Skip to content

Rubberband: Memory-Elastic, Skew-Tolerant GPU Hash Joins

· 0 citations · 42 references

TL;DR

Rubberband is a new hash join in CoddSpeed, Microsoft Fab-ric’s production GPU-accelerated analytical engine that addresses memory elasticity as HBM pressure tightens and a logical rewrite that lifts the equality test out of the probe loop and applies it as a post-join filter.

View source

Similar papers

Review Aug 2026

Concurrency Response of Plain Global Loads on the NVIDIA H100

The main result concerns the plain-load path: attained LDG bandwidth peaks at a small offered per-thread load (K ~ 2) and then declines, by about 35% from K=2 to K=8 at the authors' primary configuration.

S. Manjunath, Rahul Ramachandra · 0 citations

Breaking the Tradeoff: Elastic and Isolated GPU Sharing with Ghost

Ghost is an OS-level GPU virtualization layer integrated directly into the open-source GPU driver, using a GPU container abstraction with cgroup -like APIs for compute and memory control and privileged hardware-level scheduling and preemption for dynamic compute resource management.

Unknown authors · 0 citations
#artificial intelligence Preprint Sep 2026

EMA: Elastic and Performance Transparent Memory Across GPUs

Multi-GPU servers have become the standard building block of modern data centers, providing aggregated capacity through high-bandwidth interconnects. At the same time, workloads such as LLM inference exhibit highly dynamic memory demands, which can cause one GPU to exhaust its local memory while others remain underutil...

Yi Xu, Tian Xia, Ion Stoica · 0 citations
Book Open access Sep 2026

Anchor: Mitigating GPU Shallow Disruptions with Decoupled Memory

Job failures are frequent in large-scale GPU clusters for LLM workloads, leading to significant resource wastage. The vast majority of these are shallow disruptions (e.g., software errors or updates), where only the worker process crashes while the underlying GPU and OS kernel remain intact. Existing recovery systems,...

Hao-Yi Ma, Shi-Wei Gao, You-Min Chen et al. · 0 citations
Preprint Sep 2026

Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture

This work proposes Hoss, a first-of-its-kind oblivious semantic search system with a heterogeneous CPU-GPU TEE architecture that supports fast, scalable search with low cost of ownership and features a host-access ORAM mechanism that goes beyond traditional performance constraints and incorporates several data-dependen...

Jian Du, Wei-Jie Huang, Cheng-Hong Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.