Issue No. 09 - September (1997 vol. 30)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/2.612249
<p>Researchers from the University of Michigan conclude that billion-transistor processors will be much as they are today, but just bigger, faster, and wider (issuing more instructions at once). The authors describe the key problems (instruction supply, data memory supply, and an implementable execution core) that prevent current superscalars from scaling up to the 16- or 32-instructions per issue. They propose using out-of-order fetching, Multi-Hybrid branch predictors, and trace caches to improve the instruction supply. They predict that replicated first-level caches, huge on-chip caches, and data value speculation will enhance the data supply. To provide a high-speed, implementable execution core capable of sustaining the necessary instruction throughput, they advocate a large, out-of-order-issue instruction window (2,000 instructions), clustered (separated) banks of functional units, and hierarchical scheduling of ready instructions. They contend that the current uniprocessor model can provide sufficient performance and use a billion transistors effectively without changing the programming model or discarding software compatibility. </p>
M. Evers, D. H. Friendly, S. J. Patel, J. Stark and Y. N. Patt, "One Billion Transistors, One Uniprocessor, One Chip," in Computer, vol. 30, no. , pp. 51-57, 1997.