{"id":13830885,"url":"https://github.com/pulp-platform/pulp-sdk","last_synced_at":"2026-02-07T23:36:16.164Z","repository":{"id":29306979,"uuid":"120611597","full_name":"pulp-platform/pulp-sdk","owner":"pulp-platform","description":null,"archived":false,"fork":false,"pushed_at":"2025-11-12T20:48:44.000Z","size":12288,"stargazers_count":120,"open_issues_count":27,"forks_count":83,"subscribers_count":17,"default_branch":"main","last_synced_at":"2025-11-12T22:22:19.773Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pulp-platform.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2018-02-07T12:22:18.000Z","updated_at":"2025-11-12T20:48:45.000Z","dependencies_parsed_at":"2024-01-13T16:20:36.104Z","dependency_job_id":"95517916-f377-47ea-8da6-1497fec60197","html_url":"https://github.com/pulp-platform/pulp-sdk","commit_stats":null,"previous_names":[],"tags_count":106,"template":false,"template_full_name":null,"purl":"pkg:github/pulp-platform/pulp-sdk","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulp-platform%2Fpulp-sdk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulp-platform%2Fpulp-sdk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulp-platform%2Fpulp-sdk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulp-platform%2Fpulp-sdk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pulp-platform","download_url":"https://codeload.github.com/pulp-platform/pulp-sdk/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulp-platform%2Fpulp-sdk/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29212754,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-07T23:36:15.537Z","status":"ssl_error","status_checked_at":"2026-02-07T23:36:12.879Z","response_time":63,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-04T10:01:11.455Z","updated_at":"2026-02-07T23:36:16.144Z","avatar_url":"https://github.com/pulp-platform.png","language":"C","funding_links":[],"categories":["C"],"sub_categories":[],"readme":"# PULP-SDK\n\nThis is the latest version of the PULP SDK, which is under active development. The previous (now legacy) version, which is no longer supported, is on the [`v1` branch](https://github.com/pulp-platform/pulp-sdk/tree/v1).\n\n## Citing\n\nIf you intend to use or reference GVSoC for an academic publication, please consider citing it:\n\n```\n@INPROCEEDINGS{9643828,\n\tauthor={Bruschi, Nazareno and Haugou, Germain and Tagliavini, Giuseppe and Conti, Francesco and Benini, Luca and Rossi, Davide},\n\tbooktitle={2021 IEEE 39th International Conference on Computer Design (ICCD)},\n\ttitle={GVSoC: A Highly Configurable, Fast and Accurate Full-Platform Simulator for RISC-V based IoT Processors},\n\tyear={2021},\n\tvolume={},\n\tnumber={},\n\tpages={409-416},\n\tdoi={10.1109/ICCD53106.2021.00071}}\n```\n\nPULP-SDK completely supports Dory as QNNs deployment tool. You can find an example of deployment [\\[here\\]](#cnns-at-the-edge). If you intend to use or reference Dory for an academic publication, please consider citing it:\n\n```\n@ARTICLE{9381618,\n\tauthor={Burrello, Alessio and Garofalo, Angelo and Bruschi, Nazareno and Tagliavini, Giuseppe and Rossi, Davide and Conti, Francesco},\n\tjournal={IEEE Transactions on Computers},\n\ttitle={DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs},\n\tyear={2021},\n\tvolume={70},\n\tnumber={8},\n\tpages={1253-1268},\n\tdoi={10.1109/TC.2021.3066883}}\n```\n\n## Getting started\n\nThese instructions were developed using a fresh Ubuntu 18.04 Bionic Beaver 64-Bit.\n\nThe following packages needed to be installed:\n\n~~~~~shell\nsudo apt-get install -y build-essential git libftdi-dev libftdi1 doxygen python3-pip libsdl2-dev curl cmake libusb-1.0-0-dev scons gtkwave libsndfile1-dev rsync autoconf automake texinfo libtool pkg-config libsdl2-ttf-dev\n~~~~~\n\nThe SDK also requires the `argcomplete` and `pyelftools` Python package. You can install them for the local user with:\n~~~~~shell\npip install --user argcomplete pyelftools\n~~~~~\nOmit `--user` to install at system level instead, which will probably require admin rights.\n\nThis version requires PULP toolchain to compile the application exploiting pulp features. PULP toolchain is available at: https://github.com/pulp-platform/pulp-riscv-gnu-toolchain\n\nYou can choose also its precompiled version, exploring: https://github.com/pulp-platform/pulp-riscv-gnu-toolchain/releases/tag/v1.0.16\n\nPlease, refer to the corresponding README for the installation.\n\nOnce PULP toolchain is correctly installed, define the path in which there is toolchain bin folder:\n\n~~~~~shell\nexport PULP_RISCV_GCC_TOOLCHAIN=\u003cINSTALL_DIR\u003e\n~~~~~\n\nSource the file corresponding to the desired configuration:\n\n~~~~~shell\ncd pulp-sdk\nsource configs/pulp-open.sh\n~~~~~\n\nAt least gcc 4.9.1 is needed. If the default one is not correct, CC and CXX can be set to\npoint to a correct one. To check if gcc has the right version:\n\n~~~~~shell\ngcc --version\n~~~~~\n\nPlease, refer to official guide to update gcc if is needed.\n\n## GVSoC\n\nGVSoC is the PULP chips simulator that is natively included in the SDK and is described and evaluated fully in Bruschi et al. [\\[arXiv:2201.08166v1\\]](https://arxiv.org/abs/2201.08166).\n\nCompile GVSoC with this command:\n\n~~~~~shell\nmake build\n~~~~~\n\n## Test execution\n\nSome examples are availaible at https://github.com/GreenWaves-Technologies/pmsis_tests\n\nThen, go to a test, for example pmsis_tests/quick/cluster/fork/, and execute:\n\n~~~~~shell\nmake clean all run\n~~~~~\n\nThis will by default execute it on GVSoC (platform=gvsoc), and you can configure the RTL platform with this command:\n\n~~~~~shell\nmake clean all run platform=rtl\n~~~~~\n\nNotice that the environment variable `VSIM_PATH` should be set to the directory where the RTL platform has been built.\nThis is typically done by sourcing the `setup/vsim.sh` file from the main folder of the RTL platform.\n\n\u003ca name='cnns-at-the-edge'\u003e\n## Application: CNNs at the Edge\n\u003c/a\u003e\n\nTo run pre-generated real-world networks, such as MobileNetV1:\n\n~~~~~shell\ncd applications/MobileNetV1\nmake clean all run platform=\u003cPLATFORM\u003e CORE=\u003cNUM_CORES\u003e\n~~~~~\n\n### Nemo + Dory + Pulp-NN\n\nOur vertical flow allows to deploy optimized QNNs on low-power and low-resources MCUs, starting from a Pytorch model.\n\n#### Nemo\n\n[\\[Nemo\\]](https://github.com/pulp-platform/nemo) is a framework for Deep Neural Networks layer-wise quantization.\nHe starts from a common Pytorch project and produces an equivalent quantized model, which well suits the usually integer MCUs.\nIts output are a `.onnx` as quantized model and several `.txt` as set of input and weigths of the network, also including the golden activations to checks the output of every network's layer.\nPlease refer to its README for more details and [\\[here\\]](https://colab.research.google.com/drive/1qdc__9uZAGk9TzylsH3S8tB73bWcA2cA?usp=sharing#scrollTo=xelcF1jxkAit) you can find a Colab project and a very detailed tutorial on how to get started with Nemo.\n\n#### Dory\n\n[\\[Dory\\]](https://github.com/pulp-platform/dory) is an automatic tool to generate and directly deploy MLP/CNNs on PULP family boards, exploiting [\\[Pulp-NN\\]](https://github.com/pulp-platform/pulp-nn) as optimized back-end.\n\nDory has a complete and autonomous testsuite, named [\\[Dory-Example\\]](https://github.com/pulp-platform/dory_examples), which is periodically updated, and please refer to its README for more details.\nTo generate the code and run one of these examples:\n\n~~~~~shell\ncd dory/dory_examples/\npython3 network_generate --network_dir \u003ce.g., ./examples/MobileNetV1/\u003e\ncd application\nmake clean all run platform=\u003cPLATFORM\u003e CORE=\u003cNUM_CORES\u003e\n~~~~~\n\nwhere you should choose `CORE=8` if you want to test the network on pulp cluster with all of the eight cores active (by default only 1 is set).\n\nTo set up and execute a custom application, firstly, copy your file `network.onnx` and files `out_layer{i}.txt` in a single folder (e.g., `pulp-sdk/application/MyCustomNetwork/`) and then:\n\n~~~~~shell\ncd dory/dory_examples/\npython3 network_generate --network_dir \u003cpulp-sdk/application/MyCustomNetwork/\u003e\ncd application\nmake clean all run platform=\u003cPLATFORM\u003e CORE=\u003cNUM_CORES\u003e\n~~~~~\n\nYou can use L1 and L2 memory constraints to specify the amount of memory used inside the application. Please refer to Dory and Dory-example READMEs for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpulp-platform%2Fpulp-sdk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpulp-platform%2Fpulp-sdk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpulp-platform%2Fpulp-sdk/lists"}