DSP | BestHub

Didi Tech

Apr 16, 2024 · Artificial Intelligence

Optimizing DSP Deep Model Latency by Externalizing Feature Processing with EzFeaFly

By externalizing feature processing with the EzFeaFly tool and feeding a dense index/value tensor directly to the GPU, the DSP platform decouples feature transformation from model inference, cutting instance usage by ~40%, reducing inference latency 70‑80%, and achieving over 60% end‑to‑end latency improvement while lowering costs.

DSPFeature EngineeringGPU Acceleration

0 likes · 11 min read

Optimizing DSP Deep Model Latency by Externalizing Feature Processing with EzFeaFly

DataFunSummit

Mar 19, 2022 · Artificial Intelligence

Intelligent Advertising in Real Estate: Challenges, Practices, and Insights from Beike

This article presents Beike's experience in intelligent real‑estate advertising, detailing the business background, key technical challenges such as conversion‑rate estimation, delayed‑feedback modeling, GEO targeting, and budget allocation, and sharing practical solutions that improved conversion rates by over 10%.

AIDSPReal Estate

0 likes · 11 min read

Intelligent Advertising in Real Estate: Challenges, Practices, and Insights from Beike

Youzan Coder

Jul 6, 2021 · Big Data

Overview of Youzan DSP Advertising Platform and Its Testing Challenges

The article outlines Youzan’s Demand‑Side Platform, detailing its ad channels, placement and bidding strategies, data tracking and order attribution mechanisms, and multi‑channel feedback, while highlighting testing difficulties such as Kafka‑driven tracking, link parameter loss, UUID inconsistencies, and the need for robust third‑party API monitoring.

Bidding StrategyDSPTesting

0 likes · 8 min read

Overview of Youzan DSP Advertising Platform and Its Testing Challenges

DataFunSummit

Jan 7, 2021 · Backend Development

Architecture and Practices of 58.com Alliance Advertising Platform

This article presents a comprehensive overview of the 58.com alliance advertising platform, detailing its business model, core modules such as SSP, DSP, media and creative platforms, system architecture, performance optimizations, big‑data processing, and future directions for programmatic creative generation.

Big DataDSPPerformance Optimization

0 likes · 13 min read

Architecture and Practices of 58.com Alliance Advertising Platform

OPPO Kernel Craftsman

Sep 30, 2020 · Mobile Development

SIMD Acceleration Techniques on Qualcomm Hexagon DSP for Mobile Devices

The article explains how SIMD acceleration on Qualcomm’s Hexagon DSP, using its HVX vector engine and specialized instructions, can off‑load compute‑intensive tasks such as image, video, and AI processing from the CPU, delivering up to 8× speed‑up, lower power consumption, reduced thermal throttling, and longer battery life on mobile devices.

DSPHexagonMobile

0 likes · 9 min read

SIMD Acceleration Techniques on Qualcomm Hexagon DSP for Mobile Devices

Tencent Music Tech Team

Apr 30, 2020 · Mobile Development

Edge Deep Learning Inference on Mobile Devices: Challenges, Hardware Diversity, and Optimization Strategies

Edge deep learning inference on mobile devices faces hardware and software fragmentation, diverse CPUs, GPUs, DSPs, and NPUs, and limited programmability; optimization techniques such as model selection, quantization, and architecture‑specific tuning enable real‑time performance, with most inference on CPUs, GPUs offering 5–10× speedups, and co‑processor support varying across Android and iOS.

DSPGPU programmingNPU

0 likes · 17 min read

Edge Deep Learning Inference on Mobile Devices: Challenges, Hardware Diversity, and Optimization Strategies

Architects' Tech Alliance

Jan 16, 2020 · Fundamentals

FPGA, ASIC, and DSP: Competition, Cooperation, and Future Prospects

The article examines the evolving roles of FPGA, ASIC, and DSP in semiconductor technology, highlighting how advances in FPGA have reduced cost and power, enabling it to challenge ASIC and DSP markets, while discussing their distinct strengths, development flows, and the likely coexistence of these three technologies in the future.

ASICDSPFPGA

0 likes · 11 min read

FPGA, ASIC, and DSP: Competition, Cooperation, and Future Prospects

Youku Technology

Dec 6, 2019 · Backend Development

Technical Architecture and Strategies of Youku's Demand‑Side Platform (DSP)

Youku’s Demand‑Side Platform combines integrated RTB channel access, sophisticated delivery strategies, personalized recommendation algorithms, and real‑time monitoring to acquire and re‑engage segmented users, optimizing budgets, creative performance, and conversion funnels while continuously iterating on traffic value estimation and bidding models.

DSPadvertisingalgorithm

0 likes · 13 min read

Technical Architecture and Strategies of Youku's Demand‑Side Platform (DSP)

DataFunTalk

Dec 6, 2019 · Backend Development

Technical Architecture and Practices of Youku's Demand‑Side Platform (DSP)

This article explains how Youku built and iterated its Demand‑Side Platform, covering business goals, system architecture, channel integration, bidding and frequency strategies, material selection, smooth budget delivery, retargeting, algorithmic recall, data monitoring, and conversion‑funnel optimization to drive user growth.

DSPReal-Time Biddingadvertising

0 likes · 12 min read

Technical Architecture and Practices of Youku's Demand‑Side Platform (DSP)

Qunar Tech Salon

Sep 5, 2019 · Artificial Intelligence

Implementing Bilinear Interpolation on FPGA for Neural Network Acceleration

The article explains the principles of bilinear interpolation, why it is needed for smooth image scaling in neural‑network layers such as Interp and Resize, and details FPGA‑specific optimizations—including lookup‑table based coefficient pre‑computation, two‑line BRAM caching, and index‑driven data swapping—to reduce DSP usage and improve throughput.

BRAMBilinear InterpolationDSP

0 likes · 14 min read

Implementing Bilinear Interpolation on FPGA for Neural Network Acceleration

HomeTech

Jan 18, 2019 · Big Data

Data Mill: A Real‑Time Spark Streaming Framework for DSP Business Support

Data Mill is a Spark‑Streaming‑based real‑time computation framework that abstracts tasks as DataFrames, enables SQL‑driven development, and supports DSP business requirements by reducing latency to 15‑30 minutes while providing a scalable architecture, caching strategy, and automated fault handling.

Big DataDSPSQL

0 likes · 10 min read

Data Mill: A Real‑Time Spark Streaming Framework for DSP Business Support

360 Quality & Efficiency

Oct 12, 2018 · Backend Development

Automated Testing and Monitoring Solution for DSP Advertising Business

The article outlines a comprehensive automated testing framework for a DSP advertising platform, covering income, interface, and log layers, and detailing the use of protobuf, Pytest, Logstash, ElasticSearch, Jenkins, and Allure to achieve efficient, real‑time quality assurance and continuous integration.

Automated TestingDSPElasticsearch

0 likes · 8 min read

Automated Testing and Monitoring Solution for DSP Advertising Business

High Availability Architecture

Aug 5, 2015 · Big Data

DSP Advertising System Architecture and Key Technologies

This article presents a comprehensive overview of DSP advertising system architecture, covering real‑time bidding infrastructure, audience targeting, data processing pipelines using Hadoop, Spark and Storm, click‑through‑rate prediction models, and anti‑fraud mechanisms, offering practical insights for engineers building high‑performance ad platforms.

Big DataDSPReal-Time Bidding

0 likes · 24 min read

DSP Advertising System Architecture and Key Technologies