GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. A traditional approach is to directly integrate lossy compression into GPU-aware collectives, which can lead to serious performance issues such as underutilized GPU devices and uncontrolled data distortion. In order to address these issues, in this paper, we propose gZCCL, a first-ever general framework that designs and optimizes GPU-aware, compression-enabled collectives with an accuracy-aware design to control error propagation. To validate our framework, we evaluate the performance on up to 512 NVIDIA A100 GPUs with real-world applications and datasets. Experimental results demonstrate that our gZCCL-accelerated collectives, including both collective computation (Allreduce) and collective data movement (Scatter), can outperform NCCL as well as Cray MPI by up to 4.5 × and 28.7 ×, respectively. Furthermore, our accuracy evaluation with an image-stacking application confirms the high reconstructed data quality of our accuracy-aware framework.

With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communications turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade the overall parallel performance. To address this issue, prior research simply applies the off-the-shelf fix-rate lossy compressors in the MPI collectives, leading to suboptimal performance, limited generalizability, and unbounded errors. In this paper, we propose a novel solution, called C-Coll, which leverages error-bounded lossy compression to significantly reduce the message size, resulting in a substantial reduction in communication cost. The key contributions are three-fold. (1) We develop two general, optimized lossy-compression-based frameworks for both types of MPI collectives (collective data movement as well as collective computation), based on their particular characteristics. Our framework not only reduces communication cost but also preserves data accuracy. (2) We customize SZx, an ultra-fast error-bounded lossy compressor, to meet the specific needs of collective communication. (3) We integrate C-Coll into multiple collectives, such as MPI Allreduce, MPI Scatter, and MPI Bcast, and perform a comprehensive evaluation based on real-world scientific datasets. Experiments show that our solution outperforms the original MPI collectives as well as multiple baselines and related efforts by 1.8–2.7×.

GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. To address this issue, traditional approaches integrate lossy compression directly into GPU-aware collectives, which still suffer from serious issues such as underutilized GPU devices and uncontrolled data distortion. In this paper, we propose GPU-LCC, a general framework that designs and optimizes GPU-aware, compression-enabled collectives with well-controlled error propagation. To validate our framework, we evaluate the performance on up to 64 NVIDIA A100 GPUs with real-world applications and datasets. Experimental results demonstrate that our GPU-LCC-accelerated collective computation (Allreduce), can outperform NCCL as well as Cray MPI by up to 3.4× and 18.7×, respectively. Furthermore, our accuracy evaluation with an image-stacking application confirms the high reconstructed data quality of our accuracy-aware framework.

In the era of exascale computing, the adoption of a large number of CPU cores and nodes by high-performance computing (HPC) applications has made MPI collective performance increasingly crucial. As the number of cores and nodes increases, the importance of optimizing MPI collective performance becomes more evident. Current collective algorithms, including kernel-assisted inter-process data exchange techniques and data sharing based shared-memory approaches, are prone to significant performance degradation due to the overhead of system calls and page faults or the cost of extra data-copy latency. These issues can negatively impact the efficiency and scalability of HPC applications. To address these issues, we propose PiP-MColl, a Process-in-Process-based Multi-object Interprocess MPI Collective design that maximizes small message MPI collective performance at scale. We also present specific designs to boost the performance for larger messages, such that we observe a comprehensive improvement for a series of message sizes beyond small messages. PiP-MColl features efficient multiple sender and receiver collective algorithms and leverages Process-in-Process shared memory techniques to eliminate unnecessary system call, page fault overhead and extra data copy, which results in improved intra- and inter-node message rate and throughput. Experimental results demonstrate that PiP-MColl significantly outperforms popular MPI libraries, including OpenMPI, MVAPICH2, and Intel MPI, by up to 4.6X for the MPI collectives MPI_Scatter, MPI_Allgather, and MPI_Allreduce.

In the exascale computing era, optimizing MPI collective performance in high-performance computing (HPC) applications is critical. Current algorithms face performance degradation due to system call overhead, page faults, or data-copy latency, affecting HPC applications' efficiency and scalability. To address these issues, we propose PiP-MColl, a Process-in-Process-based Multi-object Inter-process MPI Collective design that maximizes small message MPI collective performance at scale. PiP-MColl features efficient multiple sender and receiver collective algorithms and leverages Process-in-Process shared memory techniques to eliminate unnecessary system call, page fault overhead, and extra data copy, improving intra- and inter-node message rate and throughput. Our design also boosts performance for larger messages, resulting in comprehensive improvement for various message sizes. Experimental results show that PiP-MColl outperforms popular MPI libraries, including OpenMPI, MVAPICH2, and Intel MPI, by up to 4.6X for MPI collectives like MPI_Scatter and MPI_Allgather.

Partitioned communication was introduced in MPI 4.0 as a user-friendly interface to support pipelined communication patterns, particularly common in the context of MPI+threads. It provides the user with the ability to divide a global buffer into smaller independent chunks, called partitions, which can then be communicated independently. In this work we first model the performance gain that can be expected when using partitioned communication. Next, we describe the improvements we made to MPICH to enable those gains and provide a high-quality implementation of MPI partitioned communication. We then evaluate partitioned communication in various common use cases and assess the performance in comparison with other MPI point-to-point and one-sided approaches. Specifically, we first investigate two scenarios commonly encountered for small partition sizes in a multithreaded environment: thread contention and overhead of using many partitions. We propose two solutions to alleviate the measured penalty and demonstrate their use. We then focus on large messages and the gain obtained when exploiting the delay resulting from computations or load imbalance. We conclude with our perspectives on the benefits of partitioned communication and the various results obtained.

MPI + Threads, embodied by the MPI/OpenMP hybrid programming model, is a parallel programming paradigm where threads are used for on-node shared-memory parallelization and MPI is used for multi-node distributed-memory parallelization. OpenMP provides an incremental approach to parallelize code, while MPI, with its isolated address space and explicit messaging API, affords straightforward paths to obtain good parallel performance. However, MPI + Threads is not an ideal solution. Since MPI is unaware of the thread context, it cannot be used for interthread communication. This results in duplicated efforts to create separate and sometimes nested solutions for similar parallel tasks. In addition, because the MPI library is required to obey message-ordering semantics, mixing threads and MPI via MPI_THREAD_MULTIPLE can easily result in miserable performance due to accidental serializations.

The hybrid MPI+X programming paradigm, where X refers to threads or GPUs, has gained prominence in the high-performance computing arena. This corresponds to a trend of system architectures growing more heterogeneous. The current MPI standard only specifies the compatibility levels between MPI and threading runtimes. No MPI concept or interface exists for applications to pass thread context or GPU stream context to MPI implementations explicitly. This lack has made performance optimization complicated in some cases and impossible in other cases. We propose a new concept in MPI, called MPIX stream, to represent the general serial execution context that exists in X runtimes. MPIX streams can be directly mapped to threads or GPU execution streams. Passing thread context into MPI allows implementations to precisely map the execution contexts to network endpoints. Passing GPU execution context into MPI allows implementations to directly operate on GPU streams, lowering the CPU/GPU synchronization cost.

Efforts to mitigate lock contention from concurrent threaded accesses to MPI have reduced contention through fine-grained locking, avoided locking altogether by offloading communication to dedicated threads, or alleviated negative side effects from contention by using better lock management protocols. The blocking nature of lock-based methods, however, wastes the asynchrony benefits of nonblocking MPI operations, and the offloading model sacrifices CPU resources and incurs unnecessary software offloading overheads under low contention.

MPI allows applications to treat processes as a logical collection of integer ranks for each MPI communicator, while internally translating these logical ranks into actual network addresses. In current MPI implementations the management and lookup of such network addresses use memory sizes that are proportional to the number of processes in each communicator. In this paper, we propose a new mechanism, called AV-Rankmap, for managing such translation. AV-Rankmap takes advantage of logical patterns in rank-address mapping that most applications naturally tend to have, and it exploits the fact that some parts of network address structures are naturally more performance critical than others. It uses this information to compress the memory used for network address management. We demonstrate that AV-Rankmap can achieve performance similar to or better than that of other MPI implementations while using significantly less memory.

This paper provides an in-depth analysis of the software overheads in the MPI performance-critical path and exposes mandatory performance overheads that are unavoidable based on the MPI-3.1 specification. We first present a highly optimized implementation of the MPI-3.1 standard in which the communication stack---all the way from the application to the low-level network communication API---takes only a few tens of instructions. We carefully study these instructions and analyze the root cause of the overheads based on specific requirements from the MPI standard that are unavoidable under the current MPI standard. We recommend potential changes to the MPI standard that can minimize these overheads. Our experimental results on a variety of network architectures and applications demonstrate significant benefits from our proposed changes.

The Portals 4 network specification is a low-levelAPI for high-performance networks developed by Sandia National Laboratories, Intel Corporation, and the University of NewMexico. Portals 4 is specifically designed to support both the MPIand PGAS programming models efficiently by providing building blocks upon which to implement their particular features. In this paper we discuss our ongoing efforts to add efficient and robust support for Portals 4 networks inside MPICH, and we describe how the API semantics influenced our design. In particular, we found the lack of reliability guarantees from the Portals4 layer challenging to address. To tackle this situation, we implemented an intermediate layer - Rportals (reliable Portals), which modularizes the reliability functionality within our Portals network module for MPICH. In this paper we present theRportals design and its performance impact.

In preparation for the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report, the climate community will run the Coupled Model Intercomparison Project phase 5 (CMIP-5) experiments, which are designed to answer crucial questions about future regional climate change and the results of carbon feedback for different mitigation scenarios. The CMIP-5 experiments will generate petabytes of data that must be replicated seamlessly, reliably, and quickly to hundreds of research teams around the globe. As an end-to-end test of the technologies that will be used to perform this task, a multi-disciplinary team of researchers moved a small portion (10 TB) of the multimodel Coupled Model Intercomparison Project, Phase 3 data set used in the IPCC Fourth Assessment Report from three sources---the Argonne Leadership Computing Facility (ALCF), Lawrence Livermore National Laboratory (LLNL) and National Energy Research Scientific Computing Center (NERSC)---to the 2009 Supercomputing conference (SC09) show floor in Portland, Oregon, over circuits provided by DOE's ESnet. The team achieved a sustained data rate of 15 Gb/s on a 20 Gb/s network. More important, this effort provided critical feedback on how to deploy, tune, and monitor the middleware that will be used to replicate the upcoming petascale climate datasets. We report on obstacles overcome and the key lessons learned from this successful bandwidth challenge effort.