AMD FirePro S7150 x2 vs NVIDIA H100 CNX

GPU Specs Compare

G

NVIDIA H100 CNX

NVIDIA 2023-03

Graphics Card

Release Date
Feb 2016
Mar 2023
Generation
FirePro Server
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16

Clock Speeds

Memory Clock
1250 MHz
1593 MHz
Base Clock
-
690 MHz
Boost Clock
-
1845 MHz

Memory

Memory Size
8GB
80GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
160.0GB/s
2039GB/s

Render Config

Compute Units
28
-
Shading Units
1792
14592
TMUs
112
456
ROPs
32
24
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
512 KB
50 MB
SM Count
-
114
Tensor Cores
-
456

Theoretical Performance

Pixel Rate
29.44 GPixel/s
44.28 GPixel/s
Texture Rate
103.0 GTexel/s
841.3 GTexel/s
FP16 (half)
3.297 TFLOPS
215.4 TFLOPS
FP32 (float)
3.297 TFLOPS
53.84 TFLOPS
FP64 (double)
206.1 GFLOPS
26.92 TFLOPS

Graphics Processor

GPU Name
Tonga
GH100
GPU Variant
Cloudy Tau
-
Architecture
GCN 3.0
Hopper
Foundry
TSMC
TSMC
Process Size
28 nm
4 nm
Transistors
5 billion
80 billion
Die Size
366 mm²
814 mm²

Board Design

TDP
265W
350W
Suggested PSU
600 W
750 W
Outputs
No outputs
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
8-pin EPS

Graphics Features

DirectX
12 (12_0)
N/A
OpenGL
4.6
N/A
OpenCL
2.1
3.0
Vulkan
1.2.170
N/A
Shader Model
6.5
N/A
CUDA
-
9.0