You may question the relevance of these benchmarks themselves but this is the only benchmark for which I have seen that all CPU vendors are willing to provide data.
The AMD excuse is that Intel cheats by designing it's compiler specifically to look good on SPEC scores. What I've always found amusing is how anyone could possibly design a compiler to perform well with no changes in compiler flags and still optimize code for:
Data compression utility, FPGA circuit placement and routing, C compiler, Minimum cost network flow solver, Chess program, Natural language processing, Ray tracing, Perl, Computational group theory, Object Oriented Database, Data compression utility, Place and route simulator, Quantum chromodynamics, Shallow water modeling, Multi-grid solver in 3D potential field, Parabolic/elliptic partial differential equations, 3D Graphics library, Fluid dynamics: analysis of oscillatory instability, Neural network simulation; adaptive resonance theory, Finite element simulation; earthquake modeling, Computer vision: recognizes faces, Computational chemistry, Number theory: primality testing, Finite element crash simulation, Particle accelerator, solving problems regarding temperature, wind, velocity and distribution of pollutants,
There you have it! These are the tests run by SPEC_Base and somehow Intel's compiler designers cheated by designing for this narrowly defined group of applications! No changes in compiler switches and those deceitful cheats somehow produced the fastest scores around. |
