GPU Wiki

Compare GPUs

Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.

Popular comparisons

Add a third or fourth GPU
Spec Tesla P40
Overview
Product name NVIDIA Tesla P40
Architecture Pascal
Generation / family Tesla P Series
GPU codename GP102
Launch date 2016-09-12
Market segment Data Center in Tesla P Series
Board type / entry type Data Center GPU
GPU
Process node TSMC 16 nm
Die size 471 mm²
Transistor count 11.8 billion
GPU chip GP102
SM / multiprocessor count 30
CUDA Cores 3840
ROPs 96
TMUs 240
Clocks
Base / Core clock 1,303 MHz
Boost clock 1,531 MHz
Memory clock 1,808 MHz
Memory
Memory size 24 GB
Memory type GDDR5
Memory bus width 384-bit
Memory bandwidth 347.1 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 8-pin EPS
Slot width Dual-slot, 267 mm length
Features
DirectX support DirectX 12.1
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.4
CUDA support 6.1
Shader Model 6.8
Performance / Benchmarks
FP32 throughput 11.76 TFLOPS
FP16 throughput 0.18 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.