Related papers: CXL Shared Memory Programming: Barely Distributed …
Large Language Models (LLMs) have revolutionized natural language processing tasks, but their deployment in datacenter environments faces significant challenges due to the massive memory requirements of key-value (KV) caches. During the…
Message Passing Interface (MPI) is a foundational programming model for high-performance computing. MPI libraries traditionally employ network interconnects (e.g., Ethernet and InfiniBand) and network protocols (e.g., TCP and RoCE) with…
Public cloud providers seek to meet stringent performance requirements and low hardware cost. A key driver of performance and cost is main memory. Memory pooling promises to improve DRAM utilization and thereby reduce costs. However,…
In GPU graph analytics, the use of external memory such as the host DRAM and solid-state drives is a cost-effective approach to processing large graphs beyond the capacity of the GPU onboard memory. This paper studies the use of Compute…
We consider a parallel computational model that consists of $P$ processors, each with a fast local ephemeral memory of limited size, and sharing a large persistent memory. The model allows for each processor to fault with bounded…
Modern workloads are demanding increasingly larger memory capacity. Compute Express Link (CXL)-based memory tiering has emerged as a promising solution for addressing this problem by utilizing traditional DRAM alongside slow-tier CXL memory…
Memory dominates datacenter system cost and power. Memory expansion via Compute Express Link (CXL) is an effective way to provide additional memory at lower cost and power, but its effective use requires software-level tiering for…
Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…
The ability to express a program as a hierarchical composition of parts is an essential tool in managing the complexity of software and a key abstraction this provides is to separate the representation of data from the computation. Many…
Modern out-of-order processors have increased capacity to exploit instruction level parallelism (ILP) and memory level parallelism (MLP), e.g., by using wide superscalar pipelines and vector execution units, as well as deep buffers for…
Upcoming CXL-based disaggregated memory devices feature special purpose units to offload compute to near-memory. In this paper, we explore opportunities for offloading compute to general purpose cores on CXL memory devices, thereby enabling…
Exascale systems, expected to emerge by the end of the next decade, will require the exploitation of billion-way parallelism at multiple hierarchical levels in order to achieve the desired sustained performance. The task of assessing future…
Computational memory (CM) is a promising approach for accelerating inference on neural networks (NN) by using enhanced memories that, in addition to storing data, allow computations on them. One of the main challenges of this approach is…
This paper proposes ScalePool, a novel cluster architecture designed to interconnect numerous accelerators using unified hardware interconnects rather than traditional long-distance networking. ScalePool integrates Accelerator-Centric Links…
Concurrency has been a subject of study for more than 50 years. Still, many developers struggle to adapt their sequential code to be accessed concurrently. This need has pushed for generic solutions and specific concurrent data structures.…
Approximate memory is a technique to mitigate the performance gap between memory subsystems and CPUs with its reduced access latency at a cost of data integrity. To gain benefit from approximate memory for realistic applications, it is…
The use of disaggregated or far memory systems such as CXL memory pools has renewed interest in Near-Data Processing (NDP): situating cores close to memory to reduce bandwidth requirements to and from the CPU. Hardware designs for such…
The rapid increase in LLM model sizes and the growing demand for long-context inference have made memory a critical bottleneck in GPU-accelerated serving systems. Although high-bandwidth memory (HBM) on GPUs offers fast access, its limited…
To mitigate the ever worsening "Power wall" and "Memory wall" problems, multi-core architectures with multilevel cache hierarchies have been widely accepted in modern processors. However, the complexity of the architectures makes modeling…
Remote procedure calls are the workhorse of distributed systems. However, as software engineering trends, such as micro-services and serverless computing, push applications towards ever finer-grained decompositions, the overhead of…