The path a packet takes when handled by the Linux Kernel has been well established for a
long time. Its overhead/bottleneck issues are also known. Nonetheless, complexity has …

Modern network hardware is able to meet the stringent bandwidth demands of applications
like GPU-accelerated AI. However, existing host network stacks offer a hard tradeoff …

SmartNICs are on the rise as a packet processing platform, with the trend towards a uniform
P4 programming model. However, unleashing SmartNIC packet processing performance in …

Dedicated, tightly integrated, and static packet processing pipelines in today's most widely
deployed network stacks preclude them from fully exploiting capabilities of modern …

Direct-attached accelerators, where application accelerators are directly connected to the
datacenter network via a hardware network stack, offer substantial benefits in terms of …

Careful orchestration of requests at a datacenter server is crucial to meet tight tail latency
requirements and ensure high throughput and optimal CPU utilization. Orchestration is multi …

Cross-silo federated learning (FL) leverages homomorphic encryption (HE) to obscure the
model updates from the clients. However, HE poses the challenges of complex …

SmartNICs have become an indispensable communication fabric and computing substrate
in today's data centers and enterprise clusters, providing in-network computing capabilities …

Memory optimization kernel features, such as memory deduplication, are designed to
improve the overall efficiency of systems like datacenter servers, and they have proven to be …

The TCP remains the workhorse protocol for many modern large-scale data centers.
However, the increasingly demanding performance expectations—led by advancement in …