GPU Wiki

Compare GPUs

Pick up to four GPUs and compare their specs row by row. Specs that mean different things across generations are kept apart.

Popular comparisons

Add a third or fourth GPU
Spec Tesla PG503-216
Overview
Product name NVIDIA Tesla PG503-216
Architecture Volta
Generation / family Tesla P Series
GPU codename GV100
Launch date 2019-11-26
Market segment Data Center in Tesla P Series
Board type / entry type Data Center GPU
GPU
Process node TSMC 12 nm
Die size 815 mm²
Transistor count 21.1 billion
GPU chip GV100
SM / multiprocessor count 80
CUDA Cores 4608
Tensor Cores 640
ROPs 128
TMUs 288
Clocks
Base / Core clock 1,312 MHz
Boost clock 1,530 MHz
Memory clock 1,106 MHz
Memory
Memory size 32 GB
Memory type HBM2
Memory bus width 4,096-bit
Memory bandwidth 1,130 GB/s
Bus / Interface
Bus interface PCIe 3.0 x16
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 250 W
Recommended PSU 600 W
Power connectors None
Slot width Dual-slot
Features
DirectX support DirectX 12.1
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.4
CUDA support 7.0
Shader Model 6.8
Performance / Benchmarks
FP32 throughput 14.1 TFLOPS
FP16 throughput 28.2 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

DLAA counts as native resolution; DLSS, FSR and XeSS upscaling never do. A ray tracing setting without a readable on or off value is read as on.