Data lakehouses combine the almost infinite scale and diverse tooling of a data lake with the reliability and functionality of a data warehouse. This paper presents extensions that enhance data lake-houses using Apache Iceberg and Apache Spark with performant petabyte-scale row-level operations. The framework is capable of handling both high-density and sparse modifications by either materializing changes at the file level during writes or producing equality and position deletes that are lazily merged with existing data during reads. The paper also outlines essential improvements in determining and applying row-level changes: eliminating expensive shuffles with storage-partitioned joins, minimizing write amplification with runtime filtering, and optimizing the layout of output data with adaptive writes. Our evaluation demonstrates the relative strengths and weaknesses of the various materialization strategies, highlighting the use cases that require each technique. We also show an order of magnitude improvement in performance after our enhancements.

Coarse-grained reconfigurable arrays (CGRAs) are a promising class of architectures conjugating flexibility and efficiency. Devising effective methodologies to map applications onto CGRAs is a challenging task, due to their parallel execution paradigm and constrained hardware resources. In order to handle complex applications, it is important to devise efficient strategies to partition a kernel into pieces that obey resource constraint and methodologies to schedule them on the underlying hardware. In this paper, we tackle these problems by proposing algorithms to address partitioning based on recursive searches over abstract trees. A novel scheduling strategy is also described that, leveraging differences in delays of various operations, is able to efficiently map operations on CGRA architectures. Experimental evidence on kernels derived from a diverse set of data flow graphs and EEMBC benchmarks demonstrate the efficacy of the described methods, which, when combined, achieve a higher runtime performance on a given mesh size than state-of-the-art approaches (as much as 38% for the benchmark applications considered).

Coarse Grained Reconfigurable Arrays (CGRAs) are a promising class of architectures conjugating flexibility and efficiency. Devising effective methodologies to map applications onto CGRAs is a challenging task, due to their parallel execution paradigm and sparse interconnection topology. In this paper we present a scheduling framework that is able to efficiently map operations on CGRA architectures. It leverages differences in delays of various operations, which a reconfigurable architecture always exhibits at run-time, to effectively route data. We call this ability “slack-awareness”. Experimental evidence showcases the benefit of slack-aware scheduling in a coarse-grained re-configurable environment, as more complex applications can be mapped for a given mesh size and more efficient schedules can be achieved, compared to the state of the art methods.

Modular multiplication is the most dominant arithmetic operation in elliptic curve cryptography (ECC), which is a type of public-key cryptography. Montgomery multiplication is commonly used as a technique for the modular multiplication and required scalability since the bit length of operands varies depending on the security levels. Also, ECC is performed in GF(P) or GF(2n), and unified architectures for GF(P) and GF(2n) multiplier are needed. However, in previous works, changing frequency or dual-radix architecture is necessary to deal with delay-time difference between GF(P) and GF(2n) circuits of the multiplier because the critical path of GF(P) circuit is longer. This paper proposes a scalable unified dual-radix architecture for Montgomery multiplication in GF(P) and GF(2n). The proposed architecture unifies 4 parallel radix-216multipliers in GF(P) and a radix-264multiplier in GF(2n) into a single unit. Applying lower radix to GF(P) multiplier shortens its critical path and makes it possible to compute the operands in the two fields using the same multiplier at the same frequency so that clock dividers to deal with the delay-time difference are not required. Moreover, parallel architecture in GF(P) reduces the clock cycles increased by dual-radix approach. Consequently, the proposed architecture achieves to compute GF(P) 256-bit Montgomery multiplication in 0.23 mus.