Heterogeneous System Architecture

Heterogeneous System Architecture (HSA) is a cross-vendor set of specifications that allow for the integration of central processing units and graphics processors on the same bus, with shared memory and tasks. The HSA is being developed by the HSA Foundation, which includes (among many others) AMD and ARM. The platform's stated aim is to reduce communication latency between CPUs, GPUs and other compute devices, and make these various devices more compatible from a programmer's perspective, relieving the programmer of the task of planning the moving of data between devices' disjoint memories (as must currently be done with OpenCL or CUDA). CUDA and OpenCL as well as most other fairly advanced programming languages can use HSA to increase their execution performance. Heterogeneous computing is widely used in system-on-chip devices such as tablets, smartphones, other mobile devices, and video game consoles. HSA allows programs to use the graphics processor for floating point calculation

A Dynamically Scheduled HLS Flow in MLIR

Morten Borup Petersen

In High-Level Synthesis (HLS), we consider abstractions that span from software to hardware and target heterogeneous architectures. Therefore, managing the complexity introduced by this is key to implementing good, maintainable, and extendible HLS compilers. Traditionally, HLS flows have been built on top of software compilation infrastructure such as LLVM, with hardware aspects of the flow existing peripherally to the core of the compiler. Through this work, we aim to show that MLIR, a compiler infrastructure with a focus on domain-specific intermediate representations (IR), is a better infrastructure for HLS compilers. Using MLIR, we define HLS and hardware abstractions as first-class citizens of the compiler, simplifying analysis, transformations, and optimization. To demonstrate this, we present a C-to-RTL, dynamically scheduled HLS flow. We find that our flow generates circuits comparable to those of an equivalent LLVM-based HLS compiler. Notably, we achieve this while lacking key optimization passes typically found in HLS compilers and through the use of an experimental front-end. To this end, we show that significant improvements in the generated RTL are but low-hanging fruit, requiring engineering effort to attain. We believe that our flow is more modular and more extendible than comparable open-source HLS compilers and is thus a good candidate as a basis for future research. Apart from the core HLS flow, we provide MLIR-based tooling for C-to-RTL cosimulation and visual debugging, with the ultimate goal of building an MLIR-based HLS infrastructure that will drive innovation in the field.

2022

Scalable Simulation Methodologies for Many-Core Heterogeneous Systems

Shivani Raghav

With increasing complexity and performance demands of emerging compute-intensive data-parallel workloads, many-core computing systems are becoming a popular trend in computer design. Fast and scalable simulation methods are needed to make meaningful predictions of design alternatives to prepare early software development and to assess the performance of a system before the real hardware is available. However, simulation technology for large-scale, many-core systems is lagging behind. Most of the existing simulation techniques are slow and complex or have poor scalability and high cost of development, which leads to an unacceptable performance when simulating a large number of cores. New challenges brought by emerging many-core systems demand new methods for simulating these platforms. This thesis investigates the techniques for improving the performance of parallel simulators to model many-core heterogeneous architectures. With the recent advances in programmability and processing power of graphical hardware, General Purpose Graphical Processing Units (GPGPUs) are becoming a popular host platform for solving broad range of computationally expensive problems. The easy availability of low cost, highly parallel GPGPU platforms presents an opportunity for accelerating architectural simulations. In this thesis, I propose and investigate a novel idea of using GPGPUs as a host platform for accelerating simulation of many-core systems. GPGPUs are most suitable for certain specific highly parallel workloads with fine-grained multi-threading and high computational intensity. Architectural simulation, on the other hand, is an extremely complex task with numerous dependencies and rules. To this end, I first determine the feasibility of accelerating various target many-core architectures at different levels of abstraction details, considering the particularities of prevalent GPU architectures and their programming models. Based on this study, I target a heterogeneous architecture of a multi-core CPU connected to many-core coprocessors for GPGPU acceleration. I propose ways to exploit ample parallelism in many-core simulation and present a comprehensive framework to develop an architecture-independent, fast, scalable, easy-to-use, full-system simulator. In particular, I outline some of the challenges faced and insights gained using our proposed approach. I present specific methods and approaches that maximize the throughput of GPU power and memory bandwidth allowing optimized parallelization with minimal synchronization. Our results show high scalability and high speed up in performance for simulating up to eight thousand cores.

EPFL2014

Scalable Simulation Methodologies for Many-Core Heterogeneous Systems

Shivani Raghav

EPFL2014