NVIDIA Tesla T10

The NVIDIA Tesla T10 is a workstation graphics card that launched in 2020. It is built on the Turing GPU microarchitecture (codename TU102) and is manufactured on a 12 nm process.

Memory

The Tesla T10 has 16 GB of GDDR6 memory, with a 1,575 MHz memory clock and a 256 bit interface. This gives it a memory bandwidth of 403.2 Gb/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 Tesla T10 includes 3,072 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,065 MHz and can dynamically boost its clock speed up to 1,395 MHz. Complementing the processing units are 192 texture mapping units (TMUs) for efficient texture filtering and 96 render output units (ROPs) for pixel processing. Additionally, the GPU features 384 tensor cores optimized for AI-accelerated workloads and 48 RT cores dedicated to real-time ray tracing calculations.

Compatibility & Power Consumption

The Tesla T10 is a compact, low-profile graphics card that fits into 1 PCIe expansion slot. NVIDIA recommends a power supply of at least 450 W to handle the GPU's thermal design power (TDP) of 150 W.