An official website of the United States government
In-memory processing offers a promising solution for enhancing the performance of data-intensive applications. While analog in-memory computing demonstrates remarkable efficiency, its limited precision is suitable only for approximate computing tasks. In contrast, digital in-memory computing delivers the deterministic precision necessary to accelerate high-assurance applications. Current digital in-memory computing methods typically involve manually breaking down arithmetic operations into in-memory compute kernels. In contrast, traditional digital circuits are synthesized through intricate and automated design workflows. In this article, we introduce a logic synthesis framework called LOGIC, which facilitates the translation of high-level applications into digital in-memory compute kernels that can be executed using non-volatile memory. We propose techniques for decomposing element-wise arithmetic operations into in-memory kernels while minimizing the number of in-memory operations. Additionally, we optimize the sequence of in-memory operations to reduce non-volatile memory utilization. To address the NP-hard execution sequencing optimization problem, we have developed twolook-aheadalgorithms that offer practical solutions. Additionally, we leverage data layout reorganization to efficiently accelerate applications that heavily rely on sparse matrix-vector multiplication operations. Our experimental evaluations demonstrate that our proposed synthesis approach improves the area and latency of fixed-point multiplication by 84% and 20% compared to the state-of-the-art, respectively. Moreover, when applied to scientific computing applications sourced from the SuiteSparse Matrix Collection, our design achieves remarkable improvements in area, latency, and energy efficiency by factors of 4.8×, 2.6×, and 11×, respectively.
more »
« less
UltraPrecise: A GPU-Based Framework for Arbitrary-Precision Arithmetic in Database Systems
Fixed-point decimal operations in databases with arbitrary-precision arithmetic refer to the ability to store and operate decimal fraction numbers with an arbitrary length of digits. This type of operation has become a requirement for many applications, including scientific databases, financial data processing, geometric data processing, and cryptography. However, the state-of-the-art fixed-point decimal technology either provides high performance for low-precision operations or supports arbitrary-precision arithmetic operations at low performance. In this paper, we present a design and implementation of a framework called UltraPrecise which supports arbitraryprecision arithmetic for databases on GPU, aiming to gain high performance for arbitrary-precision arithmetic operations. We build our framework based on the just-in-time compilation technique and optimize its performance via data representation design, PTX acceleration, and expression scheduling. UltraPrecise achieves comparable performance to other high-performance databases for low-precision arithmetic operations. For highprecision, we show that UltraPrecise consistently outperforms existing databases by two orders of magnitude, including workloads of RSA encryption and trigonometric function approximation.
more »
« less
- PAR ID:
- 10530377
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-1715-2
- Page Range / eLocation ID:
- 3837 to 3850
- Subject(s) / Keyword(s):
- database, parallel computing, fixed-point arithmetic, GPU
- Format(s):
- Medium: X
- Location:
- Utrecht, Netherlands
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Modern vector processors support a wide variety of instructions for fixed-point digital signal processing. These instructions support a proliferation of rounding, saturating, and type conversion modes, and are often fused combinations of more primitive operations. While these are common idioms in fixed-point signal processing, it is difficult to use these operations in portable code. It is challenging for programmers to write down portable integer arithmetic in a C-like language that corresponds exactly to one of these instructions, and even more challenging for compilers to recognize when these instructions can be used. Our system, Pitchfork, defines a portable fixed-point intermediate representation, FPIR, that captures common idioms in fixed-point code. FPIR can be used directly by programmers experienced with fixed-point, or Pitchfork can automatically lift from integer operations into FPIR using a term-rewriting system (TRS) composed of verified manual and automatically-synthesized rules. Pitchfork then lowers from FPIR into target-specific fixed-point instructions using a set of target-specific TRSs. We show that this approach improves runtime performance of portably-written fixed-point signal processing code in Halide, across a range of benchmarks, by geomean 1.31× on x86 with AVX2, 1.82× on ARM Neon, and 2.44× on Hexagon HVX compared to a standard LLVM-based compiler flow, while maintaining or improving existing compile times.more » « less
-
Abstract Solving linear systems, often accomplished by iterative algorithms, is a ubiquitous task in science and engineering. To accommodate the dynamic range and precision requirements, these iterative solvers are carried out on floating-point processing units, which are not efficient in handling large-scale matrix multiplications and inversions. Low-precision, fixed-point digital or analog processors consume only a fraction of the energy per operation than their floating-point counterparts, yet their current usages exclude iterative solvers due to the cumulative computational errors arising from fixed-point arithmetic. In this work, we show that for a simple iterative algorithm, such as Richardson iteration, using a fixed-point processor can provide the same convergence rate and achieve solutions beyond its native precision when combined with residual iteration. These results indicate that power-efficient computing platforms consisting of analog computing devices can be used to solve a broad range of problems without compromising the speed or precision.more » « less
-
A multiverse database transparently presents each application user with a flexible, dynamic, and independent view of shared data. This transformed view of the entire database contains only information allowed by a centralized and easily-auditable privacy policy. By enforcing the privacy policy once, in the database, multiverse databases reduce programmer burden and eliminate many frontend bugs that expose sensitive data. Multiverse databases' per-user transformations risk expensive queries if applied dynamically on reads, or impractical storage requirements if the database proactively materializes policy-compliant views. We propose an efficient design based on a joint dataflow across "universes" that combines global, shared computation and cached state with individual, per-user processing and state. This design, which supports arbitrary SQL queries and complex policies, imposes no performance overhead on read queries. Our early prototype supports thousands of parallel universes on a single server.more » « less
-
Verbal labels for math concepts influence multiple aspects of math learning. In this study, we examined the influence of point labels (e.g., .42 as “point four two”), decomposed labels (e.g., “four tenths and two hundredths”), and common-unit labels (e.g., “forty-two hundredths”) on children’s processing and representation of decimal magnitudes. We randomly assigned 162 5th- and 6th-graders to briefly learn decomposed, common-unit, or point labels. Children then completed measures of decimal magnitude processing and representation. We found that the place-value labels (i.e., decomposed and common-unit labels) each showed unique advantages in reducing the whole-number bias, and common-unit labels also reduced componential processing. No difference was found in the ratio effect – which served as an index of the precision of decimal magnitude representation - among children from the three conditions. These findings add to our understanding of the role of verbal labels in math learning and have important implications for instructional practices.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICDE60146.2024.00294
