| 1 |
Latency tolerant algorithms will be essential
-
Today the most extreme latency issues are seen in networks of workstations and other such metacomputers.
|
| 2 |
Hardware mechanisms for hiding and/or tolerating latency.
|
| 3 |
Language facilities (such as programmer-directed prefetching) for managing latency.
|
| 4 |
Need a "hierarchy little language" to describe latency structure
|
| 5 |
Software tools, such as visualization facilities, for measuring and managing latency.
|
| 6 |
Performance studies of distributed SMPs to study latency issues.
|
