NVIDIA CMP 170HX 8 GB vs NVIDIA H800 PCIe 80 GB

GPU · Specs Compare

Products
GPU NVIDIA CMP 170HX 8 GB NVIDIA · 2021-09
GPU NVIDIA H800 PCIe 80 GB NVIDIA · 2023-03
Graphics Card
Release Date
Sep 2021
Mar 2023
Generation
Mining GPUs
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 1.0 x4
PCIe 5.0 x16
Clock Speeds
Base Clock
1140 MHz
1095 MHz
Boost Clock
1410 MHz
1755 MHz
Memory Clock
1458 MHz
1593 MHz
Memory
Memory Size
8GB
80GB
Memory Type
HBM2e
HBM2e
Memory Bus
4096bit
5120bit
Bandwidth
1.49TB/s
2039GB/s
Render Config
SM Count
70
114
Shading Units
4480
14592
TMUs
280
456
ROPs
128
24
Tensor Cores
280
456
L1 Cache
192 KB (per SM)
256 KB (per SM)
L2 Cache
8 MB
50 MB
Theoretical Performance
Pixel Rate
180.5 GPixel/s
42.12 GPixel/s
Texture Rate
394.8 GTexel/s
800.3 GTexel/s
FP16 (half)
50.53 TFLOPS
204.9 TFLOPS
FP32 (float)
12.63 TFLOPS
51.22 TFLOPS
FP64 (double)
6.317 TFLOPS
25.61 TFLOPS
Graphics Processor
GPU Name
GA100
GH100
GPU Variant
GA100-105F-A1
—
Architecture
Ampere
Hopper
Foundry
TSMC
TSMC
Process Size
7 nm
4 nm
Transistors
54.2 billion
80 billion
Die Size
826 mm²
814 mm²
Board Design
TDP
250W
350W
Suggested PSU
600 W
750 W
Outputs
No outputs
No outputs
Power Connectors
2x 8-pin
1x 16-pin
Graphics Features
DirectX
N/A
N/A
OpenGL
N/A
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
8.0
9.0
Shader Model
N/A
N/A
▲ Specs Compare Data sourced from official specifications and benchmark tests.