UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

取消
显示结果 
搜索替代 
您的意思是: 
Adventurer
Adventurer
256 次查看
注册日期: ‎12-23-2018

为什么SDx下硬件加速生成的结果和在vivado HLS生成的结果不同

平台:zedBoard  SDx 2018.2  , SDx调用例程mmult_hw,然后我自己在vivado HLS下自建了这个程序,所有的优化指令都和SDx下一模一样,包括tcl文件里面的指令以及解决方案,我核对过SDx生成的HLS工程,没有发现哪里还有区别,为什么自己建的工程,生成的资源报告却不同,虽然时钟数一致。

vivado HLS  pic.png
vivado HLS.png
SDx.png
0 项奖励
1 条回复1
Teacher xilinxacct
Teacher
244 次查看
注册日期: ‎10-24-2018

Re: 为什么SDx下硬件加速生成的结果和在vivado HLS生成的结果不同

@liujiefei

I don't know if this is your case, but there is not a fixed 1 to 1 relationship with LUTs used and time required.

In fact the opposite can exist, where you use more LUTs to get a faster result. (e.g. better routing by less fully used LUTs)

The depth and level of the logic is more indicative of the time. (e.g. the propagation through the hardware present). If the 'worst case' was the same, no improvement in time, but improvement in resources.

Hope that helps

 

0 项奖励