GeForce RTX 4080 vs Radeon HD 8670 OEM
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 4080 and 2GB VRAM Radeon HD 8670 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4080 's Advantages
Released 9 years and 8 months late
Boost Clock has increased by 139% (2505MHz vs 1050MHz)
More VRAM (16GB vs 2GB)
Larger VRAM bandwidth (716.8GB/s vs 73.60GB/s)
9344 additional rendering cores
Radeon HD 8670 OEM 's Advantages
Lower TDP (75W vs 320W)
Score
Benchmark
FP32 (float)
GeForce RTX 4080
+5947%
48740
Radeon HD 8670 OEM
806
Graphics Card
Sep 2022
Release Date
Jan 2013
GeForce 40
Generation
Sea Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
2205 MHz
Base Clock
1000 MHz
2505 MHz
Boost Clock
1050 MHz
1400 MHz
Memory Clock
1150 MHz
Memory
16GB
Memory Size
2GB
GDDR6X
Memory Type
GDDR5
256bit
Memory Bus
128bit
716.8GB/s
Bandwidth
73.60GB/s
Render Config
-
Compute Units
6
76
SM Count
-
9728
Shading Units
384
304
TMUs
24
112
ROPs
8
304
Tensor Cores
-
76
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
64 MB
L2 Cache
256 KB
Theoretical Performance
280.6 GPixel/s
Pixel Rate
8.400 GPixel/s
761.5 GTexel/s
Texture Rate
25.20 GTexel/s
48.74 TFLOPS
FP16 (half)
-
48.74 TFLOPS
FP32 (float)
806.4 GFLOPS
761.5 GFLOPS
FP64 (double)
50.40 GFLOPS
Board Design
320W
TDP
75W
700 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 1.4a
1x VGA
1x 16-pin
Power Connectors
None
Graphics Processor
AD103
GPU Name
Oland
AD103-300-A1
GPU Variant
Oland XT
(215-0837000)
Ada Lovelace
Architecture
GCN 1.0
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
45.9 billion
Transistors
0.95 billion
379 mm²
Die Size
77 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
1.2
1.3
Vulkan
1.2
8.9
CUDA
-
6.7
Shader Model
5.1
