NVIDIA A100X

The NVIDIA A100X is an end-of-life workstation graphics card that released in Q2 2021. It is built on the Ampere GPU microarchitecture (codename GA100) and is manufactured on a 7 nm process.

Memory

The A100X has 80 GB of HBM2e memory, with a 1,593 MHz memory clock and a 5,120 bit interface. This gives it a memory bandwidth of 2.04 Tb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.

Cores and Clock Speeds

The A100X includes 6,912 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 795 MHz and can dynamically boost its clock speed up to 1,440 MHz. Complementing the processing units are 432 texture mapping units (TMUs) for efficient texture filtering and 160 render output units (ROPs) for pixel processing. Additionally, the GPU features 432 tensor cores optimized for AI-accelerated workloads.

Compatibility & Power Consumption

The A100X occupies 2 PCIe expansion slots. NVIDIA recommends a power supply of at least 700 W to handle the GPU's thermal design power (TDP) of 300 W.