NVIDIA B200 SXM6 vs AMD Radeon Pro VII

GPU · Specs Compare

Products
GPU NVIDIA B200 SXM6 NVIDIA · 2024-11
GPU AMD Radeon Pro VII AMD · 2020-05
Graphics Card
Release Date
Nov 2024
May 2020
Generation
Server Blackwell
Radeon Pro Vega
Type
Desktop
Desktop
Bus Interface
PCIe 6.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
120 MHz
1400 MHz
Boost Clock
1830 MHz
1700 MHz
Memory Clock
2000 MHz
1000 MHz
Memory
Memory Size
180GB
16GB
Memory Type
HBM3e
HBM2
Memory Bus
8192bit
4096bit
Bandwidth
8.19TB/s
1020GB/s
Render Config
SM Count
148
—
Shading Units
18944
3840
TMUs
592
240
ROPs
24
64
Tensor Cores
592
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
126 MB
4 MB
Compute Units
—
60
Theoretical Performance
Pixel Rate
43.92 GPixel/s
108.8 GPixel/s
Texture Rate
1083.4 GTexel/s
408.0 GTexel/s
FP16 (half)
1109.4 TFLOPS
26.11 TFLOPS
FP32 (float)
69.34 TFLOPS
13.06 TFLOPS
FP64 (double)
34.67 TFLOPS
6.528 TFLOPS
Graphics Processor
GPU Name
GB100
Vega 20
GPU Variant
GB100-886N-A1
Vega 20 GLXT WS(215-0914026)
Architecture
Blackwell
GCN 5.1
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
208 billion
13.23 billion
Die Size
1628 mm²
331 mm²
Board Design
TDP
1000W
250W
Suggested PSU
1400 W
600 W
Outputs
No outputs
6x mini-DisplayPort 1.4a
Power Connectors
—
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.3
CUDA
10.0
—
Shader Model
N/A
6.7
Benchmark
3DMark Time Spy
—
8,984
3DMark Time Spy Extreme
—
4,369
Blender
—
3,343
▲ Specs Compare Data sourced from official specifications and benchmark tests.