Tagged articles
DSP
22 articles · Page 1 of 1
The DSP advertising data pipeline was re‑architected by splitting three distinct links—NRR, BT, and CT—and assigning DLF Paimon for massive low‑frequency data, EMR Serverless StarRocks primary tables for high‑value low‑latency queries, and unified service‑layer merging, achieving 2‑minute freshness, sub‑5 ms point queries, ~60% storage cost reduction, and improved fault isolation.
DLF PaimonDSPEMR Serverless
0 likes · 12 min read

GopherTrunk is an open‑source, pure‑Go cluster radio scanner that decodes control channels for ten major digital trunking protocols—including P25, DMR, TETRA, NXDN—and amateur modes, offering zero‑dependency binaries, cross‑platform support, multiple UI options, and advanced DSP pipelines for physical‑penetration testing and radio security research.
DSPGoSDR
0 likes · 15 min read


Didi TechApr 16, 2024 · Artificial Intelligence
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.
DSPGPU accelerationPython
0 likes · 11 min read

This article compares motor‑control engineering and Linux driver development, outlining the core tasks, required knowledge, and typical technologies for each field, and helps readers decide which specialization aligns better with their skills and interests.
DSPLinux driverc-programming
0 likes · 5 min read

This article explains Hulu/Disney’s programmatic advertising ecosystem, detailing the roles of ADN, ADX, SSP, DSP, and DMP, the real‑time bidding workflow, private marketplace order types, and the unified decision engine that balances direct and programmatic ads to maximize revenue.
DSPPMPSSP
0 likes · 15 min read

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%.
AIDSPbudget allocation
0 likes · 11 min read

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.
AdvertisingBidding StrategyDSP
0 likes · 8 min read

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.
Ad TechAdvertisingDSP
0 likes · 13 min read

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.
DSPHexagonSIMD
0 likes · 9 min read

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.
DSPEdge InferenceGPU programming
0 likes · 17 min read

This article explains how Youku combined user‑growth objectives with real‑time bidding (RTB) advertising, designing and optimizing DSP algorithms to maximize high‑value daily active users under cost constraints, covering business background, RTB mechanics, ranking models, pricing strategies, engineering pipelines, and future directions.
AdvertisingAlgorithmDSP
0 likes · 13 min read

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

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.
BackendDSPUser Acquisition
0 likes · 13 min read

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.
DSPbackend architecturedata monitoring
0 likes · 12 min read

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

This article explains the principles of Reduced Instruction Set Computing (RISC), compares its performance advantages over Complex Instruction Set Computing (CISC), and surveys major RISC families such as ARM, MIPS, PowerPC, as well as Intel's low‑power Atom line and their roles in modern devices.
ARMCPU architectureDSP
0 likes · 11 min read

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.
CacheDSPReal-time Computing
0 likes · 10 min read

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.
DSPElasticsearchJenkins
0 likes · 8 min read

Meituan’s demand‑side platform combines real‑time bidding with a two‑service architecture—RecServer for multi‑scenario ad recall and PredictorServer for CTR and conversion‑value prediction—leveraging behavior, location, collaborative‑filtering and matrix‑factorization features, logistic‑regression and GBDT models, and continuous A/B and metric monitoring to optimize ROI.
AdvertisingDSPmachine learning
0 likes · 20 min read

This article explains the principles of Factorization Machines (FM) and Field‑aware Factorization Machines (FFM), their implementation details, and how Meituan‑Dianping applied FFM in a DSP platform to achieve superior CTR and CVR estimation for sparse, high‑dimensional advertising data.
AdvertisingCTR predictionDSP
0 likes · 4 min read

Distributed Segment Processing (DSP) offloads segmenting, hashing, and compression to the backup host, reducing bandwidth and CPU load on Data Domain appliances, while the appliance handles fingerprint filtering and reference tracking, offering bandwidth savings but increasing host CPU usage, so it should be enabled only when host resources permit.
DSPData Domainperformance
0 likes · 4 min read

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.
Ad TechAnti-FraudDSP
0 likes · 24 min read
