AMD FirePro W6170M vs NVIDIA H100 CNX

GPU · Specs Compare

Products
GPU AMD FirePro W6170M AMD · 2014-08
GPU NVIDIA H100 CNX NVIDIA · 2023-03
Graphics Card
Release Date
Aug 2014
Mar 2023
Generation
FirePro Mobile
Tesla Hopper
Type
Mobile
AI GPU
Bus Interface
MXM-B (3.0)
PCIe 5.0 x16
Clock Speeds
Memory Clock
1500 MHz
1593 MHz
Base Clock
—
690 MHz
Boost Clock
—
1845 MHz
Memory
Memory Size
2GB
80GB
Memory Type
GDDR5
HBM2e
Memory Bus
128bit
5120bit
Bandwidth
96.00GB/s
2039GB/s
Render Config
Compute Units
14
—
Shading Units
896
14592
TMUs
56
456
ROPs
16
24
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
256 KB
50 MB
SM Count
—
114
Tensor Cores
—
456
Theoretical Performance
Pixel Rate
17.60 GPixel/s
44.28 GPixel/s
Texture Rate
61.60 GTexel/s
841.3 GTexel/s
FP32 (float)
1.971 TFLOPS
53.84 TFLOPS
FP64 (double)
123.2 GFLOPS
26.92 TFLOPS
FP16 (half)
—
215.4 TFLOPS
Graphics Processor
GPU Name
Emerald
GH100
GPU Variant
Emerald XT GL(216-0857001)
—
Architecture
GCN 2.0
Hopper
Foundry
TSMC
TSMC
Process Size
28 nm
4 nm
Transistors
2.08 billion
80 billion
Die Size
160 mm²
814 mm²
Board Design
TDP
Unknown
350W
Outputs
Portable Device Dependent
No outputs
Power Connectors
None
8-pin EPS
Suggested PSU
—
750 W
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
▲ Specs Compare Data sourced from official specifications and benchmark tests.