Rugged Embedded Cpmouter AI 275 TOPs NVIDIA Jetson AGX Orin Module 900-13701-0050-000
NVIDIA Jetson AGX Orin Module 64GB 900-13701-0050-000
The NVIDIA Jetson AGX Orin module 900-13701-0050-000 is up to 275TOPs (INT8) of AI performance,and 64GB 256-bit LPDDR5 DRAM,two graphics processing cluster (GPC) ,eight texture processing clusters (TPC) ,2048 NVIDIA® CUDA® cores ,64 Tensor cores Ray-Tracing cores,170 Sparse TOPS,Maximum Operating Frequency: 1.3 GHz,Ampere GPU two GPC, eight TPC,Up to 170 INT8 Sparse TOPS or 85 Sparse FP16 TFLOPS (Tensor Cores) ,Up to 5.32 FP32 TFLOPS or 10.649 FP16 TFLOPS (CUDA cores),Up to 105 INT8 TOPS (Sparse, Deep Learning Inference),Storage and peripheral interfaces are subject to pin-muxing. Not all interfaces are available in the same system design or available simultaneously. Simultaneous support of various functions depends on the application use case and is subject to availability of memory bandwidth.
NVIDIA Jetson AGX Orin industrial Module 900-13701-0080-000 Technical Specifications
PN | 900-13701-0050-000 |
AI Perf | 275 TOPs |
GPU | Ampere GPU two GPC | eight TPC | Up to 170 INT8 Sparse TOPS or 85 Sparse FP16 TFLOPS (Tensor Cores) | Up to 5.32 FP32 TFLOPS or 10.649 FP16 TFLOPS (CUDA cores) |
CPU | Arm® v8.2 (64-bit) | 12x (up to 6× lock step) Arm Cortex-A78AE cores | three CPU clusters (four cores/cluster) | 259 SPECint_rate2006 |
Memory | 64 GB LPDDR5 |
Storage | 64 GB eMMC 5.1 |
Video Encode | 2x: 4K60 (H.265) |
Video Decode | 3x: 4K60 (H.265) / 1x: 8K30 (H.265) |
Ethernet (See Note) | 1x GbE RGMII |
Other | UART, SPI, CAN, I2C, I2S, GPIOs |
Memory Subsystem | |
Memory Type | 256-bit LPDDR5 |
Maximum Memory Bus Bandwidth (up to) | 204.8 GB/s |
Maximum Capacity | 64 GB |
Memory encryption support | 2-stage CPU MMU and SMMU, GPU MMU | Lossless memory bandwidth compression for GPU R/W |