Samsung Electronics Unveils Exynos 2100: "On Level with Qualcomm This Time?"
Published2021.01.14 11:0520% improvement in power consumption through 5nm EUV process production
Exynos to feature AMD GPUs instead of Arm starting next year
On the 12th, Samsung Electronics unveiled the 'Exynos 2100' AP, which is produced using the 5nm (nanometer) EUV process.
.jpg)
Introducing the Exynos 2100 [Photo = Samsung Electronics]
According to Samsung Electronics, the Exynos 2100 features 30% and 40% improvements in CPU and GPU performance, respectively, and enhanced on-device AI capabilities. Additionally, it is the first Samsung premium mobile AP to integrate a 5G modem.
The Exynos 2100 is designed with a Tri-Cluster architecture featuring one 2.9GHz Arm 'Cortex-X1', three 'Cortex-A78', and four 'Cortex-A55' cores. It is equipped with an Arm Mali-G78 GPU.
AI computing performance of over 26 TOPS (26 trillion operations per second) has also been secured through the inclusion of 3 NPU cores and an acceleration function design that eliminates unnecessary computations. It enables high-level AI computation on the terminal itself without data exchange with a central cloud server, allowing the use of AI services even in situations without a network.
The built-in 5G modem supports both low frequency (Sub-6GHz) and high frequency (mmWave) bands, and the high-performance Image Signal Processor (ISP), capable of processing up to 200-megapixel images, can connect up to 6 image sensors and drive 4 image sensors simultaneously.
It is manufactured using a 5nm EUV process, which improves power consumption by 20% compared to products manufactured using a 7nm process, and by incorporating AMIGO (Advanced Multi-IP Governor), a proprietary solution that optimizes power efficiency, it reduces the burden of battery drain when running high-definition, high-spec games and programs.
Qualcomm, a dominant player in the mobile AP market, unveiled the 'Snapdragon 888' last December. The Exynos 2100 and Snapdragon 888 adopt the same CPU model and architecture. However, there is a difference in the GPUs: Arm Mali-G78 (Samsung Electronics) and Qualcomm 'Adreno 660' (Qualcomm).
The industry views Adreno's performance as superior to Mali's. Kim Kyung-joon, Vice President of Samsung Electronics' Mobile Communications Business, stated, "The Exynos to be released next year will be equipped with a GPU based on AMD's 'Radeon DNA' architecture." Samsung Electronics and AMD announced a collaboration in the GPU sector in June 2019.
Samsung Electronics is currently mass-producing the Exynos 2100. The Snapdragon 888 is also being produced at Samsung Electronics' foundry.
관련뉴스
Palo Alto Launches Cloud-Native Security Platform
Prisma Cloud secures multi-cloud and hybrid cloud environments and cloud-native applications by integrating security throughout the entire DevOps lifecycle. The new product integrates the technology of Aporeto, a micro-segmentation specialist company acquired last year, into the existing Palo Alto Networks Prisma Cloud platform.
2020.10.29by 김동우 기자
Telechips Adopts Arm IP Supporting 'Functional Safety' for Automotive APs
Telechips has adopted an Arm Cortex-A76 CPU supporting automotive digital cockpit, an Arm Mali-G78AE GPU providing functional safety by supporting up to four fully independent partitions, and an Arm Ethos-N78 NPU dedicated to machine learning in its next-generation automotive AP, Dolphin 5.
2020.12.15by 명세환 기자
[Interview] "HPC Needs an Integrated, Heterogeneous Programming Environment"
Heterogeneous systems with multiple types of processors such as CPUs, GPUs, and FPGAs simultaneously mounted are widely utilized in the HPC field, but implementation is challenging due to fragmented programming environments. By leveraging a unified programming environment such as Intel's oneAPI, it becomes convenient to write code with improved code portability and performance portability across different processors.
2020.12.24by 이수민 기자
ST Microelectronics and NUS Establish Joint Research Center 'HELIX' for Edge AI
ST Microelectronics and the National University of Singapore have established the 'HELIX' joint research center aimed at implementing embedded AI in edge environments. Over a four-year period, the center will conduct research across the entire technology stack from algorithms to silicon, focusing on memory-centric architecture leveraging ST's 18nm FD-SOI technology and embedded PCM. The core objective is to implement intelligence directly in physical devices such as robots and drones while minimizing energy consumption.
2026.08.28by 배종인 기자
ams, 디지털 포토닉스로 휴머노이드 로봇 감각·소통 기능 지원
ams OSRAM이 디지털 포토닉스 기술을 활용해 휴머노이드 로봇의 감각·소통 기능을 강화하는 솔루션을 공개했다. dToF 센서, 광학식 힘 센서, 구조광 이미터 등으로 주변 환경 인식과 정밀 조작을 구현하며, EVIYOS·ALIYOS 플랫폼으로 LED 기반 비언어 소통을 지원한다. 시장조사에 따르면 휴머노이드 로봇 시장은 2025년 6억 달러에서 2035년 510억 달러로 성장할 전망이며, 로봇의 감각 능력 향상이 핵심 성장 동인으로 작용할 것으로 예상된다.
2026.08.27by 배종인 기자
