Many scientific applications that run on today's multipro- cessors, such as weather forecasting and seismic analy- sis, are bottlenecked by their file-I/O needs. Even if the multiprocessor is configured with sufficient I/O hardware, the file-system software often fails to provide the avail- able bandwidth to the application. Although libraries and enhanced file-system interfaces can make a significant im- provement, we believe that fundamental changes are needed in the file-server software. We propose a new technique, disk-directed I/O, to allow the disk servers to determine the flow of data for maximum performance. Our simula- tions show that tremendous performance gains are possible. Indeed, disk-directed I/O provided consistent high perfor- mance that was largely independent of data distribution, obtained up to 93% of peak disk bandwidth, and was as much as 16 times faster than traditional parallel file sys-tems.