The file serves one of three primary roles depending on the exact SoC generation:
The internal format is not officially documented but typically contains:
| Offset | Size (bytes) | Description |
|--------|--------------|-------------|
| 0x00 | 4 | Magic number (MACE or MCLP) |
| 0x04 | 4 | Version (e.g., 0x00010000) |
| 0x08 | 4 | Number of kernels |
| 0x0C | 4 | Total binary size |
| 0x10 | 4 | Offset to kernel table |
| ... | ... | Vendor-specific headers (Movidius blob) |
| ... | ... | Compiled ELF-like sections (VPU instructions) |
| End | ... | Possibly signature/hash |
Note: Most of the file is an opaque blob consumed directly by the Myriad X firmware. mace-cl-compiled-program.bin
output = runtime.run(input_data="input": input_array)
mace-cl-compiled-program.bin is not malware. It is not spyware. It is evidence of smart engineering.
By caching compiled OpenCL binaries, Xiaomi’s MACE framework turns a computationally expensive JIT compilation step into a near-instant load operation. For the average user, this means their camera filters apply instantly, their photo editor runs smoothly, and their AI keyboard predicts the next word without stuttering. The file serves one of three primary roles
For the developer, it represents a trade-off between storage space and latency. For the forensic analyst, it is a breadcrumb revealing which neural networks were run on a device.
Bottom line: Do not delete it unless you have to. And if you do—do not worry. The app will simply rebuild it, and you will suffer exactly one slow launch before the magic of the binary cache restores your performance.
If the app crashes while writing the binary, the file may be truncated or corrupt. This causes a load failure. Note: Most of the file is an opaque
The Fix: Delete the file manually. Navigate to Settings > Apps > [Your App] > Storage > Clear Cache. On the next launch, the file will be regenerated.
The file is produced by the MACE compiler toolchain from:
So, mace-cl-compiled-program.bin is a pre-compiled OpenCL kernel binary that was generated by the MACE framework for a specific hardware GPU (e.g., an Adreno GPU in a Snapdragon chip, or a Mali GPU).