:20:59 +08:00
; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +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"
target triple = "x86_64-apple-macosx10.8.0"
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: @reduction_sum(
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: phi <4 x i32>
;CHECK: load <4 x i32>
;CHECK: add <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: ret i32
define i32 @reduction_sum(i32 %n, i32* noalias nocapture %A, i32* noalias nocapture %B) nounwind uwtable readonly noinline ssp {
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %0, %.lr.ph
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
%sum.02 = phi i32 [ %9, %.lr.ph ], [ 0, %0 ]
%2 = getelementptr inbounds i32* %A, i64 %indvars.iv
%3 = load i32* %2, align 4
%4 = getelementptr inbounds i32* %B, i64 %indvars.iv
%5 = load i32* %4, align 4
%6 = trunc i64 %indvars.iv to i32
%7 = add i32 %sum.02, %6
%8 = add i32 %7, %3
%9 = add i32 %8, %5
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
%sum.0.lcssa = phi i32 [ 0, %0 ], [ %9, %.lr.ph ]
ret i32 %sum.0.lcssa
}
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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: @reduction_prod(
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: phi <4 x i32>
;CHECK: load <4 x i32>
;CHECK: mul <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: mul <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: mul <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: ret i32
define i32 @reduction_prod(i32 %n, i32* noalias nocapture %A, i32* noalias nocapture %B) nounwind uwtable readonly noinline ssp {
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %0, %.lr.ph
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
%prod.02 = phi i32 [ %9, %.lr.ph ], [ 1, %0 ]
%2 = getelementptr inbounds i32* %A, i64 %indvars.iv
%3 = load i32* %2, align 4
%4 = getelementptr inbounds i32* %B, i64 %indvars.iv
%5 = load i32* %4, align 4
%6 = trunc i64 %indvars.iv to i32
%7 = mul i32 %prod.02, %6
%8 = mul i32 %7, %3
%9 = mul i32 %8, %5
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
%prod.0.lcssa = phi i32 [ 1, %0 ], [ %9, %.lr.ph ]
ret i32 %prod.0.lcssa
}
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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: @reduction_mix(
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: phi <4 x i32>
;CHECK: load <4 x i32>
LoopVectorize: Preserve NSW, NUW and IsExact flags. llvm-svn: 167174
2012-11-01 05:40:39 +08:00
;CHECK: mul nsw <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: ret i32
define i32 @reduction_mix(i32 %n, i32* noalias nocapture %A, i32* noalias nocapture %B) nounwind uwtable readonly noinline ssp {
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %0, %.lr.ph
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
%sum.02 = phi i32 [ %9, %.lr.ph ], [ 0, %0 ]
%2 = getelementptr inbounds i32* %A, i64 %indvars.iv
%3 = load i32* %2, align 4
%4 = getelementptr inbounds i32* %B, i64 %indvars.iv
%5 = load i32* %4, align 4
%6 = mul nsw i32 %5, %3
%7 = trunc i64 %indvars.iv to i32
%8 = add i32 %sum.02, %7
%9 = add i32 %8, %6
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
%sum.0.lcssa = phi i32 [ 0, %0 ], [ %9, %.lr.ph ]
ret i32 %sum.0.lcssa
}
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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: @reduction_mul(
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
;CHECK: mul <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: mul <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: mul <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
;CHECK: ret i32
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
define i32 @reduction_mul(i32 %n, i32* noalias nocapture %A, i32* noalias nocapture %B) nounwind uwtable readonly noinline ssp {
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %0, %.lr.ph
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
%sum.02 = phi i32 [ %9, %.lr.ph ], [ 19, %0 ]
Vectorizer: Add support for loop reductions. For example: for (i=0; i<n; i++) sum += A[i] + B[i] + i; llvm-svn: 166351
2012-10-20 07:05:40 +08:00
%2 = getelementptr inbounds i32* %A, i64 %indvars.iv
%3 = load i32* %2, align 4
%4 = getelementptr inbounds i32* %B, i64 %indvars.iv
%5 = load i32* %4, align 4
%6 = trunc i64 %indvars.iv to i32
%7 = add i32 %3, %6
%8 = add i32 %7, %5
%9 = mul i32 %8, %sum.02
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
%sum.0.lcssa = phi i32 [ 0, %0 ], [ %9, %.lr.ph ]
ret i32 %sum.0.lcssa
}
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
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: @start_at_non_zero(
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
;CHECK: phi <4 x i32>
;CHECK: <i32 120, i32 0, i32 0, i32 0>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: add <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
;CHECK: ret i32
define i32 @start_at_non_zero(i32* nocapture %in, i32* nocapture %coeff, i32* nocapture %out, i32 %n) nounwind uwtable readonly ssp {
entry:
%cmp7 = icmp sgt i32 %n, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.09 = phi i32 [ %add, %for.body ], [ 120, %entry ]
%arrayidx = getelementptr inbounds i32* %in, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %coeff, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%mul = mul nsw i32 %1, %0
%add = add nsw i32 %mul, %sum.09
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%sum.0.lcssa = phi i32 [ 120, %entry ], [ %add, %for.body ]
ret i32 %sum.0.lcssa
}
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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: @reduction_and(
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: and <4 x i32>
LoopVectorize: Fix a bug in the initialization of reduction variables. AND needs to start at all-one while XOR, and OR need to start at zero. llvm-svn: 167032
2012-10-31 02:12:36 +08:00
;CHECK: <i32 -1, i32 -1, i32 -1, i32 -1>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: and <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: and <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: ret i32
define i32 @reduction_and(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly {
entry:
%cmp7 = icmp sgt i32 %n, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%result.08 = phi i32 [ %and, %for.body ], [ -1, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%and = and i32 %add, %result.08
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
Add support for reduction variables that do not start at zero. This is important for nested-loop reductions such as : In the innermost loop, the induction variable does not start with zero: for (i = 0 .. n) for (j = 0 .. m) sum += ... llvm-svn: 166387
2012-10-21 13:52:51 +08:00
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
for.end: ; preds = %for.body, %entry
%result.0.lcssa = phi i32 [ -1, %entry ], [ %and, %for.body ]
ret i32 %result.0.lcssa
}
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: @reduction_or(
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: or <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: or <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: or <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: ret i32
define i32 @reduction_or(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly {
entry:
%cmp7 = icmp sgt i32 %n, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%result.08 = phi i32 [ %or, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%or = or i32 %add, %result.08
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%result.0.lcssa = phi i32 [ 0, %entry ], [ %or, %for.body ]
ret i32 %result.0.lcssa
}
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$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: @reduction_xor(
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: xor <4 x i32>
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations. For example on x86 with SSE4.2 a <8 x i8> add reduction becomes movdqa %xmm0, %xmm1 movhlps %xmm1, %xmm1 ## xmm1 = xmm1[1,1] paddw %xmm0, %xmm1 pshufd $1, %xmm1, %xmm0 ## xmm0 = xmm1[1,0,0,0] paddw %xmm1, %xmm0 phaddw %xmm0, %xmm0 pextrb $0, %xmm0, %edx instead of pextrb $2, %xmm0, %esi pextrb $0, %xmm0, %edx addb %sil, %dl pextrb $4, %xmm0, %esi addb %dl, %sil pextrb $6, %xmm0, %edx addb %sil, %dl pextrb $8, %xmm0, %esi addb %dl, %sil pextrb $10, %xmm0, %edi pextrb $14, %xmm0, %edx addb %sil, %dil pextrb $12, %xmm0, %esi addb %dil, %sil addb %sil, %dl llvm-svn: 170439
2012-12-19 02:40:20 +08:00
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
;CHECK: xor <4 x i32>
;CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
;CHECK: xor <4 x i32>
;CHECK: extractelement <4 x i32> %{{.*}}, i32 0
Add support for additional reduction variables: AND, OR, XOR. Patch by Paul Redmond <paul.redmond@intel.com>. llvm-svn: 166649
2012-10-25 08:08:41 +08:00
;CHECK: ret i32
define i32 @reduction_xor(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly {
entry:
%cmp7 = icmp sgt i32 %n, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%result.08 = phi i32 [ %xor, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%xor = xor i32 %add, %result.08
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%result.0.lcssa = phi i32 [ 0, %entry ], [ %xor, %for.body ]
ret i32 %result.0.lcssa
}
Do not vectorize loops with subtraction reductions Since subtraction does not commute the loop vectorizer incorrectly vectorizes reductions such as x = A[i] - x. Disabling for now. llvm-svn: 171537
2013-01-05 06:10:16 +08:00
iLoopVectorize: Non commutative operators can be used as reduction variables as long as the reduction chain is used in the LHS. PR14803. llvm-svn: 171583
2013-01-05 09:15:47 +08:00
; In this code the subtracted variable is on the RHS and this is not an induction variable.
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: @reduction_sub_rhs(
Do not vectorize loops with subtraction reductions Since subtraction does not commute the loop vectorizer incorrectly vectorizes reductions such as x = A[i] - x. Disabling for now. llvm-svn: 171537
2013-01-05 06:10:16 +08:00
;CHECK-NOT: phi <4 x i32>
;CHECK-NOT: sub nsw <4 x i32>
;CHECK: ret i32
iLoopVectorize: Non commutative operators can be used as reduction variables as long as the reduction chain is used in the LHS. PR14803. llvm-svn: 171583
2013-01-05 09:15:47 +08:00
define i32 @reduction_sub_rhs(i32 %n, i32* noalias nocapture %A) nounwind uwtable readonly {
Do not vectorize loops with subtraction reductions Since subtraction does not commute the loop vectorizer incorrectly vectorizes reductions such as x = A[i] - x. Disabling for now. llvm-svn: 171537
2013-01-05 06:10:16 +08:00
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%x.05 = phi i32 [ %sub, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%sub = sub nsw i32 %0, %x.05
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%x.0.lcssa = phi i32 [ 0, %entry ], [ %sub, %for.body ]
ret i32 %x.0.lcssa
}
iLoopVectorize: Non commutative operators can be used as reduction variables as long as the reduction chain is used in the LHS. PR14803. llvm-svn: 171583
2013-01-05 09:15:47 +08:00
; In this test the reduction variable is on the LHS and we can vectorize it.
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: @reduction_sub_lhs(
iLoopVectorize: Non commutative operators can be used as reduction variables as long as the reduction chain is used in the LHS. PR14803. llvm-svn: 171583
2013-01-05 09:15:47 +08:00
;CHECK: phi <4 x i32>
;CHECK: sub nsw <4 x i32>
;CHECK: ret i32
define i32 @reduction_sub_lhs(i32 %n, i32* noalias nocapture %A) nounwind uwtable readonly {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%x.05 = phi i32 [ %sub, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%sub = sub nsw i32 %x.05, %0
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%x.0.lcssa = phi i32 [ 0, %entry ], [ %sub, %for.body ]
ret i32 %x.0.lcssa
}
LoopVectorizer: Improve reduction variable identification The two nested loops were confusing and also conservative in identifying reduction variables. This patch replaces them by a worklist based approach. llvm-svn: 181369
2013-05-08 05:55:37 +08:00
; We can vectorize conditional reductions with multi-input phis.
; CHECK: reduction_conditional
; CHECK: fadd <4 x float>
define float @reduction_conditional(float* %A, float* %B, float* %C, float %S) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%sum.033 = phi float [ %S, %entry ], [ %sum.1, %for.inc ]
%arrayidx = getelementptr inbounds float* %A, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds float* %B, i64 %indvars.iv
%1 = load float* %arrayidx2, align 4
%cmp3 = fcmp ogt float %0, %1
br i1 %cmp3, label %if.then, label %for.inc
if.then:
%cmp6 = fcmp ogt float %1, 1.000000e+00
br i1 %cmp6, label %if.then8, label %if.else
if.then8:
%add = fadd fast float %sum.033, %0
br label %for.inc
if.else:
%cmp14 = fcmp ogt float %0, 2.000000e+00
br i1 %cmp14, label %if.then16, label %for.inc
if.then16:
%add19 = fadd fast float %sum.033, %1
br label %for.inc
for.inc:
%sum.1 = phi float [ %add, %if.then8 ], [ %add19, %if.then16 ], [ %sum.033, %if.else ], [ %sum.033, %for.body ]
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
%sum.1.lcssa = phi float [ %sum.1, %for.inc ]
ret float %sum.1.lcssa
}
; We can't vectorize reductions with phi inputs from outside the reduction.
; CHECK: noreduction_phi
; CHECK-NOT: fadd <4 x float>
define float @noreduction_phi(float* %A, float* %B, float* %C, float %S) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%sum.033 = phi float [ %S, %entry ], [ %sum.1, %for.inc ]
%arrayidx = getelementptr inbounds float* %A, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds float* %B, i64 %indvars.iv
%1 = load float* %arrayidx2, align 4
%cmp3 = fcmp ogt float %0, %1
br i1 %cmp3, label %if.then, label %for.inc
if.then:
%cmp6 = fcmp ogt float %1, 1.000000e+00
br i1 %cmp6, label %if.then8, label %if.else
if.then8:
%add = fadd fast float %sum.033, %0
br label %for.inc
if.else:
%cmp14 = fcmp ogt float %0, 2.000000e+00
br i1 %cmp14, label %if.then16, label %for.inc
if.then16:
%add19 = fadd fast float %sum.033, %1
br label %for.inc
for.inc:
%sum.1 = phi float [ %add, %if.then8 ], [ %add19, %if.then16 ], [ 0.000000e+00, %if.else ], [ %sum.033, %for.body ]
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
%sum.1.lcssa = phi float [ %sum.1, %for.inc ]
ret float %sum.1.lcssa
}
; We can't vectorize reductions that feed another header PHI.
; CHECK: noredux_header_phi
; CHECK-NOT: fadd <4 x float>
define float @noredux_header_phi(float* %A, float* %B, float* %C, float %S) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%sum2.09 = phi float [ 0.000000e+00, %entry ], [ %add1, %for.body ]
%sum.08 = phi float [ %S, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%add = fadd fast float %sum.08, %0
%add1 = fadd fast float %sum2.09, %add
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 128
br i1 %exitcond, label %for.body, label %for.end
for.end:
%add1.lcssa = phi float [ %add1, %for.body ]
%add.lcssa = phi float [ %add, %for.body ]
%add2 = fadd fast float %add.lcssa, %add1.lcssa
ret float %add2
}
LoopVectorizer: Disallow reductions whose header phi is used outside the loop If an outside loop user of the reduction value uses the header phi node we cannot just reduce the vectorized phi value in the vector code epilog because we would loose VF-1 reductions. lp: p = phi (0, lv) lv = lv + 1 ... brcond , lp, outside outside: usr = add 0, p (Say the loop iterates two times, the value of p coming out of the loop is one). We cannot just transform this to: vlp: p = phi (<0,0>, lv) lv = lv + <1,1> .. brcond , lp, outside outside: p_reduced = p[0] + [1]; usr = add 0, p_reduced (Because the original loop iterated two times the vectorized loop would iterate one time, but p_reduced ends up being zero instead of one). We would have to execute VF-1 iterations in the scalar remainder loop in such cases. For now, just disable vectorization. PR16522 llvm-svn: 186256
2013-07-14 03:09:29 +08:00
; When vectorizing a reduction whose loop header phi value is used outside the
; loop special care must be taken. Otherwise, the reduced value feeding into the
; outside user misses a few iterations (VF-1) of the loop.
; PR16522
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: @phivalueredux(
LoopVectorizer: Disallow reductions whose header phi is used outside the loop If an outside loop user of the reduction value uses the header phi node we cannot just reduce the vectorized phi value in the vector code epilog because we would loose VF-1 reductions. lp: p = phi (0, lv) lv = lv + 1 ... brcond , lp, outside outside: usr = add 0, p (Say the loop iterates two times, the value of p coming out of the loop is one). We cannot just transform this to: vlp: p = phi (<0,0>, lv) lv = lv + <1,1> .. brcond , lp, outside outside: p_reduced = p[0] + [1]; usr = add 0, p_reduced (Because the original loop iterated two times the vectorized loop would iterate one time, but p_reduced ends up being zero instead of one). We would have to execute VF-1 iterations in the scalar remainder loop in such cases. For now, just disable vectorization. PR16522 llvm-svn: 186256
2013-07-14 03:09:29 +08:00
; CHECK-NOT: x i32>
define i32 @phivalueredux(i32 %p) {
entry:
br label %for.body
for.body:
%t.03 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%p.addr.02 = phi i32 [ %p, %entry ], [ %xor, %for.body ]
%xor = xor i32 %p.addr.02, -1
%inc = add nsw i32 %t.03, 1
%exitcond = icmp eq i32 %inc, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 %p.addr.02
}
LoopVectorize: External uses must use the last value in a reduction cycle Otherwise, we don't perform operations that would have been performed on the scalar version. Fixes PR17498. llvm-svn: 192133
2013-10-08 05:05:43 +08:00
; Don't vectorize a reduction value that is not the last in a reduction cyle. We
; would loose iterations (VF-1) on the operations after that use.
; PR17498
; CHECK-LABEL: not_last_operation
; CHECK-NOT: x i32>
define i32 @not_last_operation(i32 %p, i32 %val) {
entry:
%tobool = icmp eq i32 %p, 0
br label %for.body
for.body:
%inc613.1 = phi i32 [ 0, %entry ], [ %inc6.1, %for.body ]
%inc511.1 = phi i32 [ %val, %entry ], [ %inc5.1, %for.body ]
%0 = zext i1 %tobool to i32
%inc4.1 = xor i32 %0, 1
%inc511.1.inc4.1 = add nsw i32 %inc511.1, %inc4.1
%inc5.1 = add nsw i32 %inc511.1.inc4.1, 1
%inc6.1 = add nsw i32 %inc613.1, 1
%exitcond.1 = icmp eq i32 %inc6.1, 22
br i1 %exitcond.1, label %exit, label %for.body
exit:
%inc.2 = add nsw i32 %inc511.1.inc4.1, 2
ret i32 %inc.2
}