Rui Ma

Rui Ma, Evangelos Georganas, Alexander Heinecke et al.

Rapid advances in artificial intelligence (AI) technology have led to significant accuracy improvements in a myriad of application domains at the cost of larger and more compute-intensive models. Training such models on massive amounts of data typically requires scaling to many compute nodes and relies heavily on collective communication algorithms, such as all-reduce, to exchange the weight gradients between different nodes. The overhead of these collective communication operations in a distributed AI training system can bottleneck its performance, with more pronounced effects as the number of nodes increases. In this paper, we first characterize the all-reduce operation overhead by profiling distributed AI training. Then, we propose a new smart network interface card (NIC) for distributed AI training systems using field-programmable gate arrays (FPGAs) to accelerate all-reduce operations and optimize network bandwidth utilization via data compression. The AI smart NIC frees up the system's compute resources to perform the more compute-intensive tensor operations and increases the overall node-to-node communication efficiency. We perform real measurements on a prototype distributed AI training system comprised of 6 compute nodes to evaluate the performance gains of our proposed FPGA-based AI smart NIC compared to a baseline system with regular NICs. We also use these measurements to validate an analytical model that we formulate to predict performance when scaling to larger systems. Our proposed FPGA-based AI smart NIC enhances overall training performance by 1.6x at 6 nodes, with an estimated 2.5x performance improvement at 32 nodes, compared to the baseline system using conventional NICs.

Omer Tanovic, Rui Ma, Koon Hoo Teo

In this paper an exact baseband equivalent model of a quadrature modulated all-digital transmitter is derived. No restrictions on the number of levels of a digital switched-mode power amplifier (SMPA) driving input, nor the pulse encoding scheme employed, are made. This implies a high level of generality of the proposed model. We show that all-digital transmitter (ADT) can be represented as a series connection of the pulse encoder, discrete-time Volterra series model of fixed degree and memory depth, and a linear time-varying system with special properties. This result suggests a new analytically motivated structure of a digital predistortion (DPD) of SMPA nonlinearities in ADT. Numerical simulations in MATLAB are used to verify proposed baseband equivalent model.

Xi Zheng, Rui Ma, Rui Gao et al.

Structured Light Illumination (SLI) systems have been used for reliable indoor dense 3D scanning via phase triangulation. However, mobile SLI systems for 360 degree 3D reconstruction demand 3D point cloud registration, involving high computational complexity. In this paper, we propose a phase based Simultaneous Localization and Mapping (Phase-SLAM) framework for fast and accurate SLI sensor pose estimation and 3D object reconstruction. The novelty of this work is threefold: (1) developing a reprojection model from 3D points to 2D phase data towards phase registration with low computational complexity; (2) developing a local optimizer to achieve SLI sensor pose estimation (odometry) using the derived Jacobian matrix for the 6 DoF variables; (3) developing a compressive phase comparison method to achieve high-efficiency loop closure detection. The whole Phase-SLAM pipeline is then exploited using existing global pose graph optimization techniques. We build datasets from both the unreal simulation platform and a robotic arm based SLI system in real-world to verify the proposed approach. The experiment results demonstrate that the proposed Phase-SLAM outperforms other state-of-the-art methods in terms of the efficiency and accuracy of pose estimation and 3D reconstruction. The open-source code is available at https://github.com/ZHENGXi-git/Phase-SLAM.

Tianyang Zhang, Rui Ma

Identify the cells' nuclei is the important point for most medical analyses. To assist doctors finding the accurate cell' nuclei location automatically is highly demanded in the clinical practice. Recently, fully convolutional neural network (FCNs) serve as the back-bone in many image segmentation, like liver and tumer segmentation in medical field, human body block in technical filed. The cells' nuclei identification task is also kind of image segmentation. To achieve this, we prefer to use deep learning algorithms. we construct three general frameworks, one is Mask Region-based Convolutional Neural Network (Mask RCNN), which has the high performance in many image segmentations, one is U-net, which has the high generalization performance on small dataset and the other is DenseUNet, which is mixture network architecture with Dense Net and U-net. we compare the performance of these three frameworks. And we evaluated our method on the dataset of data science bowl 2018 challenge. For single model without any ensemble, they all have good performance.

Sanggyun Kim, Diego Mesa, Rui Ma et al.

We consider the problem of transforming samples from one continuous source distribution into samples from another target distribution. We demonstrate with optimal transport theory that when the source distribution can be easily sampled from and the target distribution is log-concave, this can be tractably solved with convex optimization. We show that a special case of this, when the source is the prior and the target is the posterior, is Bayesian inference. Here, we can tractably calculate the normalization constant and draw posterior i.i.d. samples. Remarkably, our Bayesian tractability criterion is simply log concavity of the prior and likelihood: the same criterion for tractable calculation of the maximum a posteriori point estimate. With simulated data, we demonstrate how we can attain the Bayes risk in simulations. With physiologic data, we demonstrate improvements over point estimation in intensive care unit outcome prediction and electroencephalography-based sleep staging.