Radeon Pro Vega 64 and Tesla P10 - video card comparison
Radeon Pro Vega 64
Tesla P10
Architecture
GCN 5.0 (2017−2020)
Pascal (2016−2021)
GPU code name
Vega 10
GP102
Market segment
Workstation
Workstation
Release date
June 2017
September 2016
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
None
1x 8-pin
Boost clock speed
1350 MHz
1493 MHz
Core clock speed
1250 MHz
-
Floating-point performance
11,059 gflops
-
Manufacturing process technology
14 nm
16 nm
Number of transistors
12,500 million
11,800 million
Pipelines / CUDA cores
4096
3840
Power consumption (TDP)
250 Watt
250 Watt
Texture fill rate
345.6
358.3
Memory type
HBM2
GDDR5X
Maximum RAM amount
16 GB
24 GB
Memory bus width
2048 Bit
384 Bit
Memory clock speed
1572 MHz
14.5 GB/s
Memory bandwidth
402.4 GB/s
694.3 GB/s
Display Connectors
No outputs
No outputs
DirectX
12 (12_1)
12 (12_1)
CUDA
-
6.1
OpenCL
2.0
1.2
OpenGL
4.6
4.6
Shader Model
6.4
6.4
Vulkan
1.1.125
1.2