GPU Comparison
RADEON
AMD AeroBox GPU
CORE STATE
Kryptos
VRAM
8 GB
CLOCK SPEED
985 MHz
TDP
100 W
BUS WIDTH
256 bit
ARCHITECTURE
GCN 1.0
PROCESS
16 nm
LAUNCH DATE
2020
VS
GEFORCE
GeForce RTX 3080
CORE STATE
GA102
VRAM
10 GB
CLOCK SPEED
1710 MHz
TDP
320 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2020
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
AeroBox GPU
RTX 3080
Core Specs
Shading Units
896
8,704
+871.4%
Shaders
896
8,704
+871.4%
TMUs
56
272
+385.7%
ROPs
16
96
+500.0%
Compute Units
14
—
SM Count
—
68
Clocks
Base Clock
935 MHz
1440 MHz
Boost Clock
985 MHz
1710 MHz
Memory Clock
1066 MHz
2.1 Gbps effective
1188 MHz
19 Gbps effective
Memory
Memory Size
8 GB
10 GB
VRAM (MB)
8,192
10,240
+25.0%
Memory Type
DDR3
GDDR6X
Memory Bus
256 bit
320 bit
Bandwidth
68.22 GB/s
760.3 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
5 MB
Performance
Pixel Rate
15.76 GPixel/s
164.2 GPixel/s
Texture Rate
55.16 GTexel/s
465.1 GTexel/s
FP32 (TFLOPS)
1.765 TFLOPS
29.77 TFLOPS
FP64 (TFLOPS)
110.3 GFLOPS (1:16)
465.1 GFLOPS (1:64)
FP16 (TFLOPS)
3.530 TFLOPS (2:1)
29.77 TFLOPS (1:1)
AI/RT
RT Cores
—
68
Tensor Cores
—
272
Power
TDP
100 W
320 W
TDP (W)
100
320
+220.0%
Suggested PSU
—
700 W
Power Connectors
—
1x 12-pin
Architecture
Architecture
GCN 1.0
Ampere
GPU Name
Kryptos
GA102
Generation
Console GPU
(Chuwi)
GeForce 30
Process Size
16 nm
8 nm
Transistors
—
28,300 million
Die Size
—
628 mm²
Foundry
TSMC
Samsung
Density
—
45.1M / mm²
API Support
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
1.2
1.4
OpenCL
1.2
3.0
CUDA
—
8.6
Shader Model
5.1
6.8
Physical
Slot Width
—
Dual-slot
Length
289 mm
11.4 inches
285 mm
11.2 inches
Height
238 mm
9.4 inches
112 mm
4.4 inches
Outputs
1x DVI
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
—
PCIe 4.0 x16
Other
Launch Price
—
699 USD
Production
End-of-life
End-of-life
Predecessor
—
GeForce 20
Successor
—
GeForce 40