Topic Guide
What Is Accelerated computing?
Accelerated computing is a subject covered in depth across 1 podcast episode in our database. Below you'll find key concepts, expert insights, and the top episodes to listen to — all distilled from hours of conversation by leading experts.
What Experts Say About Accelerated computing
- 1.NVIDIA has transitioned to "extreme co-design" across the entire computing stack, from individual components like GPUs and CPUs to full data center infrastructure, to solve complex distributed problems that no longer fit a single computer.
- 2.The necessity for extreme co-design arises from the goal to achieve speedups "a million times faster" than simply increasing the number of computers, requiring intricate sharding of algorithms, data, and models.
- 3.Jensen Huang leads with a unique organizational structure where a large staff of 60+ technical experts collaborates in group settings, allowing for a comprehensive, cross-disciplinary approach to problem-solving inherent to co-design.
- 4.A crucial strategic decision for NVIDIA was embedding CUDA into GeForce GPUs, despite incurring significant costs that severely impacted profitability and temporarily reduced the company's market cap, to establish a vital developer "install base" which ultimately powered the deep learning revolution.
- 5.Huang believes that the "install base defines an architecture" more than its elegance, illustrating this with the success of x86 versus more elegantly designed RISC architectures.
- 6.Jensen Huang's leadership strategy for bold bets involves intensely reasoning about a future outcome, then systematically shaping the belief systems of his team, board, and external partners over an extended period to ensure widespread buy-in for strategic shifts.