User manual

Table Of Contents
Zynq-7000 AP SoC Technical Reference Manual www.xilinx.com 654
UG585 (v1.11) September 27, 2016
Chapter 22: Programmable Logic Design Guide
22.3.3 OCM Efficiency
A similar efficiency test to the DDR example above using four high-performance ports to OCM show
a maximum efficiency of 80%.
22.3.4 Interconnect Throughput Bottlenecks
At typical high-performance clock ratios, the PS interconnect is not typically the limiting factor in a
high-performance system. One exception to this is when using two high-performance (HP/AFI) ports
to DDR. Since ports 0/1 and 2/3 are arbitrated before the DDR controller, it is beneficial in the two
port case to use one port each from these pairs, such as port 0 and 2.
Table 22-6: DDR Efficiency versus AXI Burst Length (System #1, 4 HP/AFI masters, Sequential
Read/Writes)
Burst Length DDR Efficiency (%)
487
887
16 87
Table 22-7: Latency Example Measurement Systems
System
PL AXI Clock
(MHz)
CPU_6x4x
(MHz)
CPU_2x
(MHz)
DDR_3x
(MHz)
DDR_2x
(MHz)
DRAM
DRAM
(Mb/s)
#1 150 675 225 525 350 DDR3 1,050