Tokyo, November 9, 2023
Fujitsu today announced the development of the world’s first technology to optimize the use of CPUs and GPUs by allocating resources in real time to prioritize processes with high execution efficiency, even when running programs that use GPUs . Fujitsu designed the new technology to address the global shortage of GPUs due to the explosive demand for generative AI, deep learning and other applications by optimizing users’ existing computing resources.
Fujitsu has also developed a new technology for parallel processing that switches the processing of multiple programs in real time without waiting for the completion of a running program in an HPC system that performs large-scale calculations by connecting multiple computers. This technology makes it possible to immediately perform the processing of applications that require large computational resources and real-time performance, such as digital twins and generative AI programs.
Fujitsu will provide the newly developed technology as part of a future computing workload broker, a software initiative currently under development that enables AI to automatically calculate and select the most appropriate resource for a problem that customers want to solve according to with their requirements, including computation time, computation accuracy, and cost, and will continue to validate this technology with customers to realize a platform that can solve societal problems and create innovation to achieve a sustainable future.
Fujitsu will demonstrate these technologies at SC23, which will be held at the Colorado Convention Center in Denver, Colorado, starting Sunday, November 12, 2023, with the HPC technology featured in the Research Posters program.
Features of new technology
1. World’s first technology to use CPU and GPU even during program processing
Fujitsu has developed the world’s first technology to distinguish between applications that require a GPU and those that can be processed by a CPU, even when multiple applications are being processed, by predicting the acceleration rate and by allocating GPUs in real-time for high-priority application processing .
For example, as shown in Figure 1, if the user wants to process three programs efficiently using one CPU and two GPUs, it is possible to assign GPUs to programs 1 and 2 according to the availability of GPU’ is. Then, in response to the request of program 3, the GPU allocation is changed from program 1 to program 3 for performance measurement, and the degree of processing acceleration on the GPU is measured. As a result of the measurement, it is found that the total processing time would be reduced by allocating the GPU to program 3 instead of to program 1. Therefore, the GPU would be allocated to program 3 and the CPU would be allocated to program 1 during that time. After program 2 is finished, the GPU becomes free, so the GPU is allocated to program 1 again, thus allocating the computational resources so that the program processing is completed in the shortest time.
This technology makes it possible to quickly train models to process graphical AI data in the development of applications such as AI using GPUs and advanced image recognition.
2. The world’s first technology for real-time switching of execution of multiple programs on an HPC system
Fujitsu has developed the world’s first technology for real-time switching between multiple programs that can be used without waiting for the current program to finish in an HPC system that connects multiple computers, making it possible to use HPC systems to perform applications that require real-time performance.
Because the conventional control method uses unicast communication, which switches program execution to each server one by one, variations in switching timing occur, making it difficult to perform batch switching of program execution in real time. By using broadcast communication that can be sent concurrently with the communication that switches program execution, Fujitsu has enabled real-time batch switching of program execution by reducing the interval between program processing switches that affect program performance from a few seconds to 100 milliseconds on 256-node HPC -environment. Since the appropriate communication method depends on application requirements and network quality, the optimal communication method can be selected considering the degree of performance improvement due to broadcast communication and performance degradation due to packet loss.
This technology enables applications that require real-time performance for digital twins, generative AI, and material and drug discovery to be executed faster using HPC-like computational resources.
In the future, Fujitsu plans to use the CPU/GPU resource optimization technology for processing that requires GPUs for its Fujitsu Kozuchi (codename) – AI Platform, which allows users to rapidly test advanced AI technologies. The HPC optimization technology will also be applied to Fujitsu’s 40 qubit quantum computer simulator for collaborative computing using a large number of nodes.
Fujitsu will also consider applications for Fujitsu Computing as a Service HPC, which allows users to develop and execute applications for simulation, AI and combinatorial optimization problems, as well as the Composable Disaggregated Infrastructure (CDI) architecture, a technology that allows changing hardware configurations among servers in an effort to create a society where everyone can easily access cost-effective, high-performance computing resources.
Fujitsu’s commitment to the Sustainable Development Goals (SDGs)
The Sustainable Development Goals (SDGs), adopted by the United Nations in 2015, represent a set of shared goals to be achieved worldwide by 2030.
Fujitsu’s purpose – “to make the world more sustainable by building trust in society through innovation” – is a pledge to contribute to the vision of a better future, mandated by the SDGs.
Fujitsu’s purpose is to make the world more sustainable by creating trust in society through innovation. As the digital transformation partner of choice for customers in over 100 countries, our 124,000 employees work to solve some of the biggest challenges facing humanity. Our range of services and solutions draw on five key technologies: Computing, Networks, AI, Data & Security and Converging Technologies, which we bring together to deliver sustainability transformation. Fujitsu Limited (TSE:6702) reported consolidated revenue of 3.7 trillion yen ($28 billion) for the fiscal year ending March 31, 2023, and remains the largest digital services company in Japan by market share. Find out more: www.fujitsu.com.
Public and Investor Relations Division
All company or product names mentioned herein are trademarks or registered trademarks of their respective owners. The information in this press release is accurate at the time of publication and is subject to change without notice.
Date: November 9, 2023
Town: Tokyo, Japan
Company: Fujitsu Limited