Results 1 - 10
of
21,567
Table 1: Parallel processors comparison
"... In PAGE 1: ... During the last years, di erent authors have focused on the realization of parallel preprocessing of multi-dimensional signals, using either purely digital techniques [1] or mixed-signal techniques, like in [2]. The data in Table1 can help us to compare these two approaches. Here, the peak computing power (expressed as operations per second: XPS) per unit area and power is shown.... In PAGE 2: ... Also, taking full advantage of the full digital resolution requires highly accurate A/D converters, what creates additional area and power overhead. The third row in Table1 corresponds to the chip presented here. This chip out- performs the one in [2] in terms of functionality as it implements a reduced model of the biological retina [3].... ..."
Table 2-2 contains a list of vector and parallel processors that are
1991
Table 2.1: SIMD distributed-memory parallel processor implementations.
Table 3: Summary of results with 5 processors and parallel heuristics
1993
"... In PAGE 15: ... Time: 5 processors with heuristics. Table3 is a comparison of the system with the 5 processors and the four heuristics with the 1 processor and 5 processor systems without the four heuris- tics. While 2.... ..."
Cited by 8
Table 3. Ideal and{parallelism Program Scheduling Processors
"... In PAGE 7: ... Benchmarks with good performance in Tables 1 and 2 show good speedups here also. But the inverse is not true: benchmarks with low e ciency in max- imum parallelism can perform well in actual executions: for example the sim- ulated speedups for the benchmark bpebpf (Figure 3), are quite good for a reduced number of processors (see Table3 ). As expected, more regular bench-... ..."
Table II. Absolute Speedups for Parallelized Programs Number of Processors
2000
Cited by 86
Table 3 Comparison of sequential and parallel (on four processors) execution times.
"... In PAGE 18: ... Further experimentation is necessary to evaluate the accuracy of execution-time estimates for different programs. Table3 contains parallel-execution-time measurements for a small collection of programs from the GENESIS [58], PERFECT [59], and SPEC [60] benchmark sets. These programs are much larger than the example program discussed in Figures 1-5 and are more representative of real applications.... ..."
Table 6.4 Rotating geometry (parallel computation on 128 processors)
1999
Cited by 30
Results 1 - 10
of
21,567