Main Content

记忆Controller

Arbitrate memory transactions for one or more Memory Channel blocks

  • 图书馆:
  • SOC阻滞 /内存

  • 记忆Controller block

Description

记忆Controllerblock arbitrates between masters and grants them unique access to shared memory. Configure this block to support multiple channels with various arbitration protocols. The记忆Controller块还具有仪器来记录和显示性能数据,使您能够在模拟时进行调试和了解系统的性能。

这following image shows the implementation of the记忆Controller堵塞。

这numbers in the image represent different latency stages of the block.

  1. 一个爆发的重点进入街区。

  2. 这request may be delayed by arbitration until it is granted access to the bus. Set the arbitration policy in互连仲裁

  3. 如果您的模型在首次转移开始之前需要额外的延迟,请在请求首先转移(时钟)

  4. 突发执行延迟是由突发大小,数据宽,时钟频率和带宽衍生(%)价值。

  5. If your model requires a delay from burst completion until a burst response is issued to the channel, set that value in最后转移到交易完成(时钟)

内存控制器具有内部状态,使用时可见Logic Analyzer查看仿真和执行指标。状态值是:

  • BurstRequest:爆发请求进入块。

  • BurstExecuting:一个正在执行。

  • 布斯多内:爆发完成了。

  • BurstComplete: The burst is complete and theburstDonesignal is sent to the master.

For information about visualizing memory controller latencies, see记忆Controller Latency Plots

Limitations

  • When互连仲裁is set to罗宾,,,,the model does not support simulation stepping. For more information on simulation stepping, seeSimulation Stepper

  • 一个包含一个模型记忆Channel块不支持仿真步进。万博1manbetx有关模拟步进的更多信息,请参阅Simulation Stepper

Ports

Input

expand all

该端口接收到记忆访问作为消息的请求。将此输入端口连接到爆发请求消息端口之一(wrBurstReqorrdburstreq) from a记忆Channelor内存流量生成器堵塞。有关消息的更多信息,请参阅Messages

的数量burstReqninput ports is defined by thenumber of mastersparameter.burstReqnrepresents thenTH输入端口。

Data Types:Burstrequest2Busobj

输出

expand all

在授予主人对内存的访问并完成爆发交易完成后,此端口发送了一条交易完成的消息。然后,根据仲裁方案将内存访问给出下一个主人。有关消息的更多信息,请参阅Messages

的数量burstDonenoutput ports is defined by thenumber of mastersparameter.burstDonenrepresents thenth input port

Data Types:Burstrequest2Busobj

参数

expand all

This property is read-only.

此参数显示指向选定的硬件板的链接。单击链接以打开配置参数,然后调整设置或选择其他板。

要了解有关内存控制器配置参数的更多信息,请参见FPGA设计(MEM控制器)

Main

设置此参数以相应地生成接口,并指定有多少大师连接到内存。

Advanced

设置内存内部连接块的仲裁策略。当多个大师请求内存访问时,策略由此参数的值确定。

  • 罗宾基于上一个服务时间设置公平的仲裁。

  • Fixed port priority设置固定优先级burstReq1,,,,burstReq2,,,,burstReq3,,,,and so on, whereburstReq1gets the highest priority.

选择this parameter to use the same model-wide settings as set in the configuration parameters. Clear this parameter to customize the settings for this memory controller. When using customized settings, values are still checked against hardware-specific constraints. For more information, seeFPGA设计(MEM控制器)

This property is read-only.

该值显示了内存控制器和外部内存之间计算出的带宽。它被计算为频率(MHz)multiplied byData width (bits)

这clock rate of the bus used to drive interactions with the external memory. The controller frequency determines the overall system bandwidth for external memory that must be shared among all the masters in the model.

依赖性

要启用此参数,请清除使用硬件板设置parameter.

将存储器控制器和内存互连之间的数据路径的宽度设置为位。

依赖性

要启用此参数,请清除使用硬件板设置parameter.

模型内存交易效率低下,由降低百分比值指定。对于每100个时钟,记忆事务执行被暂停,以等于时钟的数量带宽衍生。To set this parameter, measure the maximum bandwidth on your board and reflect the bandwidth derating from your board in this parameter. See an example inAnalyze Memory Bandwidth Using Traffic Generators

依赖性

要启用此参数,请清除使用硬件板设置parameter.

Specify the delay, in clock cycles, between a read or write request and the start of a transfer. Specify nonnegative integer values in bothWriteandRead盒子。

此延迟是向内存控制器提出请求与返回响应之前的时钟周期数。它反映在Logic Analyzerwaveforms as the time that the memory controller state remains asBurstAccepted。For more information about viewing waveforms in simulation, see缓冲和爆发波形

To set this value, measure the clock cycles between the burst-request and start of transfer on your board. For instructions for extracting this information from a hardware execution, seeConfiguring and Querying the AXI Interconnect Monitor

依赖性

要启用此参数,请清除使用硬件板设置parameter.

指定内存传输结束和交易结束之间的时钟周期延迟。在这两个中指定非负整数值WriteandRead盒子。

要设置此值,请测量爆发结束和板上交易完成之间的时钟周期。有关从硬件执行中提取此信息的说明,请参阅Configuring and Querying the AXI Interconnect Monitor

依赖性

要启用此参数,请清除使用硬件板设置parameter.

Performance

点击启动性能应用程序to open the Performance Metrics window. For additional information, see模拟性能图

扩展功能

定点转换
Design and simulate fixed-point systems using Fixed-Point Designer™.

在R2019a中引入