Cache-Oblivious Algorithms
Citations
10 citations
9 citations
9 citations
Cites background or methods from "Cache-Oblivious Algorithms"
...[29, 30] and Prokop [30], which was based on Sleator and Tarjan’s [44]’s classic paging results; cache-adaptive analysis [16, 17, 37]; and parallel caching models based on work stealing [23]....
[...]
...HBM does not fit into a standard memory hierarchy model [12, 30], because in traditional hierarchies, both the latency and bandwidth improve as the levels get smaller....
[...]
...These include the seminal ideal cache-model of Frigo et al. [29, 30] and Prokop [30], which was based on Sleator and Tarjan’s [44]’s classic paging results; cache-adaptive analysis [16, 17, 37]; and parallel caching models based on work stealing [23]....
[...]
...Unlike the Ideal Cache model [29, 30], our HBM model has two resources to manage: the HBM itself and the far channel between...
[...]
9 citations
Cites methods from "Cache-Oblivious Algorithms"
...We conclude by mentioning a solution [13] that solves the weak prefix search problem efficiently in the Cache-Oblivious Model [14], and, thus, makes the above approach suitable for this model....
[...]
9 citations
References
21,651 citations
11,795 citations
"Cache-Oblivious Algorithms" refers methods in this paper
...The basic algorithm is the well-known “six-step” variant [Bailey 1990; Vitter and Shriver 1994b] of the Cooley-Tukey FFT algorithm [Cooley and Tukey 1965]....
[...]
11,671 citations
"Cache-Oblivious Algorithms" refers background or methods in this paper
...We assume that the caches satisfy the inclusion property [Hennessy and Patterson 1996, p. 723], which says that the values stored in cache i are also stored in cache i + 1 (where cache 1 is the cache closest to the processor)....
[...]
...Moreover, the iterative algorithm behaves erratically, apparently due to so-called “conflict” misses [Hennessy and Patterson 1996, p. 390], where limited cache associativity interacts with the regular addressing of the matrix to cause systematic interference....
[...]
...Our strategy for the simulation is to use an LRU (least-recently used) replacement strategy [Hennessy and Patterson 1996, p. 378] in place of the optimal and omniscient replacement strategy....
[...]
...The ideal cache is fully associative [Hennessy and Patterson 1996, Ch. 5]: cache blocks can be stored anywhere in the cache....
[...]