Increased the Microblaze performance for the VCU118 carrier:
- Increased the size of Instruction Cache and Data Cache to 64kB
Increased the Microblaze clock frequency:
- Using the DDR4 Controller to generate a new sys_mb_clk of 214 MHz to drive all the Microblaze interfaces at higher frequencies
Signed-off-by: Filip Gherman <Filip.Gherman@analog.com>
The HBM interfacing core requires a 450MHz clock, make it part of the
base design.
The clock can't be obtained from the DDR controller so a clock wizard is
used instead.
Deprecate unused parameters.
Change to MEM_SIZE_LOG2, to support only power of 2 storage sizes for
now. However in the future we might want to add support for non pow2
sizes so register map is not changed.
Change transfer length to -1 value to spare logic.
Change FIFO interface to AXIS to have backpressure, this allows the
implementation of data movement logic in the storage unit and let the
FSM handle high level control an synchronization and control the storage
unit through a control interface.
Refactor FSM to have preparation states where slow storages can be
configured and started ahead of the data handling.
Make bypasss FIFO optional since in some cases causes timing failures
due the missing output register of the memory. This can be targeted in
a later commit.
Hook up underflow/overflow to regmap useful in case of external memory
where rate drops due misconfiguration can be detected.
Cleanup for verilator.
Scripting:
Add HBM and DDR external memory support using util_hbm IP
Replace asym_block_ram with util_do_ram IP
There are no external termination resistors on the VCU118 and VCU128 for
the SGMII clock lines.
The board files of the VCU118 enables them, but this was not reflected in the
constraint files.
For VCU128 the clocking is similar, even if diff terms are not set in the
board files we should have a consistent approach with the VCU118.
There are no external termination resistors on the VCU118 for the SGMII
clock lines. The board files enables them, but this was not reflected in the
constraint files.
The default address space for a new bridge is 256 Kbytes. Add an
avl_address_width attribute to the ad_cpu_interoconnect porecess to
define other address space sizes if needed.
The avl_peripheral_mm_bridge will have an 128 Kbyte address space from
address 0x0000.
This commit adds a new synthesis option to the design, that controls
whether an internal clock domain crossing will be generated. Disabling
this option allows you to use a synchronization signal that is
synchronized to the write clock domain externally, and possibly shared
between multiple devices.
The default value retains the old behavior.
Signed-off-by: David Winter <david.winter@analog.com>
The derived clocks of the zynqmp core are not calculated correctly due
rounding issues, instead of 100MHz the value of 99999001 is received
causing warnings during system validation.
This can be fixed/worked around with the proper reference clock
definition.
Update vivado version to 2020.2:
- update default vivado version from 2020.1 to 2020.2
- add conditions to apply specific contraints only in Out Of Context mode.
- update DDR controler parameters for vcu118 and kcu105 dev boards
Without defining this signal, the UART lines receive garbage data
when no cable is connected to the J4 USB UART port.
The GPIO9 is enabled in the reference base design along with the
4MA CURRENT_STRENGTH constraint on the UART pins
-change the video memory interfacing from f2h_axi_slave to
f2h_sdram0
- add f2h_sdram1 port as the default interface for converter DMA
- set as default the full HD resolution at 60 FPS (pixel clock 148.5MHz)
- use a second 200MHz(198MHz) clock from the pixel_clk_pll, as DMA source
to destination clock.
Due to the interface differences between HPS's AXI4 and DMA's AXI4, the
tool will try to automaticaly add some bridges between the two
interface. Unfortunatly it does generate timing issues at the f2sdram0
interface of the HPS instance. By explicitly instantiating an AXI
bridge, these timing issues disappears.
If we have a lot of peripherals connected to the CPU's memory interface,
the generated interconnect can grow to much decreasing the timing
margin.
One solution is to group the peripherals by its interface types and
functions and use bridges to connect them to the memory interface.
This commit adds the possibility to insert an Avalon Memory Mapped
bridge when we create the connection between the peripheral and CPU.
Should be used just with Avalaon Memory Mapped interfaces.
Iacob_Liviu
Sergiu Arpadi
Filip Gherman
Laszlo Nagy
PopPaul2021
David Winter
hotoleanudan
Adrian Costina
Istvan Csomortani
stefan.raus
AndreiGrozav
Stanca Pop
Stanca.Pop