Parallel Computing podcasts

Philip Kiely surveys inference engineering at the intersection of GPU programming, applied research and distributed systems. Topics include batching, quantisation, speculative execution, cache reuse and workload-specific serving, alongside the choices between hosted APIs, dedicated deployments and internal platforms for multimodal and agent applications.

Hosted by Sam Charrington

Zain Asgar examines running agent inference across heterogeneous hardware. The discussion covers splitting workloads between GPUs and CPUs, compilation for different targets, automated kernel optimisation and hardware-aware scheduling. It also explores networking constraints and trade-offs among numerical precision, application accuracy, performance and cost.

Hosted by Sam Charrington

Kunle Olukotun explains reconfigurable dataflow architectures for AI inference. The discussion examines mapping computation onto model dataflow graphs, reducing memory-bandwidth bottlenecks, serving multiple models and switching between them efficiently. It also considers dynamic hardware architectures and using AI agents to develop compilers.

Hosted by Sam Charrington