Polyhedral techniques have been widely used for automatic code optimization in low-level compilers and higher-level processes. Loop optimization is central to this technique, and several polyhedral schedulers like Feautrier, Pluto, isl and Tensor Scheduler have been proposed, each of them targeting a different architecture, parallelism model, or application scenario. The need for scenario-specific optimization is growing due to the heterogeneity of architectures. One of the most critical cases is represented by NPUs (Neural Processing Units) used for AI, which may require loop optimization with different objectives. Another factor to be considered is the framework or compiler in which polyhedral optimization takes place. Different scenarios, depending on the target architecture, compilation environment, and application domain, may require different kinds of optimization to best exploit the architecture feature set. We introduce a new configurable polyhedral scheduler, PolyTOPS, that can be adjusted to various scenarios with straightforward, high-level configurations. This scheduler allows the creation of diverse scheduling strategies that can be both scenario-specific (like state-of-the-art schedulers) and kernel-specific, breaking the concept of a one-size-fits-all scheduler approach. PolyTOPS has been used with isl and CLooG as code generators and has been integrated in MindSpore AKG deep learning compiler. Experimental results in different scenarios show good performance: a geomean speedup of 7.66x on MindSpore (for the NPU Ascend architecture) hybrid custom operators over isl scheduling, a geomean speedup up to 1.80× on PolyBench on different multicore architectures over Pluto scheduling. Finally, some comparisons with different state-of-the-art tools are presented in the PolyMage scenario.

Automatic parallel code generation from high-level abstractions such as those manipulated by artificial intelligence and deep learning (AI/DL) frameworks heavily rely on compiler techniques for automatic parallelization and optimization. Many recent advances rely on the polyhedral framework for this task because of its ability to model and to apply a wide range of loop transformations. However, modeling the complexity of the target architecture and of efficient cost models to decide about the best transformation is in general out of reach for a framework based on linear/affine constraints. In this work, we propose to decouple the polyhedral framework into linear and non-linear components. We introduce the constraint tree abstraction which may be generated by a non-linear optimizer and injected to the polyhedral optimization process to build better solutions. We present how to benefit from such a mechanism to generate efficient codes for GPU in the context of AI/DL operators. Our constraint injection allows to drive the polyhedral scheduler towards efficient solutions for load/store vectorization relying both on memory coalescing and vector types. We implemented our scheduler supporting constraint injection and our constraint construction system within a production AI/DL framework. Experiments on well known neural networks show the efficiency of this approach with respect to state-of-the-art polyhedral scheduling for GPU.

Optimizations, transformations and analyses are applied to programs by compilers at the intermediate representation level, which usually does not include explicit variable declarations. This description level is fine for middle-ends and for source-to-source optimizers of simple languages. Meanwhile, the C language has become much more flexible since the C99 standard, and let variable and type declarations appear almost anywhere in source code. We present in this paper a new concept to manage C99 declarations in a source-to-source compiler: the Effects Dependence Graph, which is an extension of the classical Data Dependence Graph. It deals particularly efficiently with user-defined type declarations or dependent types like Variable-Length Array. It is also interesting because no legal scheduling transformation is hindered and because existing algorithms are either not or slightly modified. Finally it reduces the need for variable, struct and array privatization or live range analyses in automatic parallelizers. To the best of our knowledge, the declaration issue is ignored in the literature: existing C source-to-source compilers either do not support C99, or accept only restricted portions of code, and production compilers use low-level intermediate representations, possibly with annotations. In this way our solution addresses a wider range of compiler analysis issues.