Sponsors
MIMOS





ATL Website
miacclib





Visitors


 

About GPU R&D AND COMPUTE SOLUTION CENTER

The first in South East Asia, GPU Solution Center in Malaysia is a unique collaborative environment between NVIDIA, HP, MIMOS and key software vendors, that serves to display and share the latest GPU technologies together with GPU enabled applications such as SolidWorks, Autodesk 3ds Max, ANSYS, Abaqus, Adobe CS6, and others.

Besides latest GPU application showcasing, this center also caters for various GPU related R&D activities such as GPU Accelerator Libraries Development, GPGPU enabled Application Specific/Generic Algorithm R&D, GPGPU application benchmark & testing.

The Center helps promote the dynamic growth of GPU Computing in Malaysia through collaborative university research projects, CUDA teaching center formation at universities, annual GPGPU workshop, annual CUDA programming contest, technology road shows, various Government & private entity visits hosting and other GPU related activities.

GPU R&D and Compute Solution Center Objectives:

  • To facilitate adaptation of many-core/parallel/GPU techniques in scientific, financial, big data processing areas
  • To enhance GPU related R&D activities in Malaysia
  • To serve as a one-stop center to promote, share & teach GPU technologies/solutions to customers and those interested in GPGPU, and to do joint collaborations on GPU topics

Vision

  • To set GPU R&D and Compute Solution Centre as a Center of Excellence for pioneering work in parallel computing research in South East Asia using accelerated technology and GPUs utilizing integrated compute solution platforms
  • To embark on research projects and education activities for the continued interest and benefits in massively parallel computing and NVIDIA, HP, and MIMOS technology
  • To promote interests in taking GPU-based solutions to indigenous local industries

Mission

  • To conduct research and development on the use of GPU personal supercomputing platforms as well as GPU-enhanced multi/many-cores platforms
  • To engage in a number of research, development and educational activities (e.g., applications, software development tools, system software and architectures) that leverage heterogeneous & scalable computing
  • To provide expertise, information, guidance and tools for affiliate members to engage in GPU & Compute-related projects
  • To be at the forefront of computing technology for developing state-of-the-art computational algorithms that drive innovation in the industrial application, sciences and engineering
  • To promote participation of Affiliated members to be involved in GPU-related activities by cross-fertilizing ideas and skills, by sharing software and hardware facilities, leveraging training materials and efforts, and by streamlining interactions with closer, priority access to NVIDIA/HP staff and capabilities
 

About Accelerative Technology Lab (ATL)

Accelerative Technology Lab is established as part of ICT Division at MIMOS. Currently, the lab is focused on research and development in four areas:

  • Many-core Computing
  • AV & Image Data Processing
  • Large Data Processing
  • Middleware & Framework

The lab drives key R&D activities leading to on time project delivery which was later taken-up by other software development team within MIMOS and also external companies (Technology Recipients) as part of software platform for commercialization purposes. The “GPU R&D and Compute Solution Center” was also established under the lab, jointly funded and governed by Nvidia, HP and MIMOS, serving as the center of GPGPU related R&D activities by collaborating with international companies, universities and industry partners.

The lab has successfully delivered key technologies including the MIMOS Accelerated Library (Mi-AccLib) library which enables computational accelerations for niche applications and markets. These include computational finance, text processing & analytics, and In-memory Database operations. Recently, the library has been officially listed as one of the most popular GPU-accelerated applications by NVIDIA. Further information about projects undertaken in ATL can be found here.