NVIDIA GeForce RTX 3070 Ti vs NVIDIA P102-100

What is the difference between NVIDIA GeForce RTX 3070 Ti and NVIDIA P102-100. Find out which graphics card has better performance.

Graphics Processor (GPU)

GA104GPU NameGP102
GA104-400-A1Model numberGP102-100-A1
AmpereArchitecturePascal
SamsungFoundryTSMC
8 nmProcess Size16 nm
17,400 millionTransistors11,800 million
392 mm²Die Size471 mm²

Graphics Card

May 31st, 2021Release DateFeb 12th, 2018
GeForce 30FamilyMining GPUs
ActiveProductionActive
PCIe 4.0 x16Bus InterfacePCIe 3.0 x4

Memory

8 GBMemory Size5 GB
GDDR6XMemory TypeGDDR5X
256 bitMemory Bus320 bit
608.3 GB/sBandwidth440.3 GB/s

Performance

169.9 GPixel/sPixel fillrate134.6 GPixel/s
339.8 GTexel/sTexture fillrate336.6 GTexel/s
21.75 TFLOPS (1:1)FP16 (half) performance168.3 GFLOPS (1:64)
21.75 TFLOPSFP32 (float) performance10.77 TFLOPS
339.8 GFLOPS (1:64)FP64 (double) performance336.6 GFLOPS (1:32)

Clock Speeds

1575 MHzBase Clock1582 MHz
1770 MHzBoost Clock1683 MHz
1188 MHz
19 Gbps effective
Memory Clock1376 MHz
11 Gbps effective

Render Config

6144Shading Units3200
192TMUs200
96ROPs80
128 KB (per SM)L1 Cache48 KB (per SM)
4 MBL2 Cache2.5 MB
48SM Count25

Board Design

Dual-slotSlot WidthDual-slot
267 mm
10.5 inches
Length267 mm
10.5 inches
290 WThermal design power (TDP)250 W
600 WSuggested PSU600 W
1x HDMI
3x DisplayPort
Display ConnectorsNo outputs
1x 12-pinPower Connectors2x 8-pin
PG143 SKU 15Board NumberPG611 SKU 100

API support

12 Ultimate (12_2)DirectX12 (12_1)
4.6OpenGL4.6
3.0OpenCL3.0
1.2Vulkan1.2
6.6Shader Model6.4
8.6CUDA6.1