NVIDIA B100 vs NVIDIA CMP 40HX

GPU Specs Compare

G

NVIDIA B100

NVIDIA
G

NVIDIA CMP 40HX

NVIDIA 2021-02

Graphics Card

Release Date
Unknown
Feb 2021
Generation
Server Blackwell
Mining GPUs
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 1.0 x4

Clock Speeds

Base Clock
700 MHz
1470 MHz
Boost Clock
975 MHz
1650 MHz
Memory Clock
2000 MHz
1750 MHz

Memory

Memory Size
96GB
8GB
Memory Type
HBM3e
GDDR6
Memory Bus
4096bit
256bit
Bandwidth
4.10TB/s
448.0GB/s

Render Config

SM Count
132
36
Shading Units
16896
2304
TMUs
528
144
ROPs
24
64
Tensor Cores
528
288
L1 Cache
256 KB (per SM)
64 KB (per SM)
L2 Cache
50 MB
4 MB
RT Cores
-
36

Theoretical Performance

Pixel Rate
23.40 GPixel/s
105.6 GPixel/s
Texture Rate
514.8 GTexel/s
237.6 GTexel/s
FP16 (half)
131.8 TFLOPS
15.21 TFLOPS
FP32 (float)
32.95 TFLOPS
7.603 TFLOPS
FP64 (double)
16.47 TFLOPS
237.6 GFLOPS

Graphics Processor

GPU Name
GB102
TU106
Architecture
Blackwell
Turing
Foundry
TSMC
TSMC
Process Size
5 nm
12 nm
Transistors
104 billion
10.8 billion
Die Size
Unknown
445 mm²
GPU Variant
-
TU106-100-A1

Board Design

TDP
1000W
185W
Suggested PSU
1400 W
450 W
Outputs
No outputs
No outputs
Power Connectors
-
1x 8-pin

Graphics Features

DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
CUDA
10.1
7.5
Shader Model
N/A
6.8

📊 Benchmark

Blender
-
1,174