NVIDIA H100 CNX vs AMD FirePro W9100
GPU · Specs Compare
Graphics Card
Release Date
Mar 2023
Mar 2014
Generation
Tesla Hopper
FirePro
Type
AI GPU
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
690 MHz
—
Boost Clock
1845 MHz
—
Memory Clock
1593 MHz
1250 MHz
Memory
Memory Size
80GB
16GB
Memory Type
HBM2e
GDDR5
Memory Bus
5120bit
512bit
Bandwidth
2039GB/s
320.0GB/s
Render Config
SM Count
114
—
Shading Units
14592
2816
TMUs
456
176
ROPs
24
64
Tensor Cores
456
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
1024 KB
Compute Units
—
44
Theoretical Performance
Pixel Rate
44.28 GPixel/s
59.52 GPixel/s
Texture Rate
841.3 GTexel/s
163.7 GTexel/s
FP16 (half)
215.4 TFLOPS
—
FP32 (float)
53.84 TFLOPS
5.238 TFLOPS
FP64 (double)
26.92 TFLOPS
2.619 TFLOPS
Graphics Processor
GPU Name
GH100
Hawaii
Architecture
Hopper
GCN 2.0
Foundry
TSMC
TSMC
Process Size
4 nm
28 nm
Transistors
80 billion
6.2 billion
Die Size
814 mm²
438 mm²
GPU Variant
—
Hawaii GL44
Board Design
TDP
350W
275W
Suggested PSU
750 W
600 W
Outputs
No outputs
6x mini-DisplayPort 1.21x S-Video
Power Connectors
8-pin EPS
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
N/A
12 (12_0)
OpenGL
N/A
4.6
OpenCL
3.0
2.0
Vulkan
N/A
1.2
CUDA
9.0
—
Shader Model
N/A
6.3
▲ Specs Compare
Data sourced from official specifications and benchmark tests.