Close Menu
  • Graphic cards
  • Laptops
  • Monitors
  • Motherboard
  • Processors
  • Smartphones
  • Smartwatches
  • Solid state drives
Facebook X (Twitter) Instagram
Facebook X (Twitter) Instagram
Dutchieetech
Subscribe Now
  • Graphic cards
  • Laptops
  • Monitors
  • Motherboard
  • Processors
  • Smartphones
  • Smartwatches
  • Solid state drives
Dutchieetech
Processors

Samsung’s Exynos 2400 Cellular AP Claims Superior GPU Efficiency Over US Rivals

dutchieetech.comBy dutchieetech.com29 October 2023No Comments4 Mins Read

Park Yong-in, president of Samsung Electronics’ System LSI Division, delivers a keynote speech at the Semiconductor Expo 2023 held at COEX in Seoul on Oct. 26.
Park Yong-in, president of Samsung Electronics’ System LSI Division, delivers a keynote speech on the Semiconductor Expo 2023 held at COEX in Seoul on Oct. 26.


Park Yong-in, who oversees Samsung Electronics’ system semiconductor design operations as President of the System LSI Division, expressed confidence within the success of the corporate’s newest cellular utility processor, the Exynos 2400.


On Oct. 26, following his keynote handle at Semiconductor Expo 2023 held at COEX in Seoul, Park met with reporters and acknowledged, “The Exynos 2400 boasts superior graphics processing capabilities in comparison with North American opponents, and I imagine it would carry out effectively.” He additional added, “I hope the upcoming Samsung Galaxy S24 sequence, which is able to characteristic the Exynos processor, may also achieve success.”


Earlier this month, Samsung Electronics unveiled the Exynos 2400, a next-generation cellular processor fitted to the age of generative AI. This processor is slated to be integrated into Samsung’s flagship Galaxy S24 sequence. The Exynos AP confronted challenges earlier this 12 months when not a single chip was included within the Galaxy S23 because of efficiency points, denting the model’s delight. Nonetheless, the corporate is aiming for a resurgence by considerably enhancing varied performances, leveraging a 4-nanometer (nm) foundry, neural processing unit (NPU), central processing unit (CPU), and extra. In comparison with its predecessor, the Exynos 2200, the CPU efficiency has improved by 1.7 occasions and AI capabilities by 14.7 occasions, marking an bold goal to shut the hole with world leaders like Qualcomm and Apple.


Park additionally hinted on the potential use of the gate-all-around (GAA) 3-nm course of, which Samsung Electronics’ foundry started mass-producing as a world first. Relating to this, he famous, “Within the realm past 100 million pixels, we (Samsung Electronics) dominate.” When pressed additional, he responded succinctly, “We’re getting ready, and it’ll go effectively.”


In his keynote, Park emphasised the importance of progress in AI semiconductors. “Costs of GPUs used as AI accelerators are on the rise, they usually have vital power consumption points. Consequently, there’s a rising shift in direction of different processes optimized for AI workloads, akin to NPUs and RISC architectures,” he defined.


Highlighting the environmental influence of technological developments, Park acknowledged, “Resulting from generative AI, the overall annual energy consumption of information facilities now exceeds that of nations like Spain, the U.Ok., or Italy. By 2030, the ability consumption will possible surpass this 12 months’s 470 terawatts, reaching over 1,000 terawatts.”


Describing the options of the GPU embedded within the Exynos 2400, Park significantly talked about its ray tracing know-how, which has been extremely praised by GPU consultants. Ray tracing is a graphics know-how that realistically represents objects by tracing gentle because it refracts, displays, and penetrates them. This GPU was co-designed with world semiconductor firm AMD and was additionally applied in Samsung’s flagship smartphone, the S23, launched earlier this 12 months. “This know-how may also be integrated into telephones launched subsequent 12 months. Smartphones are actually performing features that supercomputers used to do,” he famous.


Park predicts a shift in direction of “on-device AI” sooner or later. On-device AI refers back to the majority of AI operations being executed on edge units, connecting to the cloud selectively. “As AI functions enhance, cloud operational prices stay a problem, and challenges like information latency and safety persist. The time period ‘on-device AI’ will grow to be outstanding, and Samsung’s objective is to put a robust machine, akin to a supercomputer, in everybody’s palms, enabling them to make use of generative AI anytime,” he emphasised.


Relating to Samsung Electronics’ upcoming challenges, Park acknowledged, “Within the visible area, we goal to develop cameras that may seize what’s unseen by 2027. Within the olfactory and auditory domains, many sensors and algorithms can be crucial. The primary problem for the semiconductor division can be designing cellular units whereas minimizing energy consumption and warmth technology.”

Source link

dutchieetech.com
  • Website

Related Posts

Intel simply up to date us on sport crashes, and it’s not trying good

21 June 2024

Intel Publishes Steerage For Crashing Core I9 Processors, ETVB Bugfix On The Approach – Pokde.Internet

21 June 2024

Linux 6.10 Fixes AMD Zen 5 CPU Frequency Reporting With cpupower

6 June 2024

Intel Unveils Core Extremely Processor with Built-in AI Capabilities

6 June 2024

AORUS Tachyon, AORUS Master, AORUS Ultra, AORUS Elite, AERO G

6 June 2024

Intel particulars its Lunar Lake structure with spectacular enhancements

4 June 2024
Leave A Reply Cancel Reply

You must be logged in to post a comment.

Legal Pages
  • Disclaimer
  • Privacy Policy
  • About Us
  • Contact Us

Type above and press Enter to search. Press Esc to cancel.