NVIDIA H800 SXM5 vs NVIDIA H100 PCIe 80 GB
AI GPUAI GPU
We compared two GPUs: 80GB VRAM H800 SXM5 and 80GB VRAM H100 PCIe 80 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA H800 SXM5 's Advantages
2304 additional rendering cores
NVIDIA H100 PCIe 80 GB 's Advantages
Larger VRAM bandwidth (2.04TB/s vs 1681GB/s)
Lower TDP (350W vs 700W)
Score
Benchmark
FP32 (float)
H800 SXM5
+15%
59.3 TFLOPS
H100 PCIe 80 GB
51.22 TFLOPS
Graphics Card
Mar 2023
Release Date
Oct 2022
Tesla Hopper
Generation
Server Hopper
AI GPU
Type
AI GPU
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1095 MHz
Base Clock
1095 MHz
1755 MHz
Boost Clock
1755 MHz
1313 MHz
Memory Clock
1593 MHz
Memory
80GB
Memory Size
80GB
HBM3
Memory Type
HBM2e
5120bit
Memory Bus
5120bit
1681GB/s
Bandwidth
2.04TB/s
Render Config
-
-
-
132
SM Count
114
16896
Shading Units
14592
528
TMUs
456
24
ROPs
24
528
Tensor Cores
456
-
-
-
256 KB (per SM)
L1 Cache
256 KB (per SM)
50 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
42.12 GPixel/s
Pixel Rate
42.12 GPixel/s
926.6 GTexel/s
Texture Rate
800.3 GTexel/s
237.2 TFLOPS
FP16 (half)
204.9 TFLOPS
59.30 TFLOPS
FP32 (float)
51.22 TFLOPS
29.65 TFLOPS
FP64 (double)
25.61 TFLOPS
Board Design
700W
TDP
350W
1100 W
Suggested PSU
750 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
1x 16-pin
Graphics Processor
GH100
GPU Name
GH100
-
-
-
Hopper
Architecture
Hopper
TSMC
Foundry
TSMC
4 nm
Process Size
5 nm
80 billion
Transistors
80 billion
814 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
9.0
CUDA
9.0
N/A
Shader Model
N/A
