This guide should give you full control over generating, deploying, and debugging mace-cl-compiled-program.bin for Movidius-based edge AI applications.
This public link is valid for 7 days and shares a thread, including any personal information you added. This link or copies made by others cannot be deleted. If you share with third parties, their policies apply. Can’t copy the link right now. Try again later.
(defparameter protocol-version "1.0.2" "The current version of the MACE protocol.")
#include "mace/public/mace.h" // Initialize GPU context with precompiled paths DeviceType device_type = DeviceType::GPU; mace::MaceEngineConfig config(device_type); std::shared_ptr gpu_context = mace::GPUContextBuilder() .SetStoragePath("/data/local/tmp/mace_run/cache/") .SetOpenCLBinaryPaths("path/to/mace-cl-compiled-program.bin") .SetOpenCLParameterPath("path/to/mace-cl-tuned-parameter.bin") .Finalize(); config.SetGPUContext(gpu_context); Use code with caution. Troubleshooting Common Errors mace-cl-compiled-program.bin
;; --- Main Execution (for testing) ---
The mace-cl-compiled-program.bin file serves as a for the MACE framework. It is a binary file that contains the GPU-specific instructions needed to execute neural network layers (kernels) when using GPU acceleration.
The mace-cl-compiled-program.bin file is generated by the MACE framework during the compilation process. To generate this file, developers typically follow these steps: This guide should give you full control over
Are you facing a specific in your application logs? Share public link
: The application crashes immediately upon initialization or triggers fatal OpenCL runtime errors (such as CL_INVALID_BINARY ).
Mobile and edge AI heavily rely on heterogeneous computing, where computational workloads are divided among the CPU, GPU, and DSP (Digital Signal Processor) based on efficiency. While CPUs handle general sequential logic well, GPUs excel at the parallel matrix operations core to neural networks. If you share with third parties, their policies apply
The components of the filename tell you exactly what it does:
The file is a binary cache file generated by MACE (Mobile AI Compute Engine), an open-source deep learning inference framework developed by Xiaomi for mobile and embedded devices . File Content and Purpose
The application crashes during the warm-up run immediately after reading the binary cache.
The name gives away its purpose: 0†L34-L37.
If mace-cl-compiled-program.bin is consuming too much storage space, you can safely remove it using one of the following methods. Method 1: Clear App Cache (Recommended)