Q0E21A - Refurbished - HPE NVIDIA Tesla P100 PCIe 16GB Computational Accelerator, GPU

Condition: Refurbished

Requires 8P Keyed Cable Kit (871829-B21). Need just the cable? The 869820-001 cable from that kit is available separately for $49.

HPE NVIDIA Tesla P100 PCIe 16GB Computational Accelerator (Part Number: Q0E21A) is a high-performance GPU designed for data center applications such as high-performance computing (HPC), deep learning, and scientific simulations. It leverages NVIDIA's Pascal architecture and High Bandwidth Memory (HBM2) to deliver exceptional computational capabilities.

Specifications

• GPU Architecture: NVIDIA Pascal (GP100)

• CUDA Cores: 3,584

• Base Clock: 1,189 MHz

• Boost Clock: 1,328 MHz

• Memory: 16 GB HBM2

• Memory Interface: 4,096-bit

• Memory Bandwidth: Up to 732 GB/s

• Interface: PCI Express 3.0 x16

• Form Factor: Dual-slot, full-height (267 mm x 112 mm x 38 mm)

• Cooling: Passive (requires adequate system airflow)

• Power Consumption: 250W (1x 8-pin PCIe power connector)

• ECC Support: Yes (enabled by default)

• Display Outputs: None

Performance Highlights

• FP64 (Double Precision): 4.7 TFLOPS

• FP32 (Single Precision): 9.3 TFLOPS

• FP16 (Half Precision): 18.7 TFLOPS

Compatibility & Deployment

The Tesla P100 is compatible with systems that have a PCIe 3.0 x16 slot and sufficient airflow for passive cooling. It has been used in various server models, including:

• HPE Apollo pc40

• HPE ProLiant XL270d Gen9

Due to its passive cooling design, it's essential to ensure that the host system provides adequate airflow to maintain optimal operating temperatures.