When you use neural analytics (see General information on neural analytics), the hardware requirements are the following:
- Take into account the limitations of NVIDIA SDK. The neural analytics can operate on the GPU only in the operating systems specified in the Operating system requirements page.
- VPU requirements (Intel NCS):
- Connect a device to the computer USB port.
- Make sure that the Windows system identifies a device as Movidius, Myriad X, or VSC Loopback Device.
- Use it on the computers that meet the Hardware requirements.
- Apply no more than one Intel NCS device on the server.
- Supported CPUs and requirements:
| CPU type | Supported generations/models | Key requirements and conditions |
|---|
| Intel® Core™ | 6th generation (Skylake) and higher | - Support for the AVX2 or AVX512 instruction set (see ark.intel.com)
- We don't guarantee the detector operation on CPUs lower than 6th generation
|
| Intel® Xeon® | Families v5 (Broadwell) and v6 (Skylake) | - Support for the AVX2 or AVX512 instruction set (see ark.intel.com).
- CPU compatibility with the OpenVINO toolkit version that you use (see software.intel.com)
|
| Intel VPU devices | Movidius™ Neural Compute Stick, Neural Compute Stick 2, Vision Accelerator Design with Intel® Movidius™ VPUs | Support from the OpenVINO toolkit version that you use (see software.intel.com) |
- Requirements for NVIDIA GPU:
| Parameter | Minimum/recommended requirements |
|---|
| GPU model | - NVIDIA GeForce GTX 1050 and later (for Detector Pack 3.14–3.15.1)
- NVIDIA GeForce GTX 1650 and later (for Detector Pack 3.15.2 and later)
|
| Video memory space | At least 2 GB. For the accurate calculation, we recommend using AxxonSoft Platform Calculator (see AxxonSoft Platform Calculator documentation) |
| CUDA version | - 11.1–11.8 (for Detector Pack 3.14–3.15.1)
- 12.8.1 (for Detector Pack 3.15.2 and later)
|
| Compute Capability | - 6.0–9.0 (for Detector Pack 3.14–3.15.1)
- 7.5–12.0 (for Detector Pack 3.15.2 and later)
You can check the version here or on the manufacturer's website |
| Supported architectures | - Kepler (late), Maxwell, Pascal, Volta, Turing, Ampere, Ada Lovelace (partially) (for Detector Pack 3.14–3.15.1)
- Turing, Ampere, Ada Lovelace (partially), Hopper, and Blackwell (for Detector Pack 3.15.2 and later)
- In Windows OS, starting with the Detector Pack 3.15.2 version, the support for Hopper and Blackwell is added for the following detectors:
|
| Drivers | We recommend installing the latest driver version from the official website |
| Configuration | You can use up to four GPUs on one server |
- For the correct operation, each detector must meet individual specific requirements (see Detectors) to:
- Hardware platform,
- Video stream and scene,
- Image characteristics.