Search

Compiling programs to an instruction set architecture (ISA) requires a set of rewrite rules that map patterns consisting of compiler instructions to patterns consisting of ISA instructions. We synthesize such rules by constructing SMT queries, whose solutions represent two functionally equivalent programs. These two programs are interpreted as an instruction selection rewrite rule. Existing work is limited to single-instruction ISA patterns, whereas our solution does not have that restriction. Furthermore, we address inefficiencies of existing work by developing two optimized algorithms. The first only generates unique rules by preventing synthesis of duplicate and composite rules. The second only generates lowest-cost rules by preventing synthesis of higher-cost rules. We evaluate our algorithms on multiple ISAs. Without our optimizations, the vast majority of synthesized rewrite rules are either duplicates, composites, or higher cost. Our optimizations result in synthesis speed-ups of up to 768x and 4004x for the two algorithms., Comment: 9 pages, 2 figures, in submission to FMCAD24, fixed small bugs in results generation, improved baseline comparison, improved background and writing clarity

Domain-specific languages for hardware can significantly enhance designer productivity, but sometimes at the cost of ease of verification. On the other hand, ISA specification languages are too static to be used during early stage design space exploration. We present PEak, an open-source hardware design and specification language, which aims to improve both design productivity and verification capability. PEak does this by providing a single source of truth for functional models, formal specifications, and RTL. PEak has been used in several academic projects, and PEak-generated RTL has been included in three fabricated hardware accelerators. In these projects, the formal capabilities of PEak were crucial for enabling both novel design space exploration techniques and automated compiler synthesis.

Domain-specific accelerators are used in various computing systems ranging from edge devices to data centers. Coarse-grained reconfigurable arrays (CGRAs) represent an architectural midpoint between the flexibility of an FPGA and the efficiency of an ASIC and are a promising candidate for servicing multi-tasked workloads within an application domain. Unfortunately, scheduling multiple tasks onto a CGRA is challenging. CGRAs lack abstractions that capture hardware resources, leaving workload schedulers unable to reason about performance, energy, and utilization for different schedules. This work first proposes a CGRA architecture that can flexibly partition key resources, including the global buffer memory capacity, the global buffer memory bandwidth, and the compute resources. Partitioned resources serve as hardware abstractions that decouple compilation and resource allocation. The compiler uses these abstractions for coarse-grained resource mapping, and the scheduler uses them for flexible resource allocation at run time. We then propose two hardware mechanisms to support multi-task execution. A flexible-shape execution region increases the overall resource utilization by mapping multiple tasks with different resource requirements. Dynamic partial reconfiguration (DPR) enables a CGRA to update the hardware configuration as the scheduler makes decisions rapidly. We show that our abstraction can help automatic and efficient scheduling of multi-tasked workloads onto our target CGRA with high utilization, resulting in 1.05x-1.24x higher throughput and a 23-28% lower latency in a multi-tasked cloud workload and 60.8% reduced latency in an autonomous system workload when compared to a baseline CGRA running single tasks at a time.

The architecture of a coarse-grained reconfigurable array (CGRA) interconnect has a significant effect on not only the flexibility of the resulting accelerator, but also its power, performance, and area. Design decisions that have complex trade-offs need to be explored to maintain efficiency and performance across a variety of evolving applications. This paper presents Canal, a Python-embedded domain-specific language (eDSL) and compiler for specifying and generating reconfigurable interconnects for CGRAs. Canal uses a graph-based intermediate representation (IR) that allows for easy hardware generation and tight integration with place and route tools. We evaluate Canal by constructing both a fully static interconnect and a hybrid interconnect with ready-valid signaling, and by conducting design space exploration of the interconnect architecture by modifying the switch box topology, the number of routing tracks, and the interconnect tile connections. Through the use of a graph-based IR for CGRA interconnects, the eDSL, and the interconnect generation system, Canal enables fast design space exploration and creation of CGRA interconnects., Comment: Preprint version

While coarse-grained reconfigurable arrays (CGRAs) have emerged as promising programmable accelerator architectures, pipelining applications running on CGRAs is required to ensure high maximum clock frequencies. Current CGRA compilers either lack pipelining techniques resulting in low performance or perform exhaustive pipelining resulting in high energy and resource consumption. We introduce Cascade, an application pipelining toolkit for CGRAs, including a CGRA application frequency model, automated pipelining techniques for CGRA application compilers that work with both dense and sparse applications, and hardware optimizations for improving application frequency. Cascade enables 7 - 34x lower critical path delays and 7 - 190x lower EDP across a variety of dense image processing and machine learning workloads, and 2 - 4.4x lower critical path delays and 1.5 - 4.2x lower EDP on sparse workloads, compared to a compiler without pipelining., Comment: Preprint version

Achieving high code reuse in physical design flows is challenging but increasingly necessary to build complex systems. Unfortunately, existing approaches based on parameterized Tcl generators support very limited reuse and struggle to preserve reusable code as designers customize flows for specific designs and technologies. We present a vision and framework based on modular flow generators that encapsulates coarse-grain and fine-grain reusable code in modular nodes and assembles them into complete flows. The key feature is a flow consistency and instrumentation layer embedded in Python, which supports mechanisms for rapid and early feedback on inconsistent composition. The approach gradually types the Tcl language and allows both automatic and user-annotated static assertion checks. We evaluate the design flows of successive generations of silicon prototypes designed in TSMC16, TSMC28, TSMC40, SKY130, and IBM180 technologies, showing how our approach can enable significant code reuse in future flows.

Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e.g. video, audio) at unprecedented energy-efficiency. AI hardware architectures today cannot meet the demand due to a fundamental "memory wall": data movement between separate compute and memory units consumes large energy and incurs long latency. Resistive random-access memory (RRAM) based compute-in-memory (CIM) architectures promise to bring orders of magnitude energy-efficiency improvement by performing computation directly within memory. However, conventional approaches to CIM hardware design limit its functional flexibility necessary for processing diverse AI workloads, and must overcome hardware imperfections that degrade inference accuracy. Such trade-offs between efficiency, versatility and accuracy cannot be addressed by isolated improvements on any single level of the design. By co-optimizing across all hierarchies of the design from algorithms and architecture to circuits and devices, we present NeuRRAM - the first multimodal edge AI chip using RRAM CIM to simultaneously deliver a high degree of versatility for diverse model architectures, record energy-efficiency $5\times$ - $8\times$ better than prior art across various computational bit-precisions, and inference accuracy comparable to software models with 4-bit weights on all measured standard AI benchmarks including accuracy of 99.0% on MNIST and 85.7% on CIFAR-10 image classification, 84.7% accuracy on Google speech command recognition, and a 70% reduction in image reconstruction error on a Bayesian image recovery task. This work paves a way towards building highly efficient and reconfigurable edge AI hardware platforms for the more demanding and heterogeneous AI applications of the future., Comment: 34 pages, 14 figures, 1 table

Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performance for flexible hardware, or ASICs, which rapidly become obsolete as applications change. Programmable domain-specific accelerators have emerged as a promising middle-ground between these two extremes, but such architectures have traditionally been difficult compiler targets. The main obstacle is that these accelerators often use a different memory abstraction than CPUs and GPUs: push memories that send a data stream from one computation kernel to other kernels, possibly reordered. To address the compilation challenges caused by push memories, we propose that the representation of memory in the middle and backend of the compiler be altered to combine storage with address generation and control logic in a single structure -- a unified buffer. We show that this compiler abstraction can be implemented efficiently on a programmable accelerator, and design a memory mapping algorithm that combines polyhedral analysis and software vectorization techniques to target our accelerator. Our evaluation shows that the compiler supports programmability while maintaining high performance. It can compile a wide range of image processing and machine learning applications to our accelerator with 4.7x better runtime and 4.3x better energy-efficiency as compared to an FPGA.

The architecture of a coarse-grained reconfigurable array (CGRA) processing element (PE) has a significant effect on the performance and energy efficiency of an application running on the CGRA. This paper presents an automated approach for generating specialized PE architectures for an application or an application domain. Frequent subgraphs mined from a set of applications are merged to form a PE architecture specialized to that application domain. For the image processing and machine learning domains, we generate specialized PEs that are up to 10.5x more energy efficient and consume 9.1x less area than a baseline PE.

For several skin conditions such as vitiligo, accurate segmentation of lesions from skin images is the primary measure of disease progression and severity. Existing methods for vitiligo lesion segmentation require manual intervention. Unfortunately, manual segmentation is time and labor-intensive, as well as irreproducible between physicians. We introduce a convolutional neural network (CNN) that quickly and robustly performs vitiligo skin lesion segmentation. Our CNN has a U-Net architecture with a modified contracting path. We use the CNN to generate an initial segmentation of the lesion, then refine it by running the watershed algorithm on high-confidence pixels. We train the network on 247 images with a variety of lesion sizes, complexity, and anatomical sites. The network with our modifications noticeably outperforms the state-of-the-art U-Net, with a Jaccard Index (JI) score of 73.6% (compared to 36.7%). Moreover, our method requires only a few seconds for segmentation, in contrast with the previously proposed semi-autonomous watershed approach, which requires 2-29 minutes per image.

We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops of DNNs, which enables us to create a formal taxonomy of all existing dense DNN accelerators. Surprisingly, the loop transformations needed to create these hardware variants can be precisely and concisely represented by Halide's scheduling language. By modifying the Halide compiler to generate hardware, we create a system that can fairly compare these prior accelerators. As long as proper loop blocking schemes are used, and the hardware can support mapping replicated loops, many different hardware dataflows yield similar energy efficiency with good performance. This is because the loop blocking can ensure that most data references stay on-chip with good locality and the processing units have high resource utilization. How resources are allocated, especially in the memory system, has a large impact on energy and performance. By optimizing hardware resource allocation while keeping throughput constant, we achieve up to 4.2X energy improvement for Convolutional Neural Networks (CNNs), 1.6X and 1.8X improvement for Long Short-Term Memories (LSTMs) and multi-layer perceptrons (MLPs), respectively., Comment: Published as a conference paper at ASPLOS 2020