An official website of the United States government
A spatial accelerator’s efficiency depends heavily on both its mapper and cost models to generate optimized mappings for various operators of DNN models. However, existing cost models lack a formal boundary over their input programs (operators) for accurate and tractable cost analysis of the mappings, and this results in adaptability challenges to the cost models for new operators. We consider the recently introduced Maestro Data-Centric (MDC) notation and its analytical cost model to address this challenge because any mapping expressed in the notation is precisely analyzable using the MDC’s cost model. In this article, we characterize the set of input operators and their mappings expressed in the MDC notation by introducing a set of conformability rules . The outcome of these rules is that any loop nest that is perfectly nested with affine tensor subscripts and without conditionals is conformable to the MDC notation. A majority of the primitive operators in deep learning are such loop nests. In addition, our rules enable us to automatically translate a mapping expressed in the loop nest form to MDC notation and use the MDC’s cost model to guide upstream mappers. Our conformability rules over the input operators result in a structured mapping space of the operators, which enables us to introduce a mapper based on our decoupled off-chip/on-chip approach to accelerate mapping space exploration. Our mapper decomposes the original higher-dimensional mapping space of operators into two lower-dimensional off-chip and on-chip subspaces and then optimizes the off-chip subspace followed by the on-chip subspace. We implemented our overall approach in a tool called Marvel , and a benefit of our approach is that it applies to any operator conformable with the MDC notation. We evaluated Marvel over major DNN operators and compared it with past optimizers.
more »
« less
benhills/effmed-ice: Release for Reviews of Geophysics
Some notation changes to go with the community notation decided in the review article. Some Jupyter notebooks to reproduce figures in the article.
more »
« less
- PAR ID:
- 10654590
- Publisher / Repository:
- Zenodo
- Date Published:
- Edition / Version:
- v1.1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Processing In-Memory (PIM) is a data-centric computation paradigm that performs computations inside the memory, hence eliminating the memory wall problem in traditional computational paradigms used in Von-Neumann architectures. The associative processor, a type of PIM architecture, allows performing parallel and energy-efficient operations on vectors. This architecture is found useful in vector-based applications such as Hyper-Dimensional (HDC) Reinforcement Learning (RL). HDC is rising as a new powerful and lightweight alternative to costly traditional RL models such as Deep Q-Learning. The HDC implementation of Q-Learning relies on encoding the states in a high-dimensional representation where calculating Q-values and finding the maximum one can be done entirely in parallel. In this article, we propose to implement the main operations of a HDC RL framework on the associative processor. This acceleration achieves up to\(152.3\times\)and\(6.4\times\)energy and time savings compared to an FPGA implementation. Moreover, HDRLPIM shows that an SRAM-based AP implementation promises up to\(968.2\times\)energy-delay product gains compared to the FPGA implementation.more » « less
-
FPGAs have been shown to operate reliably within harsh radiation environments by employing single-event upset (SEU) mitigation techniques, such as configuration scrubbing, triple-modular redundancy, error correction coding, and radiation aware implementation techniques. The effectiveness of these techniques, however, is limited when using complex system-level designs that employ complex I/O interfaces with single-point failures. In previous work, a complex SoC system running Linux applied several of these techniques only to obtain an improvement of 14\(\times\)in mean time to failure (MTTF). A detailed post-radiation fault analysis found that the limitations in reliability were due to the DDR interface, the global clock network, and interconnect. This article applied a number of design-specific SEU mitigation techniques to address the limitations in reliability of this design. These changes include triplicating the global clock, optimizing the placement of the reduction output voters and input flip-flops, and employing a mapping technique called “striping.” The application of these techniques improved MTTF of the mitigated design by a factor of 1.54\(\times\)and thus provides a 22.8X\(\times\)MTTF improvement over the unmitigated design. A post-radiation fault analysis using BFAT was also performed to find the remaining design vulnerabilities.more » « less
-
In this study, we report one group of students’ efforts to create a community meaning for set- builder notation collectively. Students’ ability to develop and interpret set-builder notation is essential to transition-to-proof courses. Conventionally, a colon is used in set-builder notation to (1) separate the universe of discourse from the set’s defining property and (2) indicate an ordering to these components, with the universe to the left and the property to the right of the colon. We describe one normative and non-normative interpretation of this notation and how the students’ individual attribution of conventional meanings for the colon to different inscriptions within the notation helped (or inhibited) them from interpreting these expressions. We report how communicative discourse between the students affected their meanings and discussions.more » « less
-
This article proves, in the case of split groups over arbitrary fields, that all fibers of convolution morphisms attached to parahoric affine flag varieties are paved by products of affine lines and affine lines minus a point. This applies in particular to the affine Grassmannian and to the convolution morphisms in the context of the geometric Satake correspondence. The second part of the article extends these results over $$\mathbb Z$$. Those in turn relate to the recent work of Cass-van den Hove-Scholbach on the geometric Satake equivalence for integral motives, and provide some alternative proofs for some of their results. Comment: 24 pages. Minor error corrected with the addition of Lemma 7.2. Lemma 7.3 added. Material on triviality of morphisms added to section 5. Minor changes in notation. Published versionmore » « less
