NDLI: CAWS: criticality-aware warp scheduling for GPGPU workloads

Please wait, while we are loading the content...

Internet of mobile things: challenges and opportunities

Virtues and limitations of commodity hardware transactional memory

ATCache: reducing DRAM cache latency via a small SRAM tag cache

What is the cost of weak determinism?

Versatile and scalable parallel histogram construction

Adaptive heterogeneous scheduling for integrated GPUs

Invyswell: a hybrid transactional memory for haswell's restricted transactional memory

PATS: pattern aware scheduling and power gating for GPGPUs

Realm: an event-based low-level runtime for distributed memory architectures

Domain-specific models for innovation in analytics

OpenTuner: an extensible framework for program autotuning

Memory scheduling towards high-throughput cooperative heterogeneous computing

Trading cache hit rate for memory performance

PEMOGEN: automatic adaptive performance modeling during program runtime

$D^{2}MA:$ accelerating coarse-grained data transfer for GPUs

Automatic execution of single-GPU computations across multiple GPUs

An Event-Based Language for Dynamic Binary Translation Frame Works

Cooperative cache scrubbing

SpongeDirectory: flexible sparse directories utilizing multi-level memristors

ILP and TLP in shared memory applications: a limit study

Bitwise data parallelism in regular expression matching

Warp-aware trace scheduling for GPUs

Consolidated conflict detection for hardware transactional memory

Heterogeneous microarchitectures trump voltage scaling for low-power cores

kMAF: automatic kernel-level management of thread and data affinity

Velociraptor: an embedded compiler toolkit for numerical programs targeting CPUs and GPUs

Bounded memory scheduling of dynamic task graphs

Compiler support for selective page migration in NUMA architectures

ArrayTool: a lightweight profiler to guide array regrouping

VAST: the illusion of a large memory space for GPUs

LCA: a memory link and cache-aware co-scheduling approach for CMPs

Improving Performance of Streaming Applications with Filtering and Control Messages

KLA: a new algorithmic paradigm for parallel graph computations

EFetch: optimizing instruction fetch for event-driven webapplications

CAWS: criticality-aware warp scheduling for GPGPU workloads

DeSTM: harnessing determinism in STMs for application development

RCS: runtime resource and core scaling for power-constrained multi-core processors

Shuffling: a framework for lock contention aware thread scheduling for multicore multiprocessor systems

COLORIS: a dynamic cache partitioning system using page coloring

Design for scalability in enterprise SSDs

Automatic optimization of thread-coarsening for graphics processors

A run-time power manager exploiting software parallelism

Stratified Sampling for Even Workload Partitioning

Tiling and optimizing time-iterated computations on periodic domains

XStream: cross-core spatial streaming based MLC prefetchers for parallel applications in CMPs

Graph-based performance accounting for chip multiprocessor memory systems

Design of a Hybrid MPI-CUDA Benchmark Suite for CPU-GPU Clusters

SQRL: hardware accelerator for collecting software data structures

Data Remapping for an Energy Efficient Burst Chop in DRAM Memory Systems

Optimizing stencil code via locality of computation

Data-reuse Optimizations for pipelined Tiling with Parametric Tile Sizes

ADHA: automatic data layout framework for heterogeneous architectures

From Petascale to the Pocket: Adaptively Scaling Parallel Programs for Mobile SoCs

Active learning accelerated automatic heuristic construction for parallel program mapping

Coarrays in GNU Fortran

Preemptive thread block scheduling with online structural runtime prediction for concurrent GPGPU kernels

Locality-Aware Memory Association for Multi-Target Worksharing in OpenMP

Using STT-RAM to enable energy-efficient near-threshold chip multiprocessors

Processing Big Data Graphs on Memory-Restricted Systems

Protection and utilization in shared cache through rationing

Automatic parallelism through macro dataflow in high-level array languages

A runtime support mechanism for fast mode switching of a self-morphing core for power efficiency

Rollback-free value prediction with approximate loads

Measuring flexibility in single-ISA heterogeneous processors

SM-centric transformation: circumventing hardware restrictions for flexible GPU scheduling

CAWS: criticality-aware warp scheduling for GPGPU workloads

Content Provider	ACM Digital Library
Author	Lee, Shin-Ying Wu, Carole-Jean
Abstract	The ability to perform fast context-switching and massive multi-threading is the forte of modern GPU architectures, which have emerged as an efficient alternative to traditional chip-multiprocessors for parallel workloads. One of the main benefits of such architecture is its latency-hiding capability. However, the efficacy of GPU's latency-hiding varies significantly across GPGPU applications. To investigate this, this paper first proposes a new algorithm that profiles execution behavior of GPGPU applications. We characterize latencies caused by various pipeline hazards, memory accesses, synchronization primitives, and the warp scheduler. Our results show that the current round-robin warp scheduler works well in overlapping various latency stalls with the execution of other available warps for only a few GPGPU applications. For other applications, there is an excessive latency stall that cannot be hidden by the scheduler effectively. With the latency characterization insight, we observe a significant execution time disparity for warps within the same thread block, which causes sub-optimal performance, called the warp criticality problem. To tackle the warp criticality problem, we design a family of criticality-aware warp scheduling (CAWS) policies by scheduling the critical warp(s) more frequently than other warps. Our results on the breadth-first-search, B+tree search, two point angular correlation function, and K-means clustering show that, with oracle knowledge of warp criticality, our best-performing scheduling policy can improve GPGPU applications' performance by 17% on average. With our designed criticality predictor, the various scheduling policies can improve performance by 10-21% on breadth-first-search. To our knowledge, this is the first paper to characterize warp criticality and explore different criticality-aware warp scheduling policies for GPGPU workloads.
Starting Page	175
Ending Page	186
Page Count	12
File Format	PDF
ISBN	9781450328098
DOI	10.1145/2628071.2628107
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2014-08-24
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Gpu performance characterization Warp/wavefront scheduling Gpgpu
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

CAWS: criticality-aware warp scheduling for GPGPU workloads (2014)

Improving GPU performance via large warps and two-level warp scheduling

SAWS: synchronization aware GPGPU warp scheduling for multiple independent warp schedulers

CAWA: coordinated warp scheduling and cache prioritization for critical warp acceleration of GPGPU workloads

OWL: Cooperative Thread Array Aware Scheduling Techniques for Improving GPGPU Performance (2013)

CAWA: Coordinated warp scheduling and Cache Prioritization for critical warp acceleration of GPGPU workloads

CAWA:coordinated warp scheduling and cache prioritization for critical warp acceleration of GPGPU workloads

Divergence-aware warp scheduling

Virtual thread: maximizing thread-level parallelism beyond GPU scheduling limit

CAWS: criticality-aware warp scheduling for GPGPU workloads

Similar Documents

CAWS: criticality-aware warp scheduling for GPGPU workloads (2014)

Improving GPU performance via large warps and two-level warp scheduling

SAWS: synchronization aware GPGPU warp scheduling for multiple independent warp schedulers

CAWA: coordinated warp scheduling and cache prioritization for critical warp acceleration of GPGPU workloads

OWL: Cooperative Thread Array Aware Scheduling Techniques for Improving GPGPU Performance (2013)

CAWA: Coordinated warp scheduling and Cache Prioritization for critical warp acceleration of GPGPU workloads

CAWA:coordinated warp scheduling and cache prioritization for critical warp acceleration of GPGPU workloads

Divergence-aware warp scheduling

Virtual thread: maximizing thread-level parallelism beyond GPU scheduling limit

CAWS: criticality-aware warp scheduling for GPGPU workloads