Dataflow and tile size choices, which we collectively refer to as mappings, dictate the efficiency (i.e., latency and energy) of DNN accelerators. Rapidly evolving DNN models is one of the major challenges for DNN accelerators since the optimal mapping heavily depends on the layer shape and size. To maintain high efficiency across multiple DNN models, flexible accelerators that can support multiple mappings have emerged. However, we currently lack a metric to evaluate accelerator flexibility and quantitatively compare their capability to run different mappings.

The hardware security crisis brought on by recent speculative execution attacks has shown that it is crucial to adopt a security-conscious approach to architecture research, analyzing the security of promising architectural techniques before they are deployed in hardware. This paper offers the first security analysis of cache compression, one such promising technique that is likely to appear in future processors. We find that cache compression is insecure because the compressibility of a cache line reveals information about its contents.

AI-enabled applications such as augmented and virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for various sub-tasks such as object detection, image segmentation, eye-tracking, speech recognition, and so on. Because of the diversity of the sub-tasks, the layers within and across the DNN models are highly heterogeneous in operation and shape.

This paper presents Sparseloop, the first infrastructure that implements an analytical design space exploration methodology for sparse tensor accelerators. Sparseloop comprehends a wide set of architecture specifications including various sparse optimization features such as compressed tensor storage. Using these specifications, Sparseloop can calculate a design's energy efficiency while accounting for both optimization savings and metadata overhead at each storage and compute level of the architecture using stochastic tensor density models.

The efficiency of an accelerator depends on three factors -- mapping, deep neural network (DNN) layers, and hardware -- constructing extremely complicated design space of DNN accelerators. To demystify such complicated design space and guide the DNN accelerator design for better efficiency, we propose an analytical cost model, MAESTRO. MAESTRO receives DNN model description and hardware resources information as a list, and mapping described in a data-centric representation we propose as inputs.

Modern day computing increasingly relies on specialization to satiate growing performance and efficiency requirements. A core challenge in designing such specialized hardware architectures is how to perform mapping space search, i.e., search for an optimal mapping from algorithm to hardware. Prior work shows that choosing an inefficient mapping can lead to multiplicative-factor efficiency overheads. Additionally, the search space is not only large but also non-convex and non-smooth, precluding advanced search techniques.

Generalized tensor algebra is a prime candidate for acceleration via customized ASICs. Modern tensors feature a wide range of data sparsity, with the density of non-zero elements ranging from 10^-6% to 50%. This paper proposes a novel approach to accelerate tensor kernels based on the principle of hierarchical elimination of computation in the presence of sparsity.

In recent years, many accelerators have been proposed to efficiently process sparse tensor algebra applications (e.g., sparse neural networks). However, these proposals are single points in a large and diverse design space. The lack of systematic description and modeling support for these sparse tensor accelerators impedes hardware designers from efficient and effective design space exploration. This paper first presents a unified taxonomy to systematically describe the diverse sparse tensor accelerator design space.

Finding high-quality mappings of Deep Neural Network (DNN) models onto tensor accelerators is critical for efficiency. State-of-the-art mapping exploration tools use remainderless (i.e., perfect) factorization to allocate hardware resources, through tiling the tensors, based on factors of tensor dimensions. This limits the size of the search space, (i.e., mapspace), but can lead to low resource utilization. We introduce a new mapspace, Ruby, that adds remainders (i.e., imperfect factorization) to expand the mapspace with high-quality mappings for user-defined architectures.

The data partitioning and scheduling strategies used by DNN accelerators to leverage reuse and perform staging are known as dataflow, and they directly impact the performance and energy efficiency of DNN accelerator designs. An accelerator microarchitecture dictates the dataflow(s) that can be employed to execute a layer or network.