Flow Computing Podcast Series: Prof. Dr. Jörg Keller on PPU Technology (Episode 2: Performance Gains)

In Episode 2 of our Flow Computing podcast series, Prof. Dr. Jörg Keller explores the performance benefits of the PPU, specifically focusing on how it enhances both newly developed and legacy software. He emphasizes the crucial role of source code availability in unlocking the PPU's full potential.

For new software designed with the PPU in mind, the performance gains are substantial. The PPU's compiler can automatically detect opportunities for parallelization and translate them into highly efficient executable code. Developers can further fine-tune the source code for even greater performance improvements.

"If we have original code, this allows programmers to recompile with a compiler that is aware of Flow technology. So the compiler can detect all possibilities for performance improvements and turn them automatically into executable code." - Prof. Dr. Jörg Keller

Transcript

JÖRG KELLER: If we have original code, this allows programmers to recompile with a compiler that is aware of Flow technology. So the compiler can detect all possibilities for performance improvements and turn them automatically into executable code.

JK: The programmer naturally also can fine tune the source code with additional time effort.

JK: If we don't have the source code, we can still use a binary to binary translator that searches the original executable for code patterns that can be transformed into faster code when we have the PPU cores. A further benefit for these legacy codes can be obtained if operating system or programming system libraries can be recompiled for Flow computing, then those will run faster on the PPU’s course, even if the application code itself is unmodified and just calls the improved libraries.

Interested in a deeper dive into Flow Computing's PPU technology?

If you'd like to explore the technical details and insights from Professor Keller's due diligence, you can request access to the full report. Simply contact us at info@flow-computing.com, and we'll be happy to send it your way!