Samsung Develops Industry’s First High Bandwidth Memory with AI Processing Power
17.2.2021 13:00:00 EET | Business Wire | Press release
Samsung Electronics Co., Ltd., the world leader in advanced memory technology, today announced that it has developed the industry's first High Bandwidth Memory (HBM) integrated with artificial intelligence (AI) processing power — the HBM-PIM. The new processing-in-memory (PIM) architecture brings powerful AI computing capabilities inside high-performance memory, to accelerate large-scale processing in data centers, high performance computing (HPC) systems and AI-enabled mobile applications.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20210217005384/en/
Samsung's HBM-PIM with AI processing power (Photo: Business Wire)
Kwangil Park, senior vice president of Memory Product Planning at Samsung Electronics stated, "Our groundbreaking HBM-PIM is the industry's first programmable PIM solution tailored for diverse AI-driven workloads such as HPC, training and inference. We plan to build upon this breakthrough by further collaborating with AI solution providers for even more advanced PIM-powered applications."
Rick Stevens, Argonne’s Associate Laboratory Director for Computing, Environment and Life Sciences commented, “I’m delighted to see that Samsung is addressing the memory bandwidth/power challenges for HPC and AI computing. HBM-PIM design has demonstrated impressive performance and power gains on important classes of AI applications, so we look forward to working together to evaluate its performance on additional problems of interest to Argonne National Laboratory.”
Most of today's computing systems are based on the von Neumann architecture, which uses separate processor and memory units to carry out millions of intricate data processing tasks. This sequential processing approach requires data to constantly move back and forth, resulting in a system-slowing bottleneck especially when handling ever-increasing volumes of data.
Instead, the HBM-PIM brings processing power directly to where the data is stored by placing a DRAM-optimized AI engine inside each memory bank — a storage sub-unit — enabling parallel processing and minimizing data movement. When applied to Samsung's existing HBM2 Aquabolt solution, the new architecture is able to deliver over twice the system performance while reducing energy consumption by more than 70%. The HBM-PIM also does not require any hardware or software changes, allowing faster integration into existing systems.
Samsung’s paper on the HBM-PIM has been selected for presentation at the renowned International Solid-State Circuits Virtual Conference (ISSCC) held through Feb. 22. Samsung’s HBM-PIM is now being tested inside AI accelerators by leading AI solution partners, with all validations expected to be completed within the first half of this year.
###
About Samsung Electronics Co., Ltd.
Samsung inspires the world and shapes the future with transformative ideas and technologies. The company is redefining the worlds of TVs, smartphones, wearable devices, tablets, digital appliances, network systems, and memory, system LSI, foundry and LED solutions. For the latest news, please visit the Samsung Newsroom at http://news.samsung.com.
To view this piece of content from cts.businesswire.com, please give your consent at the top of this page.
View source version on businesswire.com: https://www.businesswire.com/news/home/20210217005384/en/
Contact information
Ujeong Jahnke
Samsung Semiconductor Europe GmbH
Tel. +49(0)89-45578-1000
Email: sseg.comm@samsung.com
About Business Wire
For more than 50 years, Business Wire has been the global leader in press release distribution and regulatory disclosure.
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
Beacon Acquires Haize Labs to Power AI for the Real Economy17.9.2026 17:30:00 EEST | Press release
Beacon Software (Beacon), the first centralized AI holding company, today announced that it has acquired Haize Labs, an AI reliability company that tests and safeguards AI agents for real-world deployment. The Haize Labs team will join Beacon to form its Applied AI Research Group, with co-founder and CEO Leonard Tang joining as VP of AI Research to lead the AI operating system that is deployed across Beacon’s companies. Beacon believes that the fastest way to bring AI to the traditional economy is through the software businesses that essential industries already use and trust, equipping them with AI infrastructure. Beacon acquires these businesses for long-term growth and connects them to a centralized AI operating system that compounds with each additional acquisition and industry. The addition of the Haize Labs team will strengthen this centralized technology platform, which provides shared engineering, AI, product and go-to-market capabilities to Beacon’s portfolio of 45 software co
TIMELAB Develops OEM/ODM Hair Straightener Reaching 200°C at All Three Measured Points in 15 Seconds17.9.2026 17:00:00 EEST | Press release
TIMELAB Co., Ltd., a Japanese beauty-appliance OEM/ODM provider, has developed a hair straightener for OEM/ODM customization for international hair care brands and professional markets. In testing at 230 V with a 260°C setting, all three measured plate locations reached at least 200°C after 15 seconds. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260914187865/en/ Three-Point Plate Testing A European-market development unit with a maximum setting of 260°C was tested at 230 V. Fifteen seconds after power-on, readings at the front, center and rear were 212.5°C, 227.5°C and 200.0°C, respectively. From around 60 seconds onward, temperature differences among the three points narrowed, indicating a stable trend. Precision Temperature Control An NTC sensor inside the metal ceramic heater (MCH) detects temperature. A microcontroller (MCU) reads the signal and adjusts heater output. Upper and lower MCH heaters are controlled indepen
Earnix Brings Agentic AI to the Decisions That Drive Insurance Performance17.9.2026 16:09:00 EEST | Press release
Earnix today announced the introduction of Agent Hub, a curated catalog of insurance-specific AI agents and apps within Earnix AIOS — the AI Orchestration System powering Earnix’s pricing and rating, underwriting, and customer engagement solutions. Agent Hub brings agentic AI directly into these solutions, enabling more intelligent workflows and strengthening the high-stakes decisions that shape pricing, underwriting, customer engagement, growth, and profitability. In an increasingly turbulent insurance environment, the useful life of an insurance decision is getting shorter. Risk and market conditions are changing faster, making growth, profitability, and portfolio performance harder to manage. AI is increasing the speed and scope of what insurers can analyze, recommend, and increasingly act on — but as intelligence moves closer to action, the standard for governance, explainability, and accountability also rises. For insurers, that shift has direct implications for both financial per
Medisca Launches Global Peptide Division17.9.2026 16:07:00 EEST | Press release
Medisca today announced the launch of Medisca Peptides, a dedicated global division focused on expanding access to API-grade peptides and building an integrated peptide platform for pharmaceutical and personalized medicine markets worldwide. As the peptide landscape evolves, Medisca is proactively building the capabilities and infrastructure needed to support API-grade peptides within applicable regulatory frameworks. The launch represents a significant long-term commitment to peptides, including the expansion of Medisca’s portfolio, strategic manufacturing relationships, and the pharmaceutical infrastructure needed to support the category’s growth. It also signals Medisca’s ambition to become a leading force in the next generation of peptide innovation. For Medisca, the opportunity is familiar. More than 35 years ago, the company was founded to help close the gap between the pharmaceutical standards compounders needed and the quality ingredients they could readily access. Today, as pe
Elliptic Launches Its Decode Agent to Answer On-Chain Risk Questions and Shows Its Work17.9.2026 16:00:00 EEST | Press release
Elliptic, the global leader in on-chain risk, today launched Decode, an AI agent built on Elliptic’s intelligence platform. The Decode agent answers natural-language questions about cryptoasset addresses and their exposure in seconds, and returns the evidence behind every answer. Compliance and investigations teams need answers to questions nobody planned for. Getting them out of the data is now a specialist skill, so the questions wait for someone who has it, or go unasked. Meanwhile illicit actors move at machine speed, and agents are starting to sit on both sides of a payment. General-purpose AI assistants can produce an answer. They cannot show where it came from. A fluent response with nothing behind it cannot be put in front of a second-line reviewer, an auditor, or a regulator. “The market is full of AI that asks to be trusted. That is not good enough when someone asks how you reached a decision,” said Jackson Hull, CTO at Elliptic. “We published the Elliptic Standard last week
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom