Analyzing Cache Misses

Years and Authors of Summarized Original Work

• 2003; Mehlhorn, Sanders

Problem Definition

The problem considered here is multiple sequence access via cache memory. Consider the following pattern of memory accesses. k sequences of data, which are stored in disjoint arrays and have a total length of N, are accessed as follows:

for t : = 1 to N do

select a sequence s _i  ∈ { 1, … k}

work on the current element of sequence s _i

advance sequence s _i to the next element.

The aim is to obtain exact (not just asymptotic) closed form upper and lower bounds for this problem. Concurrent accesses to multiple sequences of data are ubiquitous in algorithms. Some examples of algorithms which use this paradigm are distribution sorting, k-way merging, priority queues, permuting, and FFT. This entry summarizes the analyses of this problem in [5, 8].

Caches, Models, and Cache Analysis

Modern computers have hierarchical memory which consists of registers, one or more levels of caches, main memory, and...