NVIDIA GeForce RTX 3080 Ti vs AMD Radeon R9 390
GPU · Specs Compare
Graphics Card
Release Date
May 2021
Jun 2015
Generation
GeForce 30
Pirate Islands
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1365 MHz
—
Boost Clock
1665 MHz
—
Memory Clock
1188 MHz
1500 MHz
Memory
Memory Size
12GB
8GB
Memory Type
GDDR6X
GDDR5
Memory Bus
384bit
512bit
Bandwidth
912.4GB/s
384.0GB/s
Render Config
SM Count
80
—
Shading Units
10240
2560
TMUs
320
160
ROPs
112
64
Tensor Cores
320
—
RT Cores
80
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
6 MB
1024 KB
Compute Units
—
40
Theoretical Performance
Pixel Rate
186.5 GPixel/s
64.00 GPixel/s
Texture Rate
532.8 GTexel/s
160.0 GTexel/s
FP16 (half)
34.10 TFLOPS
—
FP32 (float)
34.10 TFLOPS
5.120 TFLOPS
FP64 (double)
532.8 GFLOPS
640.0 GFLOPS
Graphics Processor
GPU Name
GA102
Grenada
GPU Variant
GA102-225-A1
Grenada PRO(215-0880030)
Architecture
Ampere
GCN 2.0
Foundry
Samsung
TSMC
Process Size
8 nm
28 nm
Transistors
28.3 billion
6.2 billion
Die Size
628 mm²
438 mm²
Board Design
TDP
350W
275W
Suggested PSU
750 W
600 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
Power Connectors
1x 12-pin
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.0
Vulkan
1.3
1.2
CUDA
8.6
—
Shader Model
6.6
6.3
Benchmark
3DMark Time Spy
19,629
3,964
3DMark Time Spy Extreme
10,032
1,931
3DMark Speed Way
5,330
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.