Towards Relational Cache Analysis

ثبت نشده
چکیده

Programs in hard real-time systems have to satisfy non-functional constraints, such as timing constraints, beyond their functional requirements. The static analysis that derives bounds on the execution times has to take into account the components of the underlying hardware platform, such as caches and pipelines, in order to derive tight bounds on the execution times. Static cache analysis classifies memory accesses as cache hits, cache misses or unknown. State-of-the-art cache analyses cannot precisely model accesses whose addresses are imprecisely determined: no hits can be predicted for those accesses and they deteriorate analysis information excessively. We present a relational cache analysis that can represent cache elements with imprecisely determined addresses and uses relations between cache elements — obtained by congruence analyses — in order to do precise updates and classifications. This paves the way for cache analysis to profit from analyses other than value analyses and enables the prediction of hits for new classes of accesses, e.g. those with input-dependent addresses.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Computing Same Block Relations for Relational Cache Analysis

In contrast to the classical cache analysis of Ferdinand, the relational cache analysis does not rely on precise address information. Instead, it uses same block relations between memory accesses to predict cache hits. The relational data cache analysis can thus also predict cache hits if fully unrolling a loop is not feasible during analysis, for example due to high memory consumption or long ...

متن کامل

Asynchronous Adaptive Delay Tolerant Index Cache Using In-memory Delta Cell

Relational database indexes, used to speed up access to data stored in a database, are maintained when data in the source table of the index is modified. Therefore, relational database index management can involve time consuming manual analysis and specialized development efforts, and impose organizational overhead and database usage costs, especially in the context of big data. To address this...

متن کامل

Two-Level Caching of Composite Object Views of Relational Databases

We describe a two-level client-side cache for composite objects mapped as views of a relational database. A semantic model, the Structural Model, is used to specify joins on the relational database that are useful for de ning composite objects. The lower level of the cache contains the tuples from each relation that have already been loaded into memory. These tuples are linked together from rel...

متن کامل

Client's Cache Updating Using Idle Time of Clients in Relational Database Management Systems

Although multi-tiered software development is taking the place in database application environments, client-server infrastructure has still been in use for years. Furthermore, both infrastructures still need to be improved in some aspects. One of the important aspects of improvement is caching. This paper addresses the issue of caching in relational database system within client-server structur...

متن کامل

Weaving Relations for Cache Performance

Relational database systems have traditionally optimzed for I/O performance and organized records sequentially on disk pages using the N-ary Storage Model (NSM) (a.k.a., slotted pages). Recent research, however, indicates that cache utilization and performance is becoming increasingly important on modern platforms. In this paper, we first demonstrate that in-page data placement is the key to hi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012