Current and future (HEP) experiments look for extremely rare processes hidden by severe background conditions. The trigger
directly affects our ability to extract these tiny signals from the huge backgrounds. Fortunately digital electronics is becoming so powerful that the difference between real-time and offline algorithm
performances can be significantly reduced, even in extremely complex situations.
We propose Supercomputers that combine the high performances of rigid dedicated hardware with most of the distinctive flexibility of general-purpose but lower-performance CPUs. The
architecture's key role is played by powerful FPGAs, the modern programmable devices, cooperating with standard-cell ASICs for utmost gate integration requirements. Optimal partitioning of a very complex
algorithm across a variety of computing technologies is a powerful strategy that offers enormous computing potentiality to scientific fields limited by computer power necessities.
High Energy Physics experiments, forced by necessity into the dominant trend towards very large computing farms, would particularly benefit by complementing CPUs with this innovative strategy.
