RTX 2000 Embedded Ada Generation vs Radeon Graphics 384SP

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
ArchitectureGCN 5.1 (2018−2022)Ada Lovelace (2022−2024)
GPU code nameCezanneAD107
Market segmentDesktopMobile workstation
Release date13 April 2021 (3 years ago)21 March 2023 (1 year 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 cores3843072
Core clock speed300 MHz1530 MHz
Boost clock speed1700 MHz2010 MHz
Number of transistors9,800 million18,900 million
Manufacturing process technology7 nm5 nm
Power consumption (TDP)45 Watt50 Watt
Texture fill rate40.80193.0
Floating-point processing power1.306 TFLOPS12.35 TFLOPS
ROPs848
TMUs2496
Tensor Coresno data96
Ray Tracing Coresno data24

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).

InterfaceIGPPCIe 4.0 x16
WidthIGPno data
Supplementary power connectorsNoneNone

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 typeSystem SharedGDDR6
Maximum RAM amountSystem Shared8 GB
Memory bus widthSystem Shared128 Bit
Memory clock speedSystem Shared2000 MHz
Memory bandwidthno data256.0 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display ConnectorsNo outputsPortable Device Dependent

API compatibility

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

DirectX12 (12_1)12 Ultimate (12_2)
Shader Model6.7 (6.4)6.8
OpenGL4.64.6
OpenCL2.13.0
Vulkan1.31.3
CUDA-8.9

Pros & cons summary


Recency 13 April 2021 21 March 2023
Chip lithography 7 nm 5 nm
Power consumption (TDP) 45 Watt 50 Watt

Graphics 384SP has 11.1% lower power consumption.

RTX 2000 Embedded Ada Generation, on the other hand, has an age advantage of 1 year, and a 40% more advanced lithography process.

We couldn't decide between Radeon Graphics 384SP and RTX 2000 Embedded Ada Generation. We've got no test results to judge.

Be aware that Radeon Graphics 384SP is a desktop card while RTX 2000 Embedded Ada Generation is a mobile workstation one.


Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.

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.


AMD Radeon Graphics 384SP
Radeon Graphics 384SP
NVIDIA RTX 2000 Embedded Ada Generation
RTX 2000 Embedded Ada Generation

Comparisons with similar GPUs

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.


4.4 20 votes

Rate Radeon Graphics 384SP on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3 2 votes

Rate RTX 2000 Embedded Ada Generation on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Questions & comments

Here you can ask a question about this comparison, agree or disagree with our judgements, or report an error or mismatch.