Skip to main content

Table 1 Present GPU specs

From: Accelerating CFD simulation with high order finite difference method on curvilinear coordinates for modern GPU clusters

GPU Models

RTX 2080 Ti

Tesla P100

Titan V

CUDA Cores

4352

3584

5120

SM count

68

56

80

Based Clock (MHz)

1350

1190

1200

Total Memory

11 GB GDDR6

16 GB HBM2

12 GB HBM2

Memory Bandwidth (GB/sec)

616

732.2

652.8

FP32 Performance (TFlops)

13.45

9.3

14.90

FP64 Performance (TFlops)

0.42

4.7

7.45

Computation Capability

7.5

6.0

7.0

Architecture

Turing

Pascal

Volta

  1. Titan V has the highest double precision operation performance. RTX 2080 Ti utilizes the newest architecture and provides the highest single precision operation performance