by Roy Kim

Watching the session “Application of Tesla C2050 to Flow Cytometry and Cancer Detection,” led by Bob Zigon, of Beckman Coulter, I got thinking: How many problems could we begin solving if we had access to an infinite amount of computation capacity? 

Zigon’s product, Kaluza, enables doctors to detect cells in the body that aren’t functioning correctly, typically cancer cells.  Powered by Tesla GPUs,  Kaluza can run 400x faster than a CPU-only based solution, enabling doctors to look for cancer cells in real-time with more accuracy and data from each cell. 

“Results from our product will lead to better diagnostics for detecting leukemia in blood cells,” said Zigon, rather humbly. 

He and his team use lasers to analyze cells. Through light diffraction, Kaluza can measure attributes of the cells, their internal and external characteristics, and, more importantly, the presence and absence of certain proteins.  With Tesla GPUs, Kaluza has vastly greater, faster visibility into each cell.  Why does this matter?  Well, I’ll answer that with a question:  How would it change your life, or lives of people you love, if you could just walk into a doctor’s office, get a quick screen for cancerous cells, and walk away knowing the results?

Zigon's final, somewhat indirect, request to NVIDIA was to “just build hardware that is infinitely fast and let me look at every cell.”  His dream is that infinitely capable computers will detect all cancer cells in every human being on earth, before these cells become dangerous. 

While GPUs aren’t infinitely fast, (and never will be), they are enabling some amazing work.  And I’m glad to be part of the solution.