Agilex 7 M series Open FPGA Stack support
Hello, We are using Agilex 7 M series FPGA and considering to evaluate Open FPGA Stack (OFS) at some point. Currently the latest OFS release (2025.1) contains only pre-release level support for Agilex 7 M reference shell design and lacks support for many key features (https://github.com/OFS/ofs-agx7-pcie-attach/releases/tag/ofs-2025.1-1). Could we expect to get an official release level support some time in the near future? Best regards Otto5Views0likes0CommentsEltwise_mult with broadcasting on FPGA
Hi, I am using FPGA AI suite 2025.1 & OpenVINO 2024.6.0 with DE10-Agilex dev kit. In ".arch" files provided , such as AGX7_Performance.arch, I see "enable_eltwise_mult : true". But it seems not supporting broadcasting. What I want is to perform an element-wise multiplication between two tensors of shapes [1, 1, H, W] and [1, C, H, W], resulting in an output of shape [1, C, H, W], and have this operation executed on the FPGA. I'm wondering if there's a way to do this, or if I'm missing something. I'd appreciate any help Bests.Solved2.5KViews0likes7CommentsUnderstanding FPGA AI Suite with Quartus
Hi, I am new to the FPGA AI Suite and would appreciate your help in better understanding it. Referring to the attached Intel pipeline, specifically the path involving Quartus: When Quartus is involved, is the OpenVINO runtime inference engine still required to run the application? I assume that IP files are imported into Quartus. Do these files contain the model topology and weights needed to run the application, or is Quartus solely used to configure the FPGA hardware, with the inference handled by the OpenVINO runtime (via FPGA AI Suite)? If I test the model using a deep learning framework and then use the FPGA AI Suite, how can I effectively collaborate with the FPGA developer? I hope my questions are clear. Best regards.Solved2.2KViews0likes1CommentIntel FPGA AI Sutie Inference Engine
Is there any official documentation on the DLA runtime or inference engine for managing the DLA from the ARM side? I need to develop a custom application for running inference, but so far, I’ve only found the dla_benchmark (main.cpp) and streaming_inference_app.cpp example files. There should be some documentation covering the SDK. The only documentation that i found related with is the Intel FPGA AI suite PCIe based design example https://www.intel.com/content/www/us/en/docs/programmable/768977/2024-3/fpga-runtime-plugin.html From what I understand, the general inference workflow involves the following steps: Identify the hardware architecture Deploy the model Prepare the input data Send inference requests to the DLA Retrieve the output data6.6KViews0likes42CommentsOFS : Data Path of QSFP from HE_HSSI
Hi Team, I am using N6001 with Intel OFS (OFS PCIe Attach) . I wanted to test data transfer from Host1 to Host2 as below. Host1 -> N6001(Port0) -> OtherNIC(Port0) -> Host2. Is there any sample application available in OPAE/OFS which performs this transaction? Can you please suggest. In addition to above query, I wants to know how HE-HSSI sends data to QSFP?. The hssi application shows "No eth interface, so not honoring --eth-loopback". ( https://ofs.github.io/ofs-2024.1-1/hw/n6001/user_guides/ug_qs_ofs_n6001/ug_qs_ofs_n6001/ Section 7. Send traffic through the 10G AFU). Does this mean the HE_HSSI will not communicate with E-Tile or QSFPs (FIM) ? Do I need to enable any parameters to pass over QSFPs? Thankyou.5.6KViews1like44CommentsIssue with Compiling OFS Agilex PCIe Attach on F-Series Development Kit
Hello Team, I am looking to compile the OFS Agilex PCIe Attach on the F-series development kit. I was following the compilation flow using the link below: https://ofs.github.io/ofs-2023.3/hw/ftile_devkit/dev_guides/fim_dev/ug_ofs_ftile_dk_fim_dev/#1311-walkthrough-install-quartus-prime-pro-software After exporting with the respective Quartus and build root, I am facing an issue where the terminal hangs. and the compilation doesn't go any further for hours. I have compiled this on both Red Hat Enterprise Linux 8.6 and Ubuntu 22.04 having same observation. I am using a system with an Intel i7-14700 and 64GB of RAM, so system performance shouldn't be an issue. I have also attached logs for your reference. Kindly provide a solution or let me know if any changes need to be made. Thanks & Regards, Raizz4.6KViews0likes18CommentsHow to Reconfigure and make changes in Quartus for a built and compiled OFS FIM.
Hello, I have built and compiled the N6001 design from otchsare beta 3.2 SKU2 version using Quartus 23.1. It seems that within the FIM developer documents the steps to reconfigure and change the design are given all via the terminal and using Quartus commands. I was wondering if I can do design changes and other stuff within Quartus and give compilation from within quartus after building the design once. So when I tried compiling the same design without any changes from within Quartus, there were multiple tcl files which were throwing errors. -------------------------------------------------------------------------------------------------- Tcl error: can't find package options while executing "package require options" (file "ofs_partial_reconfig/user_clock_freqs_compute.tcl" line 24) invoked from within "source ofs_partial_reconfig/user_clock_freqs_compute.tcl" (file "ofs_partial_reconfig/ofs_sta_report_script_pr.tcl" line 12) invoked from within "source ofs_partial_reconfig/ofs_sta_report_script_pr.tcl" ("uplevel" body line 1) invoked from within "uplevel source $script" invoked from within "if [file exists $script] { set start_time [clock clicks -millisec] uplevel source $script set end_time [clock clicks -millisec]..." ("foreach" body line 2) invoked from within "foreach script $options(report_script) { if [file exists $script] { set start_time [clock clicks -millisec] uplevel source $scri..." invoked from within "if [is_project_open] { # The all_corners option can be set by INI as well. set all_corners_ini [get_ini_var -name "qsta_all_corners"] if {[stri..." (procedure "main" line 140) invoked from within "main" (file "t:/intelfpga_pro/23.1/quartus/common/tcl/internal/qsta_default_script.tcl" line 1610) ------------------------------------------------------------------------------------------------------- So I went through the document again and found out about Relocatable PR Directory. And I thought this is used to create a project which can be used to compile within quartus. So I tried running this and got it to work successfully, but I think I must've misunderstood what this means since it doesn't generate a Complete Quartus project file with every file present within the Quartus Project, but generates some files and binaries. What exactly is this feature used for? Is there any way after building the Quartus project in the Linux environment, after which I can copy the project file and then continue designing in a Windows environment without having to run scripts and just use Quartus to do everything?1.8KViews0likes6CommentsIntel N6001 FIM not compiling due to script failing
Hey @khtan, I am done testing the N6000 card, and wanted to test the N6001 design in the N6000 card without enabling the E810 Controller. Hence I started building and compiling the N6001 design, but the script fails. Traceback (most recent call last): File "/usr/bin/afu_json_mgr", line 5, in <module> from packager.tools.afu_json_mgr import main File "/usr/lib/python3/dist-packages/packager/tools/afu_json_mgr.py", line 35, in <module> from packager.utils.afu import AFU File "/usr/lib/python3/dist-packages/packager/utils/afu.py", line 37, in <module> from jsonschema import validators ModuleNotFoundError: No module named 'jsonschema' Error: "afu_json_mgr json-info --afu-json=/home/admin/test/intel-ofs-fim/ofs-common/scripts/common/syn/pim/dummy_afu/dummy_afu.json --verilog-hdr=../hw/afu_json_info.vh" failed Copying build from /home/admin/test/intel-ofs-fim/work_n6001/syn/syn_top/afu_with_pim/pim_template/hw/lib/build... Configuring Quartus build directory: afu/build Error running /home/admin/test/intel-ofs-fim/ofs-common/scripts/common/syn/build_fim.sh Exit code: 1 Below is the attached log file, any ideas as to what can be done are deeply appreciated. Thank you, Best Regards.Solved11KViews1like13CommentsopenFPGA Stack Requires Xeon?
Hello, In all the openFPGA stack documentation that I can find, only Intel Xeon Scalable processors are mentioned. I am wondering if this is a hard requirement, or if smaller processors can be used. I would be most interested in using the stack with the latest Core or Atom processors. Additionally, is it feasible to develop our own FIM for an Arria 10 FPGA, or Agilex 5E? I see that Stratix 10 is supported which may be largely compatible with Arria 10, and Agilex 7 may be largely compatible with 5E? I understand that development is needed; I would just like to know if it's reasonable to use lower-tier hardware for OFS as opposed to a server environment. ThanksSolved705Views0likes1Comment