NVIDIA B100 vs AMD Radeon RX 6600S

GPU · Specs Compare

Products
GPU NVIDIA B100 NVIDIA
GPU AMD Radeon RX 6600S AMD · 2022-01
Graphics Card
Release Date
Unknown
Jan 2022
Generation
Server Blackwell
Mobility Radeon
Type
Desktop
Mobile
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Clock Speeds
Base Clock
700 MHz
1700 MHz
Boost Clock
975 MHz
2000 MHz
Memory Clock
2000 MHz
1750 MHz
Memory
Memory Size
96GB
4GB
Memory Type
HBM3e
GDDR6
Memory Bus
4096bit
128bit
Bandwidth
4.10TB/s
224.0GB/s
Render Config
SM Count
132
—
Shading Units
16896
1792
TMUs
528
112
ROPs
24
64
Tensor Cores
528
—
L1 Cache
256 KB (per SM)
128 KB per Array
L2 Cache
50 MB
2 MB
Compute Units
—
28
RT Cores
—
28
L3 Cache
—
32 MB
Theoretical Performance
Pixel Rate
23.40 GPixel/s
128.0 GPixel/s
Texture Rate
514.8 GTexel/s
224.0 GTexel/s
FP16 (half)
131.8 TFLOPS
14.34 TFLOPS
FP32 (float)
32.95 TFLOPS
7.168 TFLOPS
FP64 (double)
16.47 TFLOPS
448.0 GFLOPS
Graphics Processor
GPU Name
GB102
Navi 23
Architecture
Blackwell
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
104 billion
11.06 billion
Die Size
Unknown
237 mm²
Board Design
TDP
1000W
80W
Suggested PSU
1400 W
—
Outputs
No outputs
No outputs
Power Connectors
—
None
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.3
CUDA
10.1
—
Shader Model
N/A
6.5
Benchmark
3DMark Time Spy
—
7,700
3DMark Time Spy Extreme
—
3,389
▲ Specs Compare Data sourced from official specifications and benchmark tests.