NoSQ: Store-Load Communication without a Store Queue
نویسندگان
چکیده
منابع مشابه
Scaling Load-Store Queue
In order to tolerate long latency instructions, large load and store queue is necessary to bypass in flight information to dependent instruction; but as the latency goes up, the size of the load and store queue will increase as well, which will impact cycle time, area and power. Hierarchical designs in [2] and [10] was proposed to alleviate cycle time problem, but the CAM and search functions r...
متن کاملA Power-Efficient and Scalable Load-Store Queue Design
The load-store queue (LQ-SQ) of modern superscalar processors is responsible for keeping the order of memory operations. As the performance gap between processing speed and memory access becomes worse, the capacity requirements for the LQ-SQ increase, and its design becomes a challenge due to its CAM structure. In this paper we propose an efficient load-store queue state filtering mechanism tha...
متن کاملInterprocessor Communication Seen as Load-store Instruction Generalization
This paper presents the current (2007) author’s views and opinions on interprocessor communication (IPC) and how it should evolve in future multiprocessors, with an attempt to define an IPC architecture that is uniformly extensible from small-scale chip multiprocessors (CMP) to large-scale multi-chip parallel systems. We adopt the viewpoint that all IPC is based on data transfers through an (on...
متن کاملMultiversioning in the Store Queue Is the Root of All Store-forwarding Evil
As semiconductor technologies have continued to scale according to Moore’s Law, complexity, power consumption, and energy dissipation have become first-order considerations in microprocessor design. In processors that issue instructions out-of-order, store-load forwarding is a source of significant complexity and energy dissipation. To decrease the complexity and improve the energy efficiency o...
متن کاملDuplicating and Deconstructing Virtual Load/Store Queues
ABSTRACT Virtual load/store queues (VLSQs) within existing physical load/store queues (LSQ) have been proposed as an effective mechanism for reducing energy losses and increasing performance. The VLSQ restricts reordering of memory operations by limiting the number of memory instructions visible to the issue logic. This decreases the amount of execution time wasted in replay traps and leads to ...
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 Micro
سال: 2007
ISSN: 0272-1732
DOI: 10.1109/mm.2007.17