NVIDIA Tesla V100 PCIe 32 GB vs AMD Radeon RX Vega 64 Liquid

Comparative analysis of NVIDIA Tesla V100 PCIe 32 GB and AMD Radeon RX Vega 64 Liquid videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: Geekbench - OpenCL, 3DMark Fire Strike - Graphics Score.

 

Differences

Reasons to consider the NVIDIA Tesla V100 PCIe 32 GB

  • Videocard is newer: launch date 7 month(s) later
  • Around 3% higher texture fill rate: 441.6 GTexel / s vs 429.3 GTexel / s
  • Around 25% higher pipelines: 5120 vs 4096
  • Around 3% better floating-point performance: 14,131 gflops vs 13,738 gflops
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 14 nm
  • 4x more maximum memory size: 32 GB vs 8 GB
Launch date 27 March 2018 vs 8 August 2017
Texture fill rate 441.6 GTexel / s vs 429.3 GTexel / s
Pipelines 5120 vs 4096
Floating-point performance 14,131 gflops vs 13,738 gflops
Manufacturing process technology 12 nm vs 14 nm
Maximum memory size 32 GB vs 8 GB

Reasons to consider the AMD Radeon RX Vega 64 Liquid

  • Around 14% higher core clock speed: 1406 MHz vs 1230 MHz
  • Around 22% higher boost clock speed: 1677 MHz vs 1380 MHz
  • Around 11% lower typical power consumption: 225 Watt vs 250 Watt
  • Around 8% higher memory clock speed: 1890 MHz vs 1752 MHz
Core clock speed 1406 MHz vs 1230 MHz
Boost clock speed 1677 MHz vs 1380 MHz
Thermal Design Power (TDP) 225 Watt vs 250 Watt
Memory clock speed 1890 MHz vs 1752 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla V100 PCIe 32 GB
GPU 2: AMD Radeon RX Vega 64 Liquid

Name NVIDIA Tesla V100 PCIe 32 GB AMD Radeon RX Vega 64 Liquid
Geekbench - OpenCL 334113
3DMark Fire Strike - Graphics Score 0

Compare specifications (specs)

NVIDIA Tesla V100 PCIe 32 GB AMD Radeon RX Vega 64 Liquid

Essentials

Architecture Volta GCN 5.0
Code name GV100 Vega 10
Launch date 27 March 2018 8 August 2017
Place in performance rating 3 1362
Type Workstation Desktop

Technical info

Boost clock speed 1380 MHz 1677 MHz
Core clock speed 1230 MHz 1406 MHz
Floating-point performance 14,131 gflops 13,738 gflops
Manufacturing process technology 12 nm 14 nm
Pipelines 5120 4096
Texture fill rate 441.6 GTexel / s 429.3 GTexel / s
Thermal Design Power (TDP) 250 Watt 225 Watt
Transistor count 21,100 million

Video outputs and ports

Display Connectors No outputs 1x HDMI, 3x DisplayPort

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors 2x 8-pin 2x 8-pin
Length 267 mm

API support

DirectX 12.0 (12_1)
OpenGL 4.6

Memory

Maximum RAM amount 32 GB 8 GB
Memory bandwidth 897.0 GB / s 483.8 GB / s
Memory bus width 4096 Bit 2048 Bit
Memory clock speed 1752 MHz 1890 MHz
Memory type HBM2 HBM2