Optimizing Matrix Multiplication on Intel® Xeon Phi TH x200 Architecture

Guney, Murat Efe; Goto, Kazushige; Costa, Timothy; Knepper, Sarah; Huot, Louise; Mitrano, Arthur; Story, Shane

doi:10.1109/arith.2017.19

Cited by 10 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It employs a set of techniques to improve the resource utilization to obtain higher application performance. Other works look at performance optimization for numerical solvers [38], sparse matrix vector multiplication [39], [40], and dynamic stochastic economic models [39]. Ferrão et al [41] and Memeti et al [42] develop a stream processing framework for XeonPhi to increase the programming productivity.…”

Section: Domain-specific Optimizationsmentioning

confidence: 99%

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Zhang

Fang

Yang

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

As many-core accelerators keep integrating more processing units, it becomes increasingly more difficult for a parallel application to make effective use of all available resources. An effective way for improving hardware utilization is to exploit spatial and temporal sharing of the heterogeneous processing units by multiplexing computation and communication tasks -a strategy known as heterogeneous streaming. Achieving effective heterogeneous streaming requires carefully partitioning hardware among tasks, and matching the granularity of task parallelism to the resource partition. However, finding the right resource partitioning and task granularity is extremely challenging, because there is a large number of possible solutions and the optimal solution varies across programs and datasets. This article presents an automatic approach to quickly derive a good solution for hardware resource partition and task granularity for task-based parallel applications on heterogeneous many-core architectures. Our approach employs a performance model to estimate the resulting performance of the target application under a given resource partition and task granularity configuration. The model is used as a utility to quickly search for a good configuration at runtime. Instead of hand-crafting an analytical model that requires expert insights into low-level hardware details, we employ machine learning techniques to automatically learn it. We achieve this by first learning a predictive model offline using training programs. The learnt model can then be used to predict the performance of any unseen program at runtime. We apply our approach to 39 representative parallel applications and evaluate it on two representative heterogeneous many-core platforms: a CPU-XeonPhi platform and a CPU-GPU platform. Compared to the single-stream version, our approach achieves, on average, a 1.6x and 1.1x speedup on the XeonPhi and the GPU platform, respectively. These results translate to over 93% of the performance delivered by a theoretically perfect predictor.

show abstract

Section: Domain-specific Optimizationsmentioning

confidence: 99%

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Zhang

Fang

Yang

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…The key kernel of linear algebra responsible for the high performance of many computer architectures is matrix-matrix multiplication (GEMM). It is usually one of the first kernels to be optimised and adapted for different processors and computer architectures such as multi-core CPUs, Intel Xeon Phi, ARM or GPUs [1]- [3]. Matrix multiplication is a computationally intensive problem whose performance is limited by processor speed rather than memory bandwidth and latency.…”

Section: Introductionmentioning

confidence: 99%

Batched matrix operations on distributed GPUs with application in theoretical physics

Nenad¹,

Davidović²

2022

Preprint

View full text Add to dashboard Cite

One of the most important and commonly used operations in many linear algebra functions is matrix-matrix multiplication (GEMM), which is also a key component in obtaining high performance of many scientific codes. It is a computationally intensive function requiring O(n 3 ) operations, and its high computational intensity makes it well-suited to be significantly accelerated with GPUs. Today, many research problems require solving a very large number of relatively small GEMM operations that cannot utilise the entire GPU. To overcome this bottleneck, special functions have been developed that pack several GEMM operations into one and then compute them simultaneously on a GPU, which is called a batch operation. In this research work, we have proposed a different approach based on linking multiple GEMM operations to MPI ranks and then binding multiple MPI ranks to a single GPU. To increase GPU utilisation, more MPI ranks (i.e. GEMM operations) are added. We implement and test this approach in the field of theoretical physics to compute entanglement properties through simulated annealing Monte Carlo simulation of quantum spin chains. For the specific use case, we were able to simulate a much larger spin system and achieve a speedup of up to 35× compared to the parallel CPU-only version.

show abstract