Report an Error

NVIDIA H100 SXM5 80 GB

Graphics Processor
GH100
Cores
16896
TMUs
528
ROPs
24
Memory Size
80 GB
Memory Type
HBM3
Bus Width
5120 bit
GPU Chip
GPU
The H100 SXM5 80 GB is a professional graphics card by NVIDIA, launched on March 21st, 2023. Built on the 5 nm process, and based on the GH100 graphics processor, the card does not support DirectX. Since H100 SXM5 80 GB does not support DirectX 11 or DirectX 12, it might not be able to run all the latest games. The GH100 graphics processor is a large chip with a die area of 814 mm² and 80,000 million transistors. It features 16896 shading units, 528 texture mapping units, and 24 ROPs. Also included are 528 tensor cores which help improve the speed of machine learning applications. NVIDIA has paired 80 GB HBM3 memory with the H100 SXM5 80 GB, which are connected using a 5120-bit memory interface. The GPU is operating at a frequency of 1590 MHz, which can be boosted up to 1980 MHz, memory is running at 1313 MHz.
Being a sxm module card, the NVIDIA H100 SXM5 80 GB does not require any additional power connector, its power draw is rated at 700 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. H100 SXM5 80 GB is connected to the rest of the system using a PCI-Express 5.0 x16 interface.

Graphics Processor

GPU Name
GH100
Architecture
Hopper
Foundry
TSMC
Process Size
5 nm
Transistors
80,000 million
Density
98.3M / mm²
Die Size
814 mm²

Graphics Card

Release Date
Mar 21st, 2023
Generation
Tesla Hopper
(Hxx)
Predecessor
Tesla Ada
Successor
Tesla Blackwell
Production
Active
Bus Interface
PCIe 5.0 x16

Clock Speeds

Base Clock
1590 MHz
Boost Clock
1980 MHz
Memory Clock
1313 MHz
5.3 Gbps effective

Memory

Memory Size
80 GB
Memory Type
HBM3
Memory Bus
5120 bit
Bandwidth
3.36 TB/s

Render Config

Shading Units
16896
TMUs
528
ROPs
24
SM Count
132
Tensor Cores
528
L1 Cache
256 KB (per SM)
L2 Cache
50 MB

Theoretical Performance

Pixel Rate
47.52 GPixel/s
Texture Rate
1,045 GTexel/s
FP16 (half)
267.6 TFLOPS (4:1)
FP32 (float)
66.91 TFLOPS
FP64 (double)
33.45 TFLOPS (1:2)

Board Design

Slot Width
SXM Module
TDP
700 W
Suggested PSU
1100 W
Outputs
No outputs
Power Connectors
None
Board Number
PG520

Graphics Features

DirectX
N/A
OpenGL
N/A
OpenCL
3.0
Vulkan
N/A
CUDA
9.0
Shader Model
N/A

GH100 GPU Notes

Tensor Cores: 4th Gen
NVENC: No Support
NVDEC: No Support
PureVideo HD: VP11
VDPAU: Feature Set K
Dec 12th, 2024 20:39 CST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts