AMD Radeon VII vs NVIDIA P104-100 8 GB
We compared two Desktop platform GPUs: 16GB VRAM Radeon VII and 48GB
GB VRAM NVIDIA P104 100 8 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon VII 's Advantages
Released 1 years and 2 months late
Boost Clock has increased by 1% (1750MHz vs 1733MHz)
More VRAM (16GB vs 48GB)
Larger VRAM bandwidth (1020GB/s vs 320.3GB/s)
1920 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon VII
+101%
13.44 TFLOPS
NVIDIA P104 100 8 GB
6.655 TFLOPS
Graphics Card
Feb 2019
Release Date
Dec 2017
Vega II
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
1400 MHz
Base Clock
1607 MHz
1750 MHz
Boost Clock
1733 MHz
1000 MHz
Memory Clock
1251 MHz
Memory
16GB
Memory Size
48GB
GB
HBM2
Memory Type
GDDR5X
4096bit
Memory Bus
256bit
1020GB/s
Bandwidth
320.3GB/s
Render Config
60
Compute Units
-
-
SM Count
15
3840
Shading Units
1920
240
TMUs
120
64
ROPs
64
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
112.0 GPixel/s
Pixel Rate
110.9 GPixel/s
420.0 GTexel/s
Texture Rate
208.0 GTexel/s
26.88 TFLOPS
FP16 (half)
104.0 GFLOPS
13.44 TFLOPS
FP32 (float)
6.655 TFLOPS
3.360 TFLOPS
FP64 (double)
208.0 GFLOPS
Board Design
295W
TDP
Unknown
600 W
Suggested PSU
200 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
No outputs
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
Vega 20
GPU Name
GP104
Vega 20 XT
GPU Variant
GP104-100-A1
GCN 5.1
Architecture
Pascal
TSMC
Foundry
TSMC
7 nm
Process Size
16 nm
13.23 billion
Transistors
7.2 billion
331 mm²
Die Size
314 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
6.1
6.7
Shader Model
6.8
