NVIDIA B200 vs AMD Radeon R9 M390X

GPU · Specs Compare

Products
GPU NVIDIA B200 NVIDIA · 2024-01
GPU AMD Radeon R9 M390X AMD · 2015-05
Graphics Card
Release Date
Jan 2024
May 2015
Generation
Server Blackwell
Crystal System
Type
Desktop
Mobile
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
700 MHz
—
Boost Clock
1965 MHz
—
Memory Clock
2000 MHz
1250 MHz
Memory
Memory Size
90GB
4GB
Memory Type
HBM3e
GDDR5
Memory Bus
4096bit
256bit
Bandwidth
4.10TB/s
160.0GB/s
Render Config
SM Count
148
—
Shading Units
18944
2048
TMUs
592
128
ROPs
24
32
Tensor Cores
592
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
512 KB
Compute Units
—
32
Theoretical Performance
Pixel Rate
47.16 GPixel/s
23.14 GPixel/s
Texture Rate
1163.3 GTexel/s
92.54 GTexel/s
FP16 (half)
1191.2 TFLOPS
2.961 TFLOPS
FP32 (float)
74.45 TFLOPS
2.961 TFLOPS
FP64 (double)
37.22 TFLOPS
185.1 GFLOPS
Graphics Processor
GPU Name
GB100
Amethyst
Architecture
Blackwell
GCN 3.0
Foundry
TSMC
TSMC
Process Size
5 nm
28 nm
Transistors
104 billion
5 billion
Die Size
Unknown
366 mm²
GPU Variant
—
Amethyst XT
Board Design
TDP
1000W
75W
Suggested PSU
1400 W
—
Outputs
No outputs
No outputs
Power Connectors
—
None
Graphics Features
DirectX
N/A
12 (12_0)
OpenGL
N/A
4.6
OpenCL
3.0
2.0
Vulkan
N/A
1.2
CUDA
10.0
—
Shader Model
N/A
6.3
▲ Specs Compare Data sourced from official specifications and benchmark tests.