Data Center GPU Max Subsystem vs Iris Plus Graphics 640

#ad 
Buy on Amazon
VS

Primary details

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

Place in the ranking775not rated
Place by popularitynot in top-100not in top-100
Power efficiency18.28no data
ArchitectureGeneration 9.5 (2016−2020)Generation 12.5 (2021−2023)
GPU code nameKaby Lake GT3ePonte Vecchio
Market segmentLaptopWorkstation
Release date3 January 2017 (9 years ago)10 January 2023 (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 cores38416384 ×4
Core clock speed300 MHz900 MHz
Boost clock speed1100 MHz1600 MHz
Number of transistors189 million100,000 million
Manufacturing process technology14 nm++10 nm
Power consumption (TDP)15 Watt2400 Watt
Texture fill rate52.801,638 ×4
Floating-point processing power0.8448 TFLOPS52.43 TFLOPS ×4
ROPs6no data
TMUs481024 ×4
Tensor Coresno data1024 ×4
Ray Tracing Coresno data128 ×4
L1 Cacheno data64 MB
L2 Cacheno data408 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).

InterfaceRing BusPCIe 5.0 x16
Lengthno data267 mm
Widthno data2-slot
Supplementary power connectorsno data1x 16-pin

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 typeDDR3L/LPDDR3/DDR4HBM2e
Maximum RAM amount32 GB128 GB ×4
Memory bus widthSystem Shared8192 Bit ×4
Memory clock speedSystem Shared1565 MHz
Memory bandwidthno data3,205 GB/s ×4
Shared memory+-

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 ConnectorsPortable Device DependentNo outputs

Supported technologies

Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.

Quick Sync+no data

API and SDK support

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

DirectX12 (12_1)12 (12_1)
Shader Model6.46.6
OpenGL4.64.6
OpenCL3.03.0
Vulkan1.3N/A
DLSS-+

Pros & cons summary


Recency 3 January 2017 10 January 2023
Maximum RAM amount 32 GB 128 GB
Chip lithography 14 nm 10 nm
Power consumption (TDP) 15 Watt 2400 Watt

Iris Plus Graphics 640 has 15900% lower power consumption.

Data Center GPU Max Subsystem, on the other hand, has an age advantage of 6 years, a 300% higher maximum VRAM amount, and a 40% more advanced lithography process.

We couldn't decide between Iris Plus Graphics 640 and Data Center GPU Max Subsystem. We've got no test results to judge.

Be aware that Iris Plus Graphics 640 is a notebook graphics card while Data Center GPU Max Subsystem is a workstation one.

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.


3.3 322 votes

Rate Iris Plus Graphics 640 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
2.9 133 votes

Rate Data Center GPU Max Subsystem on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about Iris Plus Graphics 640 or Data Center GPU Max Subsystem, agree or disagree with our ratings, or report errors or inaccuracies on the site.