As deep learning models become increasingly complex, the deep learning compilers are critical for enhancing the system efficiency and unlocking hidden optimization opportunities. Although excellent speedups have been achieved in inference workloads, existing compilers face significant limitations in training. Firstly, the training computation graph involves intricate operations challenging to fuse, such as normalization, loss functions, and reductions, which limit optimization opportunities like kernel fusion. Secondly, the training graph's additional edges connecting forward and backward operators pose challenges in finding optimal and feasible partitions for kernel fusion. More importantly, existing compilers cannot either generate kernels with state-of-the-art performance on modern GPUs or accommodate diverse fusion patterns.

Relational databases remain an important application infrastructure for organizing and analyzing massive volumes of data. At the same time, processor architectures are increasingly gravitating towards Multi-Bulk-Synchronous processor (Multi-BSP) architectures employing throughput-optimized memory systems, lightweight multi-threading, and Single-Instruction Multiple-Data (SIMD) core organizations. This paper explores the mapping of primitive relational algebra operations onto such architectures to improve the throughput of data warehousing applications built on relational databases.

Data warehousing applications represent an emerging application arena that requires the processing of relational queries and computations over massive amounts of data. Modern general purpose GPUs are high bandwidth architectures that potentially offer substantial improvements in throughput for these applications. However, there are significant challenges that arise due to the overheads of data movement through the memory hierarchy and between the GPU and host CPU. This paper proposes data movement optimizations to address these challenges. Inspired in part by loop fusion optimizations in the scientific computing community, we propose kernel fusion as a basis for data movement optimizations. Kernel fusion fuses the code bodies of two GPU kernels to i) reduce data footprint to cut down data movement throughout GPU and CPU memory hierarchy, and ii) enlarge compiler optimization scope. We classify producer consumer dependences between compute kernels into three types, i) fine-grained thread-to-thread dependences, ii) medium-grained thread block dependences, and iii) coarse-grained kernel dependences. Based on this classification, we propose a compiler framework, Kernel Weaver, that can automatically fuse relational algebra operators thereby eliminating redundant data movement. The experiments on NVIDIA Fermi platforms demonstrate that kernel fusion achieves 2.89x speedup in GPU computation and a 2.35x speedup in PCIe transfer time on average across the micro-benchmarks tested. We present key insights, lessons learned, measurements from our compiler implementation, and opportunities for further improvements.

Hardware and compiler techniques for mapping data-parallel programs with divergent control flow to SIMD architectures have recently enabled the emergence of new GPGPU programming models such as CUDA, OpenCL, and DirectX Compute. The impact of branch divergence can be quite different depending upon whether the program's control flow is structured or unstructured. In this paper, we show that unstructured control flow occurs frequently in applications and can lead to significant code expansion when executed using existing approaches for handling branch divergence.

Extracting performance from modern parallel architectures requires that applications be divided into many different threads of execution. Unfortunately selecting the appropriate number of threads for an application is a daunting task. Having too many threads can quickly saturate shared resources, such as cache capacity or memory bandwidth, thus degrading performance. On the other hand, having too few threads makes inefficient use of the resources available. Beyond static resource assignment, the program inputs and dynamic system state (e.g., what other applications are executing in the system) can have a significant impact on the right number of threads to use for a particular application.