A800 PCIe 80 GB vs H100 PCIe 96 GB
AI GPUAI GPU
We compared two GPUs: 80GB VRAM A800 PCIe 80 GB and 96GB VRAM H100 PCIe 96 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
A800 PCIe 80 GB Advantages
Larger VRAM bandwidth (2039GB/s vs 1681GB/s)
Lower TDP (250W vs 700W)
H100 PCIe 96 GB Advantages
Boost Clock has increased by 30% (1837MHz vs 1410MHz)
More VRAM (96GB vs 80GB)
9984 additional rendering cores
Score
Benchmark
FP32 (float)
A800 PCIe 80 GB
19490
H100 PCIe 96 GB
+218%
62080
Graphics Card
Nov 2022
Release Date
Mar 2023
Ampere
Generation
Tesla Hopper
AI GPU
Type
AI GPU
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1065 MHz
Base Clock
1665 MHz
1410 MHz
Boost Clock
1837 MHz
1593 MHz
Memory Clock
1313 MHz
Memory
80GB
Memory Size
96GB
HBM2e
Memory Type
HBM3
5120bit
Memory Bus
5120bit
2039GB/s
Bandwidth
1681GB/s
Render Config
108
SM Count
132
6912
Shading Units
16896
432
TMUs
528
160
ROPs
24
432
Tensor Cores
528
192 KB (per SM)
L1 Cache
256 KB (per SM)
80 MB
L2 Cache
50 MB
Theoretical Performance
225.6 GPixel/s
Pixel Rate
44.09 GPixel/s
609.1 GTexel/s
Texture Rate
969.9 GTexel/s
77.97 TFLOPS
FP16 (half)
248.3 TFLOPS
19.49 TFLOPS
FP32 (float)
62.08 TFLOPS
9.746 TFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
250W
TDP
700W
600 W
Suggested PSU
1100 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
8-pin EPS
Graphics Processor
GA100
GPU Name
GH100
Ampere
Architecture
Hopper
TSMC
Foundry
TSMC
7 nm
Process Size
4 nm
54.2 billion
Transistors
80 billion
826 mm²
Die Size
814 mm²
Graphics Features
N/A
DirectX
N/A
N/A
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
8.0
CUDA
9.0
N/A
Shader Model
N/A