Quantcast
Channel: Xilinx Wiki : Xilinx Wiki - all changes
Viewing all 11776 articles
Browse latest View live

Zynq UltraScale Plus MPSoC Graphics- GPU application debugging using ARM Mali Graphics Debugger tool

$
0
0
...
{writing_ip.PNG} Fig:Writing IP address
With the above steps Mali graphics debugger is connected with the target board. Now you are ready to debug the graphics application.
{frame_analysis} Fig:Single Frame capture
Appendix A:File Description in Design directory
Graphics_application_debugging.zip is extracted as

Zynq UltraScale+ MPSoC Power Advantage Tool part 8 - Building and Running the Qt PC GUI Design from Sources

$
0
0
...
1.1 Build the Qt Design
The steps to rebuild the Qt GUI from sources are as follows:
DownloadFollow the Qt documentation steps to install and set up the latest version of Qt installer .exe here (there should be a VS2015 version) and wdexpress_full.exe from here(Visualfor Visual Studio Express 2015 for Windows Desktop). Note: Microsoft has recently changed to a web installer found at the bottom under "Visual Studio 2015 +", so the .exe name may be different now.
Install Qt. Note: Some firewalls may cause the installation to fail.
Install wdexpress_full.exe.
here.
C:\Qt\Tools\QtCreator\bin\qtcreator.exe (and pin to taskbar)
File > Open File or Project > C:\zynqus\pwr\qt\ZynqusPowerTool.pro > Yes (no .pro with user settings) > Configure project

Zynq UltraScale+ MPSoC Power Advantage Tool part 7 - Building and Running the MSP430 Design from Sources

$
0
0
...
1.1 Building the MSP430 Design
The steps to rebuild the MSP430 design from sources are as follows:
DownloadFollow the TI instructions to download and install the latest
...
(CCS) from http://processors.wiki.ti.com/index.php/CCS_for_LaunchPad (currently Code Composer Studio 6.1.1).here. And set it up for MSP Ultra Low Power MCUs. Note: If
...
installation issues.
ccs_setup_6.1.1.00022.exe > Select MSP Ultra Low Power MCUs

Install a full license or a 90-day trial license per TI instructions.
Code Composer Studio > Workspace: C:\zynqus\pwr\msp430 > OK

Zynq UltraScale+ MPSoC Power Advantage Tool part 9 - Building and Installing the Gimp Artwork from Sources

$
0
0
...
1.1 Rebuilding the Qt Artwork in Gimp
The steps to rebuild the Qt Artwork has been automated in Gimp. This saves the manual process of enabling and disabling source artwork layers, as well as manually resizing the layers:
InstallFollow the Gimp instructions to install and set up the latest
...
Gimp from https://www.gimp.org/downloads/ (currentlyhttps://www.gimp.org/downloads/.
Follow the
Gimp 2.8).
Copy automation script from C:\zynqus\pwr\gimp\export.py
instructions to C:\Users\<username>\.gimp-2.8\plug-ins\export.py. Note: .gimp-2.8 may be a hidden folder.install the Python Fu Script provided in C:\zynqus\pwr\gimp\export.py.
Gimp > File > Open > C:\zynqus\pwr\gimp\Layout.xcf
File > python-fu-export. The process can take 30 minutes.

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
$ cd <Gator_source>/driver
$bash
$ export <cross compilation path> CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-
$ GATOR_WITH_MALI_SUPPORT=MALI_4xx CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_install_directory>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directory>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/ make -C
Note: In the above command, it is mandatory to use the Petalinux project directory which is created in above section.
After the above steps gator.ko kernel module get created under the <Gator_source>/driver directory.

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
Summary:
Zynq® UltraScale+™ MPSoC delivers unprecedented levels of heterogeneous multi-processing and combines seven user programmable processors including Quad-coreARM® Cortex™-A53 Application Processing Unit (APU), Dual-core 32-bit ARM® Cortex™-R5 Real Time Processing Unit (RPU), and ARM® Mali™-400 MP2 Graphics Processing Unit (GPU). It is Industry’s First All Programmable Multi-Processor SoC delivering 5x system level performance-per-watt and any-to-any connectivity.
...
performance of a graphics application running on Zynq UltraSCale
...
MPSoC Mali GPUGPU, using ARM®
Implementation Details
Implementation Details
...
Description
ARM® DS-5 Development Studio Streamline performance analyzer enables you to get the best out of your system’s resources and create high performance, energy efficient products. Its innovative user interface brings together system performance metrics, software tracing, statistical profiling and power measurement to present you with a system dashboard where you can quickly identify code hotspots, system bottlenecks and other unintended effects of your code or the system architecture.
...
performance of Zynq UltraSCale + MPSoC Mali GPU with respect to a graphics
...
optimizing their application.itapplication.It is also
...
and demonstrates analyzinghow to analyze a simple
Highlights of this Tech tip:
Below are the main topics which are covered in this tech tip :
...
Class 10 SD card (4GB or more).
Micro USB to Standard USB cable
...
Monitor and DisplayPortDisplay Port Cable.
USB 3.0 connector or USB 2.0 micro cable to standard USB female adapter, USB Hub to connect USB mouse and USB keyboard or connect USB keyboard with mouse integrated etc.
Install any HyperTerminal like Tera term, putty, etc. for serial terminal prints. Download the Tera term application at http://download.cnet.com/Tera-Term/3000-20432_4-75766675.html and follow the instructions to install.
...
{Streamline_analyzer.PNG}
Executing the tech tip with prebuilt images :
...
from the sourcescratch then, skip
First of all install the performance analyzer tool by following the section "Installing ARM Streamline performance analyzer tool on windows machine " below.
Download the ARM_Streamline_performance_analyzer.zip file using link provided at the top of this tech tip and extract to your local directory.It will be extracted as Design_files directory.
...
After the above steps run the command shown below to configure the rootfs and save.
$petalinux-config -c rootfs
...
the file <Petalinux_project_directory>/build/linux/kernel/xlnx-4.4/.config<Petalinux_project_directory>/subsystem/linux/configs/kernel/config to enable
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
...
$ cd <Gator_source>/driver
$bash
$ export CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-
$ GATOR_WITH_MALI_SUPPORT=MALI_4xx CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directory>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/ make -C <petalinux_project_directory>/build/linux/kernel/xlnx-4.4/ M=`pwd` ARCH=arm64 modules
Note: In the above command, it is mandatory to use the Petalinux project directory which is created in above section.

Zynq UltraScale MPSoC Software Acceleration TRD 2016.2

$
0
0
...
For detailed information on complete feature set, hardware and software architecture of the design, please refer to the TRD user guide here.
Download the TRD
...
from here.< link will be updated soon>
TRD Directory structure and package contents
The Software acceleration TRD package is released with the source code, hardware platform through Xilinx Vivado, SDK projects, and an SD card image that enables the user to run the demonstration and software application. It also includes the binaries necessary to configure and boot the ZCU102 board. Prior to running the steps mentioned in this wiki page, user has to download the TRD package and extract its contents to a directory referred to as ‘TRD_HOME' which is the home directory.

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
First of all install the performance analyzer tool by following the section "Installing ARM Streamline performance analyzer tool on windows machine " below.
Download the ARM_Streamline_performance_analyzer.zip file using link provided at the top of this tech tip and extract to your local directory.It will be extracted as Design_files directory.
...
all files present under the
Do the board setup by following the "ZCU102 board setup" section below in this page.
Once board setup is done,follow the section "profiling an example graphics application " to execute the demo.
...
Install the Petalinux by running the above downloaded installer
$ . / petalinux-v2016.3-final-installer.run
Note: please refereRefere the Petalinux
...
guide at belowpresent at the link for petalinux installation http://www.xilinx.com/support/documentation/sw_manuals/petalinux2014_4/ug1144-petalinux-tools-reference-guide.pdf
After installation is done set the
for installing Petalinux environment by running below command in bash shellon Linux host machine.
$ source <Petalinux_installation_path>/settings.sh
After installation is done set the Petalinux environment by running below command in bash shell
Note: use source <Petalinux_installation_path>/settings.csh command for c shell.
Cross Check the PETALINUX environment variable is set to the above installation path
...
Replace the system.hdf located at Xilinx-ZCU102-2016.3/subsystems/linux/hw-description/ with the system.hdf file provided in release files and run the following command:
$ petalinux-config --oldconfig
...
the directory <Petalinux_project_directory>/subsystem/linux/configs/rootfs/config Note:Xilinx-ZCU102-2016.3/subsystem/linux/configs/rootfs/config
Note:
Find the
...
<Local_directory>/Desing_files/Rootfs_configuration/ directory.
After the above steps run

Run
the command
$petalinux-config -c rootfs
...
the file <Petalinux_project_directory>/subsystem/linux/configs/kernel/configXilinx-ZCU102-2016.3/subsystem/linux/configs/kernel/config to enable
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
...
CONFIG_MALI400_INTERNAL_PROFILING=y
CONFIG_MALI_SHARED_INTERRUPTS=y
Now configure and save the kernel by executing below command.
$ Petalinux-config –c kernel
Do the following device tree modifications.The device tree source files are at project location Xilinx-ZCU102-2016.3/subsystems/linux/configs/device-tree.
...
Once the above changes are done, build the petalinux project.
$ Petalinux-build
...
under the <Petalinux_project_directory>/images/linuxXilinx-ZCU102-2016.3images/linux
Create BOOT.bin
...
created under <Petalinux_project_directory>/images/linux directory.Xilinx-ZCU102-2016.3/images/linux //directory.
$ Petalinux-package --boot --fsbl <Petalinux_project_directory>/images/linux/zynqmp_fsbl.elfXilinx-ZCU102-2016.3/images/linux/zynqmp_fsbl.elf --u-boot <Petalinux_project_directory>/images/linux/u-boot.elfXilinx-ZCU102-2016.3/images/linux/u-boot.elf --fpga <Petalinux_project_directory>/images/linux/design_1_wrapper.bitXilinx-ZCU102-2016.3/images/linux/design_1_wrapper.bit
Copy the BOOT.BIN,image.ub files on to a SD card.
Compiling & building gator module and gator daemon:
...
Build the gator.ko module by following below commands
$ cd <Gator_source>/driver
$bash
$ export CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-
$ GATOR_WITH_MALI_SUPPORT=MALI_4xx CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directory>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directorY>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/ make -C <petalinux_project_directory>/build/linux/kernel/xlnx-4.4/Xilinx-ZCU102-2016.3//build/linux/kernel/xlnx-4.4/ M=`pwd` ARCH=arm64
Note: In the above command, it is mandatory to use the Petalinux project directory which is created in above section.
After the above steps gator.ko kernel module get created under the <Gator_source>/driver directory.

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
$bash
$ export CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-
$ GATOR_WITH_MALI_SUPPORT=MALI_4xx CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directorY>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/CONFIG_GATOR_MALI_4XXMP_PATH=<petalinux_installed_directory>/components/linux-kernel/xlnx-4.4/drivers/staging/mali/DX910-SW-99002-r5p1-01rel0/driver/src/devicedrv/mali/ make -C
Note: In the above command, it is mandatory to use the Petalinux project directory which is created in above section.
After the above steps gator.ko kernel module get created under the <Gator_source>/driver directory.

Programming the ZynqMP Programmable Logic

$
0
0

ZYNQMP FPGA Linux Driver for Zynq Ultrascale+ MPSoC
Introduction
The ZynqMp Programmable Logic (PL) can be programmed by the First Stage Boot Loader (FSBL), U-Boot or through Linux. Programming the PL at different stages may be advantageous for different projects and workflows.
Features provided
It support only full-bitstream loading.
It is capable of loading only .bin format files into PL.it will not support the other file formats.
Known Issues and Limitations
Not support Partial,Encrypted,Authenticated Bit-stream programming into the zynqmp PL.
It is capable of loading only .bin format files into PL.it will not support the other file formats.
Work to be done
Support for Encrypted and Authenticated Bit-stream programming into the zynqmp PL
Programming the PL through Linux
Kernel Configuration Options for Driver
Device Drivers ---> FPGA Configuration Support ---> <*> Xilinx Zynqmp FPGA
{http://confluence.xilinx.com/download/attachments/33992124/config.JPG?version=1&modificationDate=1472639729625&api=v2}
Devicetree
pcap {
compatible = "xlnx,zynqmp-pcap-fpga";
};

Task Dependencies (Pre-requisites)
Setup Xilinx tools and environment
...
U-Boot> fatload mmc 0 0x4000000 bitstream.bin
U-Boot> fpga load 0 0x4000000 <bitstream file size>
ProgrammingHow to create .bin from .bit file
command : bootgen -image boot_a53_bin_pl_all.bif -arch zynqmp -process_bitstream bin
boot_a53_bin_pl_all.bif file contains
the PL through Linux
Kernel Configuration Options for Driver
Device Drivers ---> FPGA Configuration Support ---> <*> Xilinx Zynqmp FPGA
{http://confluence.xilinx.com/download/attachments/33992124/config.JPG?version=1&modificationDate=1472639729625&api=v2}
Devicetree
pcap {
compatible = "xlnx,zynqmp-pcap-fpga";
};
below lines:
all:
{
design_1_wrapper.bit
}

User space commands
Once booted into Linux, write the bitstream file to the PL.

Programming the ZynqMP Programmable Logic

$
0
0
...
Change Log
2016.3
fpga manager:manager Adding FPGA
...
Xilinx zynqmp Soc
Mainline status
The current driver not availble in the open source driver

Related Links
https://github.com/Xilinx/linux-xlnx/blob/master/drivers/fpga/zynqmp-fpga.c

Programming the ZynqMP Programmable Logic

$
0
0

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
https://github.com/ARM-software/gator
change the directory to daemon directory under the Gator source and run the below command to build the gator daemon.
$bash
$ exportCROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-

cd <Gator_source>/daemon
$make -f Makefile_aarch64
...
$bash
$ export CROSS_COMPILE=<petalinux_installed_directory>/tools/linux-i386/aarch64-linux-gnu/bin/aarch64-linux-gnu-
...
make -C Xilinx-ZCU102-2016.3//build/linux/kernel/xlnx-4.4/Xilinx-ZCU102-2016.3/build/linux/kernel/xlnx-4.4/ M=`pwd` ARCH=arm64
...
project directory (Xilinx-ZCU102-2016.3) which is
After the above steps gator.ko kernel module get created under the <Gator_source>/driver directory.
Now copy the above built gatord and gator.ko files on to the SD card( The once which used above to copy the BOOT.bin,image.ub images).
...
$ insmod gator.ko
$ ./gatord &
Note: while running the gatord daemon, few unremarkable errors may come.Those are not functional effect.
Now Run the example eglfbdev_gears_application by following below commands.
$ export DISPLAY=:0.0

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0

Zynq UltraScale Plus MPSoC Graphics- GPU application debugging using ARM Mali Graphics Debugger tool

$
0
0

profiling.jpg

Zynq UltraScale Plus MPSoC Graphics- GPU Profiling using ARM Streamline performance analyzer

$
0
0
...
$ export DISPLAY=:0.0
$ ./tri_cube &
...
connected the board.board like as shown
Now open the ARM DS-5 Streamline performance analyzer tool and provide the target IP address in the box marked in the below shown figure
{ds_5_1.PNG} Fig:setting target IP address in Streamline tool
...
{ds_5_6.PNG} Fig:selecting start capture option
After clicking start capture option, it will asks for the location to save the captured data, browse the working directory and save the file for future analysis. Then you will start seeing the GPU performance metrics information in the Streamline performance analyzer like as show in the below figure
{ds_5_7.PNG} Fig:Profiling Graphics application {profiling.jpg} Fig: GPU performance metrics information
Appendix A:File Description in Design directory
ARM_Streamline_performance_analyzer.zip is extracted as

kernel_device_driver_fpga_manager.png

Programming the Programmable Logic (add programming PL for MPSoC)

$
0
0
...
U-Boot> fatload mmc 0 0x4000000 bitstream.bit
U-Boot> fpga loadb 0 0x4000000 <bitstream file size>
Programming theZYNQ PL through
Once booted into Linux, write the bitstream file to the devcfg device:
$ cat bitstream.bit > /dev/xdevcfg
...
$ cat /sys/class/xdevcfg/xdevcfg/device/prog_done
1
Programming ZYNQ UltraScale+ MPSoC PL through Linux
ZYNQ UltraScale+ MPSoC PL can be programmed by FPGA Manager in Linux after PetaLinux 2016.3, or xilinx-v2016.3 tag of linux-xlnx. The driver of FPGA Manager needs to be enabled in kernel config.
$ petalinux-config -c kernel #For PetaLinux
$ make menuconfig #For Open Source Linux
Enable the driver for FPGA Manager: Device Driver -> FPGA Configuration Support -> FPGA Configuration Framework and Xilinx Zynqmp FPGA. Note: Make sure the mark is "*" rather than "M" by pressing <Y>
{kernel_device_driver_fpga_manager.png}
Make sure FPGA Manager is initialized properly after Linux boot up.
$ dmesg | grep FPGA
[ 1.345894] FPGA manager framework
[ 4.627730] fpga_manager fpga0: Xilinx ZynqMp FPGA Manager
Copy bin format of the bitstream to /lib/firmware/ directory.
$ cp download.bit.bin /lib/firmware/
Give FPGA Manager the filename to configure PL.
$ echo download.bit.bin > /sys/class/fpga_manager/fpga0/firmware

Related Links
Getting Started
...
Partial Reconfiguration Documentation
Platform Specific Documentation
Zynq
dmesg | grep FPGA[ 1.345894] FPGA manager framework[ 4.627730] fpga_manager fpga0: Xilinx ZynqMp FPGA Manager

Programming the Programmable Logic (update font; change download.bit.bin to bitstream.bit.bin)

$
0
0
...
$ petalinux-config -c kernel #For PetaLinux
$ make menuconfig #For Open Source Linux
...
Zynqmp FPGA. Note:
Note:
Make sure
{kernel_device_driver_fpga_manager.png}
Make sure FPGA Manager is initialized properly after Linux boot up.
...
[ 4.627730] fpga_manager fpga0: Xilinx ZynqMp FPGA Manager
Copy bin format of the bitstream to /lib/firmware/ directory.
$ cp download.bit.binbitstream.bit.bin /lib/firmware/
Give FPGA Manager the filename to configure PL.
$ echo download.bit.binbitstream.bit.bin> /sys/class/fpga_manager/fpga0/firmware
Related Links
Getting Started
Viewing all 11776 articles
Browse latest View live


<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>