NVIDIA P104-100 vs AMD Radeon Pro Vega 64

Comparative analysis of NVIDIA P104-100 and AMD Radeon Pro Vega 64 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, PassMark - G2D Mark, PassMark - G3D Mark, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the NVIDIA P104-100

  • Videocard is newer: launch date 5 month(s) later
  • Around 29% higher core clock speed: 1607 MHz vs 1250 MHz
  • Around 28% higher boost clock speed: 1733 MHz vs 1350 MHz
  • 6.4x more memory clock speed: 10008 MHz vs 1572 MHz
  • 2.5x better performance in Geekbench - OpenCL: 172967 vs 68120
Specifications (specs)
Launch date 12 December 2017 vs 27 June 2017
Core clock speed 1607 MHz vs 1250 MHz
Boost clock speed 1733 MHz vs 1350 MHz
Memory clock speed 10008 MHz vs 1572 MHz
Benchmarks
Geekbench - OpenCL 172967 vs 68120

Reasons to consider the AMD Radeon Pro Vega 64

  • Around 25% higher texture fill rate: 345.6 GTexel / s vs 277.3 GTexel / s
  • Around 60% higher pipelines: 4096 vs 2560
  • Around 25% better floating-point performance: 11,059 gflops vs 8,873 gflops
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 14 nm vs 16 nm
  • 2x more maximum memory size: 16 GB vs 8 GB
  • 6.2x better performance in PassMark - G2D Mark: 708 vs 114
  • 2.6x better performance in PassMark - G3D Mark: 11456 vs 4450
Specifications (specs)
Texture fill rate 345.6 GTexel / s vs 277.3 GTexel / s
Pipelines 4096 vs 2560
Floating-point performance 11,059 gflops vs 8,873 gflops
Manufacturing process technology 14 nm vs 16 nm
Maximum memory size 16 GB vs 8 GB
Benchmarks
PassMark - G2D Mark 708 vs 114
PassMark - G3D Mark 11456 vs 4450

Compare benchmarks

GPU 1: NVIDIA P104-100
GPU 2: AMD Radeon Pro Vega 64

Geekbench - OpenCL
GPU 1
GPU 2
172967
68120
PassMark - G2D Mark
GPU 1
GPU 2
114
708
PassMark - G3D Mark
GPU 1
GPU 2
4450
11456
Name NVIDIA P104-100 AMD Radeon Pro Vega 64
Geekbench - OpenCL 172967 68120
PassMark - G2D Mark 114 708
PassMark - G3D Mark 4450 11456
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 142.691
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 1729.558
CompuBench 1.5 Desktop - T-Rex (Frames/s) 12.693
CompuBench 1.5 Desktop - Video Composition (Frames/s) 111.376
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 1396.172
GFXBench 4.0 - Car Chase Offscreen (Frames) 13339
GFXBench 4.0 - Manhattan (Frames) 3709
GFXBench 4.0 - T-Rex (Frames) 3353
GFXBench 4.0 - Car Chase Offscreen (Fps) 13339
GFXBench 4.0 - Manhattan (Fps) 3709
GFXBench 4.0 - T-Rex (Fps) 3353

Compare specifications (specs)

NVIDIA P104-100 AMD Radeon Pro Vega 64

Essentials

Architecture Pascal GCN 5.0
Code name GP104 Vega 10
Launch date 12 December 2017 27 June 2017
Place in performance rating 78 85
Type Desktop Workstation

Technical info

Boost clock speed 1733 MHz 1350 MHz
Core clock speed 1607 MHz 1250 MHz
Floating-point performance 8,873 gflops 11,059 gflops
Manufacturing process technology 16 nm 14 nm
Pipelines 2560 4096
Texture fill rate 277.3 GTexel / s 345.6 GTexel / s
Transistor count 7,200 million 12,500 million
Thermal Design Power (TDP) 250 Watt

Video outputs and ports

Display Connectors No outputs No outputs

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Length 267 mm 267 mm
Supplementary power connectors 1x 8-pin None

API support

DirectX 12.0 (12_1) 12.0 (12_1)
OpenGL 4.6 4.6

Memory

Maximum RAM amount 8 GB 16 GB
Memory bandwidth 320.3 GB / s 402.4 GB / s
Memory bus width 256 Bit 2048 Bit
Memory clock speed 10008 MHz 1572 MHz
Memory type GDDR5X HBM2