Tesla P40 and Radeon Pro V320 - video card comparison
Tesla P40
Radeon Pro V320
Architecture
Pascal (2016−2021)
GCN 5.0 (2017−2020)
GPU code name
GP102
Vega 10
Market segment
Workstation
Workstation
Release date
September 2016
June 2017
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
8-pin EPS
2x 8-pin
Boost clock speed
1531 MHz
1500 MHz
Core clock speed
1303 MHz
852 MHz
Floating-point performance
11,758 gflops
-
Manufacturing process technology
16 nm
14 nm
Number of transistors
11,800 million
12,500 million
Pipelines / CUDA cores
3840
3584
Power consumption (TDP)
250 Watt
230 Watt
Texture fill rate
367.4
336.0
Memory type
GDDR5
HBM2
Maximum RAM amount
24 GB
8 GB
Memory bus width
384 Bit
2048 Bit
Memory clock speed
7.2 GB/s
1890 MBps
Memory bandwidth
347.1 GB/s
483.8 GB/s
Display Connectors
No outputs
4x mini-DisplayPort 1.4a
DirectX
12 (12_1)
12 (12_1)
CUDA
6.1
-
OpenCL
3.0
2.1
OpenGL
4.6
4.6
Shader Model
6.7
6.7
Vulkan
1.3
1.3