Salishan 2026 Theme
"Curiouser and Curiouser: Charting the HPC Future"
Who in the world am I? Ah, that's the great puzzle!
— Lewis Carroll, Alice in Wonderland
High Performance Computing (HPC) stands at an intersection as the landscape grows ever more complex and unpredictable. As we peer into the future, the path forward is anything but clear. The rapid evolution of hardware—fueled by the demands of artificial intelligence, machine learning, and emerging
technologies—has outpaced our ability to adapt codes and software stacks, leaving many teams grappling with porting challenges and integration hurdles. The requirements of scientific modeling and simulation can diverge from those of industry, and the solutions that propel commercial machine learning
may not fit the unique needs of our mission and science applications.
Like Alice, we find ourselves stepping through a looking-glass where familiar logic twists and the paths ahead shimmer with both promise and peril. Will we follow the well-worn trail of incremental hardware upgrades, or chart a new course into unknown territory? Can we harness agentic workflows, federated learning, and emergent methods as compasses toward our scientific mission? Might AI-driven code optimization and other strategies become the magical keys that keep us in step with hardware’s relentless advance? What wisdom lurks in the experiences of industry, academia, and our own labs to
guide us when the computational terrain beneath us is forever shifting?
Throughout the week, we invite the community to embrace curiosity and adventure as we navigate the terrain of heterogeneity, integration, and innovation. Our sessions will be inspired by the spirit of Wonderland:
Who in the world am I? Ah, that's the great puzzle!
— Lewis Carroll, Alice in Wonderland
High Performance Computing (HPC) stands at an intersection as the landscape grows ever more complex and unpredictable. As we peer into the future, the path forward is anything but clear. The rapid evolution of hardware—fueled by the demands of artificial intelligence, machine learning, and emerging
technologies—has outpaced our ability to adapt codes and software stacks, leaving many teams grappling with porting challenges and integration hurdles. The requirements of scientific modeling and simulation can diverge from those of industry, and the solutions that propel commercial machine learning
may not fit the unique needs of our mission and science applications.
Like Alice, we find ourselves stepping through a looking-glass where familiar logic twists and the paths ahead shimmer with both promise and peril. Will we follow the well-worn trail of incremental hardware upgrades, or chart a new course into unknown territory? Can we harness agentic workflows, federated learning, and emergent methods as compasses toward our scientific mission? Might AI-driven code optimization and other strategies become the magical keys that keep us in step with hardware’s relentless advance? What wisdom lurks in the experiences of industry, academia, and our own labs to
guide us when the computational terrain beneath us is forever shifting?
Throughout the week, we invite the community to embrace curiosity and adventure as we navigate the terrain of heterogeneity, integration, and innovation. Our sessions will be inspired by the spirit of Wonderland:
- "Why, sometimes I've believed as many as six impossible things before breakfast."
Software as the Thread/Science/Mission/Product/Deliverable/Workhorse: Exploring how software strategies and tools can keep pace with hardware advances and continue to enable mission success. - "It's no use going back to yesterday, because I was a different person then."
AI and Agentic Workflows: Examining how artificial intelligence and agentic methods are reshaping scientific workflows, deployment models, and applications. - “What a curious plan!”
Emerging Technologies: Investigating the breakthroughs and challenges brought by quantum computing and other transformative technologies. - “We’re all mad here”
Applications of the Future: Describing key scientific challenges on the horizon and how those challenges are driving innovation in supercomputing systems. - “Would you tell me, please, which way I ought to go from here?”
Navigating Uncertainty: A panel exploring decision-making and strategy in a world where the right road is never obvious.