Vector Architecture Exploits the Data-Level Parallelism to Achieve Significant Speedup

Essay

Vector architecture exploits the data-level parallelism to achieve significant speedup. For programmers, it is usually be make the problem/data bigger. For instance, programmers ten years ago might want to model a map with a 1000 x 1000 single-precision floating-point array, but may now want to do this with a 5000 x 5000 double-precision floating-point array. Obviously, there is abundant data-level parallelism to explore. Give some reasons why computer architecture do not intend to create a super-big vector machine (in terms of the number and the length of vector registers) to take advantage of this opportunity?