|
马上注册,结交更多好友,享用更多功能,让你轻松玩转社区。
您需要 登录 才可以下载或查看,没有账号?注册
x
Xilinx里面的DSP Slice计算乘法器,请问延迟大概是多少,怎么算?
下面是说明书中的一段话,红色部分是我看不明白的,麻烦高手解释一下:
To get the maximum performance out of the 7 series FPGA DSP48E1 slices, it is desirable to
use all the pipeline stages 【用上所有的流水线是什么意思?不用上所有流水线又是什么情况】within the slice.
To achieve maximum performance when using the DSP48E1 slice, the design needs to be fully pipelined.
For multiplier-based designs, the
DSP48E1 slice requires a three-stage pipeline. For non-multiplier-based designs【DSP slice不是就是要用乘法器吗】, a two-
stage pipeline should be used. Also see the 7-Series FPGA Data Sheet: DC and Switching
Characteristics [Ref 4]. If latency is important in the design and only one or two registers can
be used within the DSP48E1 slice, always use the M register【M寄存器是什么意思】. |
|