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
FlightSafety International Receives FAA Approval for Virtual Aircraft Preflight Inspection with Evaluation Mode6.5.2026 17:05:00 EEST | Press release
FlightSafety International Inc., the global leader in aviation training and simulation technology, today announced it has received Federal Aviation Administration (FAA) approval for Virtual Aircraft Preflight Inspection (VAPI) with Evaluation Mode for three aircraft training programs: the Embraer EMB-550, Gulfstream G500/G600, and Citation Latitude. This innovative capability allows pilots in initial training to complete a 3D virtual aircraft preflight inspection while in Training Mode, with the added ability to transition directly into the flight deck, followed by Evaluation Mode, that allows pilots to do their preflight check ride portion. “VAPI represents a meaningful advancement in training innovation,” said David Penney, VP of Safety, Courseware and Regulatory Affairs, FlightSafety International. “By leveraging an immersive 3D environment, it offers pilots a more engaging and practical way to develop aircraft familiarity, strengthen inspection discipline, and better prepare for re
Riskified Unveils Next-Generation AI Suite at Ascend 2026, Empowering Merchants with Unprecedented Visibility and Control Over Ecommerce Risk6.5.2026 16:00:00 EEST | Press release
Riskified (NYSE: RSKD), a global leader in ecommerce fraud and risk intelligence, today announced a major leap forward in its AI platform capabilities, introducing a powerful suite of control and empowerment tools designed to give merchant fraud teams complete visibility into risk patterns and identity behavior, conversational AI-driven insights, and the ability to surgically tailor their risk strategies. The innovation suite was announced onstage at Ascend 2026, Riskified’s premier global summit series, taking place May 4-6, 2026, at the Conrad New York Downtown in Manhattan, NY. With global ecommerce continuing to expand and losses from AI-driven fraud attacks projected to spike, particularly with the rise of agentic commerce, where AI bots may conduct transactions on behalf of consumers, accurate fraud decisions are fundamental, but are no longer enough. Today, more than ever, sophisticated fraud and risk teams need to understand the why behind every transaction and pattern, and req
Twilio’s Next Generation Platform: An Infrastructure Layer for Every Conversation in the Agentic Era6.5.2026 16:00:00 EEST | Press release
Twilio (NYSE: TWLO), the infrastructure for customer engagement in the AI era, kicked off its user conference, SIGNAL, by unveiling its next generation platform capabilities for the agentic era. Generally available today, Conversation Memory, Conversation Orchestrator, Conversation Intelligence, and Agent Connect combine to turn disparate interactions into continuous, intelligent, and personal conversations across humans, agents, and systems. “The agentic era is here. Agents are joining conversations alongside the people they represent, and modern customer engagement requires an infrastructure that serves both equally,” said Khozema Shipchandler, Chief Executive Officer at Twilio. “Twilio’s new platform is the foundational infrastructure layer that makes every conversation persistent, contextual, and actionable – ensuring interactions feel like part of one continuous relationship." An Infrastructure Layer for Every Conversation Every business runs on conversations. Today, however, busi
Vultr, SUSE & Supermicro Debut Unified Cloud-to-Edge Architecture for Global AI Scaling6.5.2026 15:00:00 EEST | Press release
Vultr, the world's largest privately-held cloud infrastructure company, in collaboration with SUSE and Supermicro, today announces a strategic architectural framework designed to solve the complexities of deploying and operating AI workloads across distributed environments. As AI moves closer to the point of data creation - from manufacturing floors to retail storefronts - organizations face significant challenges in latency, cost and operational consistency. This joint initiative provides a seamless, Cloud-to-Edge pipeline that integrates high-performance hardware, localized cloud infrastructure, and unified Kubernetes management. The partnership addresses the reality that sending all data back to a central cloud is no longer viable for real-time AI. The solution breaks down the infrastructure into three critical layers: The Cloud and Near-Edge - Enterprises can deploy regional Kubernetes-based AI clusters closer to their users by leveraging Vultr’s 33 global cloud data center regions
Waiv Enters Collaboration with Daiichi Sankyo to Deliver AI-Derived Biomarkers for ADC Program6.5.2026 15:00:00 EEST | Press release
Waiv, formerly Owkin Dx, a Paris-based company catalyzing AI precision testing, today announced it has entered a collaboration with Daiichi Sankyo (TSE: 4568) to lead digital pathology biomarker discovery for an antibody-drug conjugate (ADC) program. With deep expertise across diverse pathology and multimodal data, and a global data network spanning academic institutions, hospitals, and laboratories, Waiv has a proven track record delivering AI-powered biomarker solutions across the full drug development lifecycle. Under the collaboration, Waiv will apply its end-to-end computational pathology platform to early phase data. This includes tumor microenvironment (TME) analysis across both hematoxylin and eosin (H&E) and immunohistochemistry (IHC) stained samples, as well as biomarker discovery and outcome prediction capabilities aimed at identifying biomarkers of treatment response ahead of next clinical trial phases. Purpose-built AI approach tackles one of pharma's hardest challenges: b
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