AMD Radeon PRO W9070 vs NVIDIA PG506 242
GPU · Specs Compare
Graphics Card
Release Date
Unknown
Apr 2021
Generation
Mining GPUs
Tesla
Type
Desktop
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1120 MHz
930 MHz
Boost Clock
1206 MHz
1440 MHz
Memory Clock
2100 MHz
1215 MHz
Memory
Memory Size
4GB
24GB
Memory Type
GDDR5
HBM2
Memory Bus
256bit
3072bit
Bandwidth
268.8GB/s
933.1GB/s
Render Config
Compute Units
32
—
Shading Units
2048
3584
TMUs
128
224
ROPs
32
96
Tensor Cores
128
224
RT Cores
64
—
L1 Cache
16 KB (per CU)
192 KB (per SM)
L2 Cache
2 MB
24 MB
L3 Cache
64 MB
—
SM Count
—
56
Theoretical Performance
Pixel Rate
38.59 GPixel/s
138.2 GPixel/s
Texture Rate
154.4 GTexel/s
322.6 GTexel/s
FP16 (half)
4.940 TFLOPS
10.32 TFLOPS
FP32 (float)
4.940 TFLOPS
10.32 TFLOPS
FP64 (double)
308.7 GFLOPS
5.161 TFLOPS
Graphics Processor
GPU Name
Polaris 20
GA100
GPU Variant
Navi 48 XTW
—
Architecture
GCN 4.0
Ampere
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
7 nm
Transistors
5.7 billion
54.2 billion
Die Size
232 mm²
826 mm²
Board Design
TDP
180W
165W
Suggested PSU
450 W
450 W
Outputs
1x HDMI 2.0b
No outputs
Power Connectors
2x 8-pin
8-pin EPS
Graphics Features
DirectX
12 (12_0)
N/A
OpenGL
4.6
N/A
OpenCL
2.1
3.0
Vulkan
1.3
N/A
Shader Model
6.7
N/A
CUDA
—
8.0
▲ Specs Compare
Data sourced from official specifications and benchmark tests.