Home GPU Comparison NVIDIA GeForce RTX 3060 Ti GA103 vs AMD Radeon Pro Duo

NVIDIA GeForce RTX 3060 Ti GA103 vs AMD Radeon Pro Duo

We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GA103 and 4GB VRAM Radeon Pro Duo to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 3060 Ti GA103 's Advantages
Released 5 years and 10 months late
Boost Clock1665MHz
More VRAM (8GB vs 4GB)
768 additional rendering cores
Lower TDP (200W vs 350W)
AMD Radeon Pro Duo 's Advantages
Larger VRAM bandwidth (512.0GB/s vs 448.0GB/s)

Score

Benchmark

FP32 (float)
GeForce RTX 3060 Ti GA103 +97%
16.2 TFLOPS
Radeon Pro Duo
8.192 TFLOPS
VS

Graphics Card

Feb 2022
Release Date
Apr 2016
GeForce 30
Generation
Radeon Pro
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16

Clock Speeds

1410 MHz
Base Clock
-
1665 MHz
Boost Clock
-
1750 MHz
Memory Clock
500 MHz

Memory

8GB
Memory Size
4GB
GDDR6
Memory Type
HBM
256bit
Memory Bus
4096bit
448.0GB/s
Bandwidth
512.0GB/s

Render Config

-
Compute Units
64
38
SM Count
-
4864
Shading Units
4096
152
TMUs
256
80
ROPs
64
152
Tensor Cores
-
38
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
2 MB
-
-
-

Theoretical Performance

133.2 GPixel/s
Pixel Rate
64.00 GPixel/s
253.1 GTexel/s
Texture Rate
256.0 GTexel/s
16.20 TFLOPS
FP16 (half)
8.192 TFLOPS
16.20 TFLOPS
FP32 (float)
8.192 TFLOPS
253.1 GFLOPS
FP64 (double)
512.0 GFLOPS

Board Design

200W
TDP
350W
550 W
Suggested PSU
750 W
1x HDMI 2.1 3x DisplayPort 1.4a
Outputs
1x HDMI 1.4a 3x DisplayPort 1.2
1x 12-pin
Power Connectors
3x 8-pin

Graphics Processor

GA103S
GPU Name
Capsaicin
GA103-200-A1
GPU Variant
Capsaicin XT
Ampere
Architecture
GCN 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
Unknown
Transistors
8.9 billion
496 mm²
Die Size
596 mm²

Graphics Features

12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.0
1.3
Vulkan
1.2
8.6
CUDA
-
6.5
Shader Model
6.0

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy