微波EDA网,见证研发工程师的成长!
首页 > 硬件设计 > 行业新闻动态 > TI KeyStone II SoC详细介绍

TI KeyStone II SoC详细介绍

时间:07-11 来源:3721RD 点击:

ory Controller (MSMC) is the center of the KeyStone II memory architecture. It provides multiple fast and high-bandwidth channels for processor cores to access DDR and minimizes the access latency by directly connecting to the DDR. The MSMC also provides the flexibility to expand processor cores with little impact at the device level. In addition, it provides multi-bank based fast on-chip SRAM shared among processor cores and IOs. It also provides the I/O cache coherency for the device when the Cortex-A15 processor core is integrated.

The Multicore Navigator provides a packet-based IPC mechanism among processing cores and packet based peripherals. The hardware-managed queues supports multiple-in-multiple-out mode without using mutex. Coupled with the packet-based DMA, the Multicore Navigator provides a highly efficient and software-friendly tool to offload the processing core to achieve other critical tasks.

HyperLink provides a 50-GBaud chip-level interconnect that allows devices to work in tandem. Its low latency, low overhead and high throughput makes it an ideal interface for chip-to-chip interconnections.

There are two generations of KeyStone architecture. The 66AK2E05/02 is based on KeyStone II, which integrates a Cortex-A15 processor CorePac.

1.3设备描述

The 66AK2E05/02 is a high performance device based on TI's KeyStone II Multicore SoC Architecture, incorporating the most performance-optimized Cortex-A15 processor dual-core or quad-core CorePac and C66x DSP core, that can run at a core speed of up to 1.4 GHz. TI's 66AK2E05/02 device enables a high performance, power-efficient and easy to use platform for developers of a broad range of applications such as enterprise grade networking end equipment, data center networking, mission critical, medical imaging, test and automation.

TI's KeyStone II Architecture provides a programmable platform integrating various subsystems (e.g., ARM CorePac (Cortex-A15 Processor Quad Core CorePac), C66x CorePac, network processing, and uses a queue-based communication system that allows the device resources to operate efficiently and seamlessly. This unique devicearchitecture also includes a TeraNet switch that enables the wide mix of system elements, from programmable cores to high-speed IO, to each operate at maximum efficiency with no blocking or stalling.

TI's C66x core launches a new era of DSP technology by combining fixed-point and floating point computational capability in the processor without sacrificing speed, size, or power consumption. The raw computational performance is an industry-leading 38.4 GMACS/core and 19.2 Gflops/core (@ 1.2 GHz operating frequency). It can execute 8 single precision floating point MAC operations per cycle and can perform double- and mixed-precision operations and is IEEE754 compliant. For fixed-point use, the C66x core has 4× the multiply accumulate (MAC) capability of C64x+ cores. The C66x CorePac incorporates 90 new instructions targeted for floating point and vector math oriented processing. These enhancements yield sizeable performance improvements in popular DSP kernels used in signal processing, mathematical, and image acquisition functions. The C66x core is backwards code compatible with TI's previous generation C6000 fixed and floating point DSP cores, ensuring software portability and shortened software development cycles for applications migrating to faster hardware.

The 66AK2E05/02 KeyStone II device integrates a large amount of on-chip memory. The Cortex-A15 processor cores each have 32KB of L1Data and

Copyright © 2017-2020 微波EDA网 版权所有

网站地图

Top