En 30 segundos
Rene Haas argues that CPUs remain important alongside AI accelerators and discusses orchestration around training and inference. The specific division of work depends on system design.
- 1A system componentHaas expects CPUs to remain part of computing systems.
- 2Changing workloadsTraining and inference require broader system support.
- 3CoordinationHardware and software share orchestration and routing work.
Conclusiones
- AI accelerators operate within larger systems.
- CPUs can support control and coordination.
- The division of work varies by architecture.
Lee el texto editado por capítulos
CPUs and accelerators
Arm CEO Rene Haas argues that CPUs remain important in computing systems even as specialized AI accelerators become more prominent.
Arm CEO Rene Haas argues that CPUs remain important in computing systems even as specialized AI accelerators become more prominent.
He describes CPUs as a component of overall system design rather than treating an accelerator as the entire system.
System orchestration
Haas discusses workloads including training, reinforcement learning and inference, and says the surrounding infrastructure must coordinate data and execution.
Haas discusses workloads including training, reinforcement learning and inference, and says the surrounding infrastructure must coordinate data and execution.
He uses a transport analogy for orchestration and routing. The precise division of work varies by hardware and software architecture.
Más de este canal
38:06EN
No Priors: AI, Machine Learning, Tech, & Startups· 29 oct 2026Pódcast · 3 vocesServal’s Jake Stauch on coding agents for enterprise ITInvitado: Jake Stauch · Presenta: Sarah Guo, Elad GilStauch explains why Serval is challenging ServiceNow, how it approaches permissions and approvals, and why background agents remain difficult to deploy safely.
1:07ENNo Priors: AI, Machine Learning, Tech, & Startups· 27 oct 2026PódcastGeorge Kurtz on How AI May Change CyberattacksInvitado: George KurtzThe CrowdStrike CEO describes his assessment of evolving threats.
39:23ENNo Priors: AI, Machine Learning, Tech, & Startups· 15 oct 2026Pódcast · 2 vocesThe Defenders' Window: Greg Brockman on AI-Generated Knowledge, Drug Discovery, and the New Physics of CybersecurityPresenta: Sarah Guo, Elad GilOpenAI's president explains why solving open math problems is a proof point for science, how proactive agents change product form, and why security spending must exceed software spending.
1:04ENNo Priors: AI, Machine Learning, Tech, & Startups· 14 oct 2026PódcastWalter Goodwin on the Slow Steps in Chip DesignInvitado: Walter GoodwinA chip founder explains why automation does not remove every computational bottleneck.
1:09:44ENNo Priors: AI, Machine Learning, Tech, & Startups· 9 oct 2026Pódcast · 2 voces10,000 GB300s for Four Weeks: Reflection’s Open-Model LedgerPresenta: Sarah Guo, Elad GilMisha Laskin tells No Priors how Reflection trained Beam, why reinforcement learning outspent pre-training, and why the West needs its own open weights.
35:39ENNo Priors: AI, Machine Learning, Tech, & Startups· 2 oct 2026Pódcast · 2 vocesCompute Scaled a Millionfold. Bandwidth Only 40x. Fractile Wants to Fix That RatioPresenta: Sarah Guo, Elad GilIn the summer of 2022, Walter Goodwin founded Fractile in London to build very fast inference chips for the world's largest models.