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 S870
Overview
Product name NVIDIA Tesla S870
Architecture Tesla
Generation / family Tesla
GPU codename G80
Launch date 2007-05-02
Market segment Data Center in Tesla
Board type / entry type Data Center GPU
GPU
Process node TSMC 90 nm
Die size 484 mm²
Transistor count 0.68 billion
GPU chip G80
SM / multiprocessor count 16
CUDA Cores 128
ROPs 24
TMUs 32
Clocks
Base / Core clock 600 MHz
Boost clock 600 MHz
Memory clock 800 MHz
Memory
Memory size 1.5 GB
Memory type GDDR3
Memory bus width 384-bit
Memory bandwidth 76.8 GB/s
Bus / Interface
Bus interface PCIe 1.0 x16
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 800 W
Recommended PSU 1,200 W
Slot width Dual-slot
Features
DirectX support DirectX 10.0
OpenGL support OpenGL 3.3
CUDA support 1.0
Shader Model 4.0
Performance / Benchmarks
FP32 throughput 0.35 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.