Capo

Roy, Jarrod A.; Papa, David A.; Adya, Saurabh; Chan, Hayward H.; Ng, Aaron N.; Lu, James F.; Markov, Igor L.

doi:10.1145/1055137.1055184

Cited by 114 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Design Compiler [35] synthesizes the RTL design using a 14nm FinFET technology library [36]. Capo [37], an open-source floorplacer, performs floorplanning. We did part of the floorplanning by hand.…”

Section: ) Dynamic Inference Modulesmentioning

confidence: 99%

AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers

Tuli¹,

Jha²

2023

Preprint

View full text Add to dashboard Cite

Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Despite their efficacy, accelerating the transformer is challenging due to its quadratic computational complexity and large activation sizes. Existing transformer accelerators attempt to prune its tokens to reduce memory access, albeit with high compute overheads. Moreover, previous works directly operate on large matrices involved in the attention operation, which limits hardware utilization. In order to address these challenges, this work proposes a novel dynamic inference scheme, DynaTran, which prunes activations at runtime with low overhead, substantially reducing the number of ineffectual operations. This improves the throughput of transformer inference. We further propose tiling the matrices in transformer operations along with diverse dataflows to improve data reuse, thus enabling higher energy efficiency. To effectively implement these methods, we propose AccelTran, a novel accelerator architecture for transformers. Extensive experiments with different models and benchmarks demonstrate that DynaTran achieves higher accuracy than the state-of-the-art top-k hardware-aware pruning strategy while attaining up to 1.2× higher sparsity. One of our proposed accelerators, AccelTran-Edge, achieves 330K× higher throughput with 93K× lower energy requirement when compared to a Raspberry Pi device. On the other hand, AccelTran-Server achieves 5.73× higher throughput and 3.69× lower energy consumption compared to the state-of-the-art transformer co-processor, Energon.

show abstract

Section: ) Dynamic Inference Modulesmentioning

confidence: 99%

AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers

Tuli¹,

Jha²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A placement algorithm attempts to find a placement that minimizes n i=1 HP W L(x i ). Heuristic methods for placement include simulated annealing [52], continuous optimization [53], and recursive min-cut partitioning [54]. These algorithms can be applied in the present context, but require some modification as current QA architectures do not distinguish between qubits used for penalty functions and qubits used for chains.…”

Section: Placementmentioning

confidence: 99%

Solving SAT and MaxSAT with a Quantum Annealer: Foundations and a Preliminary Report

Bian

Chudak

Macready

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Quantum annealers (QAs) are specialized quantum computers that minimize objective functions over discrete variables by physically exploiting quantum effects. Current QA platforms allow for the optimization of quadratic objectives defined over binary variables (qubits), also known as Ising problems. In the last decade, QA systems as implemented by D-Wave have scaled with Moore-like growth. Current architectures provide 2048 sparsely-connected qubits, and continued exponential growth is anticipated, together with increased connectivity.We explore the feasibility of such architectures for solving SAT and MaxSAT problems as QA systems scale. We develop techniques for effectively encoding SAT -and, with some limitations, MaxSAT-into Ising problems compatible with sparse QA architectures. We provide the theoretical foundations for this mapping, and present encoding techniques that combine offline Satisfiability and Optimization Modulo Theories with on-the-fly placement and routing. Preliminary empirical tests on a current generation 2048-qubit D-Wave system support the feasibility of the approach for certain SAT and MaxSAT problems. 1 Superposition is perhaps the best-known and most surprising aspect of quantum physics (e.g. the famous Scrödinger's cat which is both dead and alive prior to observation).

show abstract