Leveraging Hardware Caches for Memoization
نویسندگان
چکیده
منابع مشابه
Hardware Memoization of Mathematical and Trigonometric Functions
Memoization is saving the input and output of previous calculations and using the output if the input is encountered again. memo-tables are cache-like tables that store the operands and results of calculations that are candidates for memoization. A successful lookup gives the result of a multi-cycle computation in a single cycle, and a failed lookup doesn't necessitate a penalty in computation ...
متن کاملWay Memoization to Reduce Fetch Energy in Instruction Caches
Instruction caches consume a large fraction of the total power in modern low-power microprocessors. In particular, set-associative caches, which are preferred because of lower miss rates, require greater access energy on hits than direct-mapped caches; this is because of the need to locate instructions in one of several ways. Way prediction has been proposed to reduce power dissipation in conve...
متن کامل8. Algorithms for Hardware Caches and TLB
Over the last 20 years or so CPU clock rates have grown explosively, and CPUs with clock rates exceeding 2 GHz are now available in the mass market. Unfortunately, the speed of main memory has not increased as rapidly: today’s main memory typically has a latency of about 60 ns. This implies that the cost of accessing main memory can be 120 times greater than the cost of performing an operation ...
متن کاملLeveraging Smartphone Hardware Capabilities for Alternative Authentication
In this project, we explore two forms of user authentication, alternative to the alpha-numeric password, through utilization of various hardware components in a modern smartphone. These components act as input channels for biometric and geolocative data, which can be used to validate the identity of a user through gesture-based authentication (via the accelerometer and orientation sensor) and l...
متن کاملLeveraging Graphics Hardware for Vision Based Human Computer Interaction
We present a system which allows users to draw on arbitrary display surfaces. The system is implemented using consumer electronics; data is gathered with a webcam, and most video analysis is done on a desktop graphics card. Two variants of the core system are discussed. In the first, users draw on a computer monitor using a laser pointer. In the second, a light pen is used to draw on a display ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Computer Architecture Letters
سال: 2018
ISSN: 1556-6056
DOI: 10.1109/lca.2017.2762308