NVIDIA H100 PCIe 80 GB vs NVIDIA A800 PCIe 80 GB
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Nov 2022
Generation
Server Hopper
Ampere
Type
AI GPU
AI GPU
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1095 MHz
1065 MHz
Boost Clock
1755 MHz
1410 MHz
Memory Clock
1593 MHz
1593 MHz
Memory
Memory Size
80GB
80GB
Memory Type
HBM2e
HBM2e
Memory Bus
5120bit
5120bit
Bandwidth
2.04TB/s
2039GB/s
Render Config
SM Count
114
108
Shading Units
14592
6912
TMUs
456
432
ROPs
24
160
Tensor Cores
456
432
L1 Cache
256 KB (per SM)
192 KB (per SM)
L2 Cache
50 MB
80 MB
Theoretical Performance
Pixel Rate
42.12 GPixel/s
225.6 GPixel/s
Texture Rate
800.3 GTexel/s
609.1 GTexel/s
FP16 (half)
204.9 TFLOPS
77.97 TFLOPS
FP32 (float)
51.22 TFLOPS
19.49 TFLOPS
FP64 (double)
25.61 TFLOPS
9.746 TFLOPS
Graphics Processor
GPU Name
GH100
GA100
Architecture
Hopper
Ampere
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
80 billion
54.2 billion
Die Size
814 mm²
826 mm²
Board Design
TDP
350W
250W
Suggested PSU
750 W
600 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
8-pin EPS
Graphics Features
DirectX
N/A
N/A
OpenGL
N/A
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
9.0
8.0
Shader Model
N/A
N/A
Benchmark
Blender
—
3,719
▲ Specs Compare
Data sourced from official specifications and benchmark tests.