Gordon Bell Prize - Prize Criteria

Prize Criteria

The ACM Gordon Bell Prize is primarily intended to recognize performance achievements that demonstrate:

• evidence of important algorithmic and/or implementation innovations
• clear improvement over the previous state-of-the-art
• solutions that don’t depend on one-of-a-kind architectures (systems that can only be used to address a narrow range of problems, or that can’t be replicated by others)
• performance measurements that have been characterized in terms of scalability (strong as well as weak scaling), time to solution, efficiency (in using bottleneck resources, such as memory size or bandwidth, communications bandwidth, I/O), and/or peak performance
• achievements that are generalizable, in the sense that other people can learn and benefit from the innovations

In earlier years, multiple prizes were sometimes awarded to reflect different types of achievements. According to current policies, the Prize can be awarded in one or more of the following categories, depending on the entries received in a given year:

Peak Performance: If the entry demonstrates outstanding performance in terms of floating point operations per second on an important science/engineering problem; the efficiency of the application in using bottleneck resources (such as memory size or bandwidth) is also taken into consideration.

Special Achievement in Scalability, Special Achievement in Time to Solution: If the entry demonstrates exceptional Scalability, in terms of both strong and weak scaling, and/or total time to solve an important science/engineering problem.