http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48052
Summary: loop not vectorized if index is "unsigned int"
Product: gcc
Version: 4.6.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassig...@gcc.gnu.org
ReportedBy: vincenzo.innoce...@cern.ch
is there any reason why "unsigned int" is not suited to index loop for
auto-vectorization?
example
cat simpleLoop.cc
#include<cstddef>
void loop1( double const * __restrict__ x_in, double * __restrict__ x_out,
double const * __restrict__ c, int N) {
for(int i=0; i!=N; ++i)
x_out[i] = c[i]*x_in[i];
}
void loop2( double const * __restrict__ x_in, double * __restrict__ x_out,
double const * __restrict__ c, unsigned int N) {
for(unsigned int i=0; i!=N; ++i)
x_out[i] = c[i]*x_in[i];
}
void loop21( double const * __restrict__ x_in, double * __restrict__ x_out,
double const * __restrict__ c, size_t N) {
for(size_t i=0; i!=N; ++i)
x_out[i] = c[i]*x_in[i];
}
void loop21( double const * __restrict__ x_in, double * __restrict__ x_out,
double const * __restrict__ c, unsigned long long N) {
for(unsigned long long i=0; i!=N; ++i)
x_out[i] = c[i]*x_in[i];
}
void loop3( double const * __restrict__ x_in, double * __restrict__ x_out,
double const * __restrict__ c, size_t N) {
double const * end = x_in+N;
for(; x_in!=end; ++x_in, ++x_out, ++c)
(*x_out) = (*c) * (*x_in);
}
result:
g++ -v -O2 -ftree-vectorize -ftree-vectorizer-verbose=2 -c simpleLoop.cc
Using built-in specs.
COLLECT_GCC=g++
COLLECT_LTO_WRAPPER=/usr/local/libexec/gcc/x86_64-unknown-linux-gnu/4.6.0/lto-wrapper
Target: x86_64-unknown-linux-gnu
Configured with: ./configure --enable-gold=yes --enable-lto --with-fpmath=avx
Thread model: posix
gcc version 4.6.0 20110205 (experimental) (GCC)
COLLECT_GCC_OPTIONS='-v' '-O2' '-ftree-vectorize' '-ftree-vectorizer-verbose=2'
'-c' '-shared-libgcc' '-mtune=generic' '-march=x86-64'
/usr/local/libexec/gcc/x86_64-unknown-linux-gnu/4.6.0/cc1plus -quiet -v
-D_GNU_SOURCE simpleLoop.cc -quiet -dumpbase simpleLoop.cc -mtune=generic
-march=x86-64 -auxbase simpleLoop -O2 -version -ftree-vectorize
-ftree-vectorizer-verbose=2 -o /tmp/innocent/ccUB9xBg.s
GNU C++ (GCC) version 4.6.0 20110205 (experimental) (x86_64-unknown-linux-gnu)
compiled by GNU C version 4.6.0 20110205 (experimental), GMP version 4.3.2,
MPFR version 2.4.2, MPC version 0.8.1
GGC heuristics: --param ggc-min-expand=30 --param ggc-min-heapsize=4096
ignoring nonexistent directory
"/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/../../../../x86_64-unknown-linux-gnu/include"
#include "..." search starts here:
#include <...> search starts here:
/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/../../../../include/c++/4.6.0
/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/../../../../include/c++/4.6.0/x86_64-unknown-linux-gnu
/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/../../../../include/c++/4.6.0/backward
/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/include
/usr/local/include
/usr/local/lib/gcc/x86_64-unknown-linux-gnu/4.6.0/include-fixed
/usr/include
End of search list.
GNU C++ (GCC) version 4.6.0 20110205 (experimental) (x86_64-unknown-linux-gnu)
compiled by GNU C version 4.6.0 20110205 (experimental), GMP version 4.3.2,
MPFR version 2.4.2, MPC version 0.8.1
GGC heuristics: --param ggc-min-expand=30 --param ggc-min-heapsize=4096
Compiler executable checksum: 0d52c927b640361d99f7371685058a2b
simpleLoop.cc:4: note: LOOP VECTORIZED.
simpleLoop.cc:3: note: vectorized 1 loops in function.
simpleLoop.cc:11: note: not vectorized: data ref analysis failed D.2386_13 =
*D.2385_12;
simpleLoop.cc:10: note: vectorized 0 loops in function.
simpleLoop.cc:16: note: LOOP VECTORIZED.
simpleLoop.cc:15: note: vectorized 1 loops in function.
simpleLoop.cc:21: note: LOOP VECTORIZED.
simpleLoop.cc:20: note: vectorized 1 loops in function.
simpleLoop.cc:28: note: LOOP VECTORIZED.
simpleLoop.cc:26: note: vectorized 1 loops in function.
