NVIDIA GeForce RTX 4070 GDDR6 vs AMD Radeon R9 390
GPU · Specs Compare
Graphics Card
Release Date
Aug 2024
Jun 2015
Generation
GeForce 40
Pirate Islands
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1920 MHz
—
Boost Clock
2475 MHz
—
Memory Clock
2500 MHz
1500 MHz
Memory
Memory Size
12GB
8GB
Memory Type
GDDR6
GDDR5
Memory Bus
192bit
512bit
Bandwidth
480.0GB/s
384.0GB/s
Render Config
SM Count
46
—
Shading Units
5888
2560
TMUs
184
160
ROPs
64
64
Tensor Cores
184
—
RT Cores
46
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
36 MB
1024 KB
Compute Units
—
40
Theoretical Performance
Pixel Rate
158.4 GPixel/s
64.00 GPixel/s
Texture Rate
455.4 GTexel/s
160.0 GTexel/s
FP16 (half)
29.15 TFLOPS
—
FP32 (float)
29.15 TFLOPS
5.120 TFLOPS
FP64 (double)
455.4 GFLOPS
640.0 GFLOPS
Graphics Processor
GPU Name
AD104
Grenada
GPU Variant
AD104-2XX-A1
Grenada PRO(215-0880030)
Architecture
Ada Lovelace
GCN 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
28 nm
Transistors
35.8 billion
6.2 billion
Die Size
294 mm²
438 mm²
Board Design
TDP
200W
275W
Suggested PSU
550 W
600 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
Power Connectors
1x 16-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
8.9
—
Shader Model
6.8
6.3
Benchmark
3DMark Time Spy
—
3,964
3DMark Time Spy Extreme
—
1,931
▲ Specs Compare
Data sourced from official specifications and benchmark tests.