TITAN RTX vs Radeon VII

TITAN RTX
Memory: 24576Mb GDDR6DESKTOP
Release date: 18 Dec 2018
TITAN RTX
Radeon VII
Memory: 16384Mb HBM2DESKTOP
Release date: 7 Feb 2019
Radeon VII

Summary

Reasons to consider TITAN RTX

Higher theoretical gaming performance, based on specifications.
Supports PhysX
Supports G-Sync
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty)
Supports Direct3D 12 Async Compute
Supports DirectX Raytracing (DXR)
Supports Deep Learning Super-Sampling (DLSS)

Reasons to consider Radeon VII

Supports Direct3D 12 Async Compute
Supports FreeSync
Supports ReLive (allows game streaming/recording with minimum performance penalty)
Supports TrueAudio
Based on an outdated architecture (AMD GCN), there may be no performance optimizations for current games and applications

TITAN RTX

HWBench recommends TITAN RTX

Based on theoretical specifications.


Specifications

Core Configuration

TITAN RTXRadeon VII
GPU NameTU102 (TU102-400-A1)vsVega 20 (Vega 20 XT)
Fab Process12 nmvs7 nm
Die Size754 mm²vs331 mm²
Transistors18,600 millionvs13,230 million
Shaders4608vs3840
Compute Units72vs60
Core clock1350 MHzvs1450 MHz
ROPs96vs64
TMUs288vs240

Memory Configuration

TITAN RTXRadeon VII
Memory TypeGDDR6vsHBM2
Bus Width384 bitvs4096 bit
Memory Speed1750 MHz
14000 MHz effective
vs1000 MHz
2000 MHz effective
Memory Size24576 Mbvs16384 Mb

Additional details

TITAN RTXRadeon VII
TDP280 wattsvs295 watts
Release Date18 Dec 2018vs7 Feb 2019

Raw Performance comparison

Pixel Rate

  • TITAN RTX
    169.90 GP/s
  • Radeon VII
    115.20 GP/s

GigaPixels - higher is better

Texel Rate

  • TITAN RTX
    509.80 GT/s
  • Radeon VII
    432.00 GT/s

GigaTexels - higher is better

Memory bandwidth

  • TITAN RTX
    672.00 GB/s
  • Radeon VII
    1024.00 GB/s

GB/s - higher is better

Single precision performance

  • TITAN RTX
    16312.00 GFLOPs
  • Radeon VII
    13824.00 GFLOPs

GFLOPs - higher is better