Founded Year

1945

About IBM Research

IBM Research specializes in the advancement of artificial intelligence, quantum computing, and hybrid cloud technologies within the research and development sector. The company focuses on creating solutions and tools that address complex challenges in these areas, including the development of AI chips, quantum computers, and cloud infrastructure. IBM Research provides open-source models and datasets to facilitate enterprise AI and scientific discovery, contributing to the broader technology and research community. It was founded in 1945 and is based in Armonk, New York. IBM Research operates as a subsidiary of IBM.

Headquarters Location

1 New Orchard Road

Armonk, New York, 10504,

United States

800-426-4968

Loading...

Loading...

Expert Collections containing IBM Research

Expert Collections are analyst-curated lists that highlight the companies you need to know in the most important technology spaces.

IBM Research is included in 1 Expert Collection, including Semiconductors, Chips, and Advanced Electronics.

S

Semiconductors, Chips, and Advanced Electronics

7,328 items

Companies in the semiconductors & HPC space, including integrated device manufacturers (IDMs), fabless firms, semiconductor production equipment manufacturers, electronic design automation (EDA), advanced semiconductor material companies, and more

Latest IBM Research News

GPU Analysis Identifying Performance Bottlenecks That Cause Throughput Plateaus In Large-Batch Inference

Mar 30, 2025

A new technical paper titled “Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference” was published by researchers at Barcelona Supercomputing Center, Universitat Politecnica de Catalunya, and IBM Research. Abstract “Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, performance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new insights and practical strategies for improving resource utilization, particularly for smaller language models.” Recasens, Pol G., Ferran Agullo, Yue Zhu, Chen Wang, Eun Kyung Lee, Olivier Tardieu, Jordi Torres, and Josep Ll Berral. “Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference.” arXiv preprint arXiv:2503.08311 (2025).

IBM Research Frequently Asked Questions (FAQ)

  • When was IBM Research founded?

    IBM Research was founded in 1945.

  • Where is IBM Research's headquarters?

    IBM Research's headquarters is located at 1 New Orchard Road, Armonk.

  • Who are IBM Research's competitors?

    Competitors of IBM Research include Cohere, Groq, Tenstorrent, QpiAI, ValidMind and 7 more.

Loading...

Compare IBM Research to Competitors

Lightmatter Logo
Lightmatter

Lightmatter is a company that works in silicon photonics within the computing and semiconductor industries. It develops photonic computing solutions aimed at supporting artificial intelligence infrastructure and promoting industry collaboration through standardization efforts. The company's products serve to improve digital data processing and interconnectivity in AI applications. It was founded in 2017 and is based in Mountain View, California.

Untether AI Logo
Untether AI

Untether AI focuses on the development of high-performance AI chips operating within the technology and artificial intelligence sectors. The company's main offerings include ultra-efficient AI chips that are designed to enhance the performance of AI applications by eliminating data movement bottlenecks, thus enabling faster, cooler, and more cost-effective operation of AI inference workloads. Untether AI primarily serves the technology and artificial intelligence industries. It was founded in 2018 and is based in Toronto, Canada.

Cerebras Logo
Cerebras

Cerebras focuses on artificial intelligence (AI) acceleration through its development of wafer-scale processors and supercomputers for different sectors. The company provides computing solutions that support deep learning, natural language processing, and other AI workloads. Cerebras serves industries including healthcare, scientific computing, and financial services with its AI supercomputers and model training services. It was founded in 2016 and is based in Sunnyvale, California.

BITMAIN Logo
BITMAIN

BITMAIN manufactures the digital currency mining sector, specializing in mining servers. The company offers technology power efficiency and provides computational infrastructure solutions to the global blockchain network. It primarily serves the cryptocurrency mining industry. It was founded in 2013 and is based in Beijing, China.

Mythic Logo
Mythic

Mythic is an analog computing company that specializes in AI acceleration technology. Its products include the M1076 Analog Matrix Processor and M.2 key cards, which provide power-efficient AI inference for edge devices and servers. Mythic primarily serves sectors that require real-time analytics and data throughput, such as smarter cities and spaces, drones and aerospace, and AR/VR applications. Mythic was formerly known as Isocline Engineering. It was founded in 2012 and is based in Austin, Texas.

Another Brain Logo
Another Brain

Another Brain operates as a company focusing on the development of artificial intelligence (AI) technologies. It specializes in the development of Organic AI, a new generation of artificial intelligence technology within the AI industry. The company offers a vision quality control solution called Blue Phosphor that uses AI algorithms for intelligent defect detection in industrial supply chains. It was founded in 2017 and is based in Paris, France.

Loading...

CBI websites generally use certain cookies to enable better interactions with our sites and services. Use of these cookies, which may be stored on your device, permits us to improve and customize your experience. You can read more about your cookie choices at our privacy policy here. By continuing to use this site you are consenting to these choices.