This dissertation presents an automated system to generate highly efficient, platform-
adapted implementations of sparse matrix kernels. We show that conventional …

Recent studies have shown that, in highly associative caches, the performance gap between
the least recently used (LRU) and the theoretical optimal replacement algorithms is large …

This paper makes a case for a new cross-layer interface, Expressive Memory (XMem), to
communicate higher-level program semantics from the application to the system software …

Recent studies have shown that in highly associative caches, the performance gap between
the least recently used (LRU) and the theoretical optimal replacement algorithms is large …

Graphics Processing Units (GPUs) have become an attractive platform for accelerating
challenging applications on a range of platforms, from High Performance Computing (HPC) …

the present invention relates to an optimum code generation method and a compiler device
for a multiprocessor. More particularly, it relates to a method of generating codes for parallel …

This paper presents a performance comparison of several file system allocation policies.
The file systems are designed to provide high bandwidth between disks and main memory …

Many optimization techniques, including several targeted specifically at embedded systems,
depend on the ability to calculate the number of points in a parameterized polytope. It is well …

Recent studies on program execution behavior reveal that a large amount of execution time
is spent in small frequently executed regions of code. Whereas adaptive cache management …

Caches have an increasing impact on overall performance because of the growing gap
between CPU cycle times and memory access times. Therefore, improving the cache …