QuickRelease: A throughput-oriented approach to release consistency on GPUs

No abstract is available for this paper.

• Publication year

  2014

• Venue

  International Symposium on High-Performance Computer Architecture

• Publication date

  2014-06-19

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/HPCA.2014.6835930
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• OpenCL

  2016cited by this paper
• Heterogeneous-race-free memory models

  2014cited by this paper
• Cache coherence for GPU architectures

  2013cited by this paper
• GPUWattch: enabling energy optimizations in GPGPUs

  2013cited by this paper
• Exploring memory consistency for massively-threaded throughput-oriented processors

  2013cited by this paper
• OpenCL and the 13 dwarfs: a work in progress

  2012cited by this paper
• AMD Fusion APU: Llano

  2012cited by this paper
• The gem5 simulator

  2011cited by this paper
• AMD'S "LLANO" Fusion APU

  2011cited by this paper
• Cache Hierarchy and Memory Subsystem of the AMD Opteron Processor

  2010cited by this paper
• Rodinia: A benchmark suite for heterogeneous computing

  2009cited by this paper
• Many-core GPU computing with NVIDIA CUDA

  2008cited by this paper
• The AMD Opteron Northbridge Architecture

  2007cited by this paper
• Mechanisms for store-wait-free multiprocessors

  2007cited by this paper
• Parallelism and the ARM instruction set architecture

  2005cited by this paper
• Characterization of TCC on chip-multiprocessors

  2005cited by this paper
• Scalable store-load forwarding via store queue index prediction

  2005cited by this paper
• Shared Memory Consistency Models: A Tutorial

  1996cited by this paper
• From Causal Consistency to Sequential Consistency in Shared Memory Systems

  1995cited by this paper
• The Stanford Dash multiprocessor

  1992cited by this paper

• PhasedStore: Supporting High-Performance Write-Through Cache-Coherence Protocols Under TSO

  2026cites this paper
• LRM-GPU: Alleviating Synchronization Overhead for Multi-Chiplet GPU Architecture

  2026cites this paper
• CORD: Low-Latency, Bandwidth-Efficient and Scalable Release Consistency via Directory Ordering

  2025cites this paper
• Atomic Cache: Enabling Efficient Fine-Grained Synchronization with Relaxed Memory Consistency on GPGPUs Through In-Cache Atomic Operations

  2024cites this paper
• CPElide: Efficient Multi-Chiplet GPU Implicit Synchronization

  2024cites this paper
• Mozart: Taming Taxes and Composing Accelerators with Shared-Memory

  2024cites this paper
• Improving the Scalability of GPU Synchronization Primitives

  2023cites this paper
• Scoped Buffered Persistency Model for GPUs

  2023cites this paper
• Turn-based Spatiotemporal Coherence for GPUs

  2023influential citation
• SIMR: Single Instruction Multiple Request Processing for Energy-Efficient Data Center Microservices

  2022cites this paper
• Only Buffer When You Need To: Reducing On-chip GPU Traffic with Reconfigurable Local Atomic Buffers

  2022influential citation
• Demystifying BERT: System Design Implications

  2022cites this paper
• sRSP: GPUlarda Asimetrik Senkronizasyon Icin Yeni Olceklenebilir Bir Cozum

  2022cites this paper
• Using a static naming approach to implement remote scope promotion

  2022cites this paper
• A Case for Fine-grain Coherence Specialization in Heterogeneous Systems

  2021influential citation
• Systems-on-Chip with Strong Ordering

  2021cites this paper
• GPS: A Global Publish-Subscribe Model for Multi-GPU Memory Management

  2021cites this paper
• sRSP: An efficient and scalable implementation of remote scope promotion

  2021cites this paper
• Neat: Low-Complexity, Efficient On-Chip Cache Coherence

  2021influential citation
• Demystifying BERT: Implications for Accelerator Design

  2021cites this paper
• Efficiently Supporting Dynamic Task Parallelism on Heterogeneous Cache-Coherent Systems

  2020cites this paper
• Survey on memory management techniques in heterogeneous computing systems

  2020cites this paper
• Designing Efficient Barriers and Semaphores for Graphics Processing Units

  2020cites this paper
• Inter-kernel Reuse-aware Thread Block Scheduling

  2020cites this paper
• HMG: Extending Cache Coherence Protocols Across Modern Hierarchical Multi-GPU Systems

  2020influential citation
• Autonomous Data-Race-Free GPU Testing

  2019cites this paper
• Optimizing GPU Cache Policies for MI Workloads*

  2019cites this paper
• High-Performance Computation of Bézier Surfaces on Parallel and Heterogeneous Platforms

  2018cites this paper
• A Case for Scoped Persist Barriers in GPUs

  2018cites this paper
• Spandex: A Flexible Interface for Efficient Heterogeneous Coherence

  2018cites this paper
• Locality-protected cache allocation scheme with low overhead on GPUs

  2018cites this paper
• Compiler assisted coalescing

  2018cites this paper
• Combining HW/SW Mechanisms to Improve NUMA Performance of Multi-GPU Systems

  2018cites this paper
• Design and Analysis of an APU for Exascale Computing

  2017cites this paper
• Efficient Sequential Consistency in GPUs via Relativistic Cache Coherence

  2017cites this paper
• TC-Release++: An Efficient Timestamp-Based Coherence Protocol for Many-Core Architectures

  2017cites this paper
• Automatically comparing memory consistency models

  2017cites this paper
• HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs

  2017cites this paper
• Paving the Path for Heterogeneous Memory Adoption in Production Systems

  2017cites this paper
• Efficient Self-Invalidation/Self-Downgrade for Critical Sections with Relaxed Semantics

  2017influential citation
• Communication and Coordination Paradigms for Highly-Parallel Accelerators

  2017cites this paper
• Thread communication and synchronization on massively parallel GPUs

  2017cites this paper
• Synchronization and Coordination in Heterogeneous Processors

  2017cites this paper
• Efficient Execution Paradigms for Parallel Heterogeneous Architectures

  2016influential citation
• GSI: A GPU Stall Inspector to characterize the sources of memory stalls for tightly coupled GPUs

  2016influential citation
• Selective GPU caches to eliminate CPU-GPU HW cache coherence

  2016cites this paper
• Building Heterogeneous Unified Virtual Memories (UVMs) without the Overhead

  2016cites this paper
• Comparing Memory Consistency Models

  2016cites this paper
• Lazy release consistency for GPUs

  2016cites this paper
• Racer: TSO consistency via race detection

  2016influential citation
• Memory consistency directed cache coherence protocols for scalable multiprocessors

  2016cites this paper
• RC3: Consistency Directed Cache Coherence for x86-64 with RC Extensions

  2015cites this paper
• Implementing Cross-Device Atomics in Heterogeneous Processors

  2015cites this paper
• Efficient GPU synchronization without scopes: Saying no to complex consistency models

  2015cites this paper
• Achieving Exascale Capabilities through Heterogeneous Computing

  2015cites this paper
• Architecting, Programming, and Evaluating an On-chip Incoherent Multi-processor Memory Hierarchy

  2015cites this paper
• Memory Controller Design for GPU Simulation in Multi2sim

  2015cites this paper
• Stash: Have your scratchpad and cache it too

  2015cites this paper
• HRF-Relaxed

  2015cites this paper
• Architectural and Runtime Enhancements for Dynamically Controlled Multi-Level Concurrency on GPUs

  2015cites this paper
• Exploring CPU-GPU Coherence

  2015cites this paper
• Remote-scope promotion: clarified, rectified, and verified

  2015influential citation
• DeNovo: rethinking the memory hierarchy for disciplined parallelism

  2015cites this paper
• Synchronization Using Remote-Scope Promotion

  2015cites this paper
• Fine-grain task aggregation and coordination on GPUs

  2014cites this paper
• Adaptive Cache Management for Energy-Efficient GPU Computing

  2014cites this paper
• Runtime Support for Adaptive Spatial Partitioning and Inter-Kernel Communication on GPUs

  2014cites this paper
• Heterogeneous-race-free memory models

  2014cites this paper
• Design Space Exploration of Memory Model for Heterogeneous Computing

  2012cites this paper