Arc A350 vs H100 SXM5

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot ratednot rated
Place by popularitynot in top-100not in top-100
ArchitectureHopper (2022−2024)Generation 12.7 (2022−2023)
GPU code nameGH100DG2-128
Market segmentWorkstationDesktop
Release date22 March 2022 (3 years ago)2022 (3 years ago)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores8448768
Core clock speed1065 MHz2000 MHz
Boost clock speed1780 MHz2000 MHz
Number of transistors80,000 million7,200 million
Manufacturing process technology4 nm6 nm
Power consumption (TDP)700 Watt25 Watt
Texture fill rate939.896.00
Floating-point processing power30.07 TFLOPS3.072 TFLOPS
ROPs2424
TMUs52848
Tensor Cores52896
Ray Tracing Coresno data6
L1 Cache24.8 MBno data
L2 Cache50 MB4 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

InterfacePCIe 5.0 x16PCIe 4.0 x8
Widthno data1-slot
Supplementary power connectors8-pin EPSno data

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory typeHBM3GDDR6
Maximum RAM amount80 GB4 GB
Memory bus width5120 Bit64 Bit
Memory clock speed1500 MHz1937 MHz
Memory bandwidth1,920 GB/s124.0 GB/s
Resizable BAR++

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display ConnectorsNo outputsNo outputs

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectXN/A12 Ultimate (12_2)
Shader ModelN/A6.6
OpenGLN/A4.6
OpenCL3.03.0
VulkanN/A1.3
CUDA9.0-
DLSS++

Pros & cons summary


Maximum RAM amount 80 GB 4 GB
Chip lithography 4 nm 6 nm
Power consumption (TDP) 700 Watt 25 Watt

H100 SXM5 has a 1900% higher maximum VRAM amount, and a 50% more advanced lithography process.

Arc A350, on the other hand, has 2700% lower power consumption.

We couldn't decide between H100 SXM5 and Arc A350. We've got no test results to judge.

Be aware that H100 SXM5 is a workstation graphics card while Arc A350 is a desktop one.

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.


NVIDIA H100 SXM5
H100 SXM5
Intel Arc A350
Arc A350

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


4.2 27 votes

Rate H100 SXM5 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.3 6 votes

Rate Arc A350 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about H100 SXM5 or Arc A350, agree or disagree with our ratings, or report errors or inaccuracies on the site.