The role of the compiler is fundamental to exploit the hardware capabili-
ties of a system running a particular application, minimizing the sequential execution
time and, in some cases, offering the possibility of parallelizing part of the code
automatically. This paper relies on the SPEC CPU2006 v1.1 benchmark suite to eval-
uate the performance of the code generated by three widely-used compilers (Intel
C++/Fortran Compiler 11.0, Sun Studio 12 and GCC 4.3.2). Performance is measure
in terms of base speed for reference problem sizes. Both sequential and automatic
parallel performance obtained is analyzed, using different hardware architectures and
configurations. The study includes a detailed description of the different problems
that arise while compiling SPEC CPU2006 benchmarks with these tools, an informa-
tion difficult to obtain elsewhere.
Having in mind that performance is a moving target in the field of compilers, our
evaluation shows that the sequential code generated by both Sun and Intel compilers
for the SPEC CPU2006 integer benchmarks present a similar performance, while the
floating-point code generated by Intel compiler is faster than its competitors. With
respect to the auto-parallelization options offered by Intel and Sun compilers, our
study shows that their benefits only apply to some floating-point benchmarks, with an
average speedup of 1.2× with four processors. Meanwhile, the GCC suite evaluated
is not capable of compiling the SPEC CPU2006 benchmark with auto-parallelization
options enabled.
