Live briefing
Everything about Spatial architecture
Array of processing elements specialized for parallelizable workloads
In computer science, spatial architectures are a kind of computer architecture leveraging many collectively coordinated and directly communicating processing elements (PEs) to quickly and efficiently run highly parallelizable kernels. The "spatial" term comes from processing element instances being typically arranged in an array or grid, both logically and in the silicon design. Their most common workloads consist of matrix multiplications, convolutions, or, in general, tensor contractions. As such, spatial architectures are often used in AI accelerators. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Spatial architectureA 5-minute orientation
- Skim a recent paper: Extended reality for enhancing spatial ability in architecture design educationInfluential work since 2022
- Pick up a classic book: Space, time and architectureThe most-reprinted book on the subject
- Read the landmark paper: Exploring tissue architecture using spatial transcriptomicsCited 1,805 times
- Go sideways: Stream processingA closely related topic
- Go sideways: Coarse-grained reconfigurable arrayA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Exploring tissue architecture using spatial transcriptomics
The architecture of perceptual spatial interactions
Spatial cellular architecture predicts prognosis in glioblastoma
Molecules into Cells: Specifying Spatial Architecture
The Impact of Centromeres on Spatial Genome Architecture
Architecture of spatial circuits in the hippocampal region
Effect of spatial architecture on cellular colonization
Spatial architecture of development and disease
🆕 Influential since 2022
Extended reality for enhancing spatial ability in architecture design education
Single-cell and spatial architecture of primary liver cancer
A hybrid spatial–temporal deep learning architecture for lane detection
An Efficient Multiscale Spatial Rearrangement MLP Architecture for Image Restoration
Reconfigurable Architecture for Spatial Sensing in Wideband Radio Front-End
📚 Books worth reading
Space, time and architectureSigfried Giedion · 1941
The hidden dimensionEdward Twitchell Hall · 1966
Cognitive ArchitectureAnn Sussman, Justin B. Hollander · 2014
The language of spaceBryan Lawson · 2001- 📕Rethinking Israeli spaceErez Tzfadia · 2011
Constructing placeSarah Menin · 2003
Public and private spaces of the cityAli Madanipour · 2003
Experience and conflictPanu Lehtovuori · 2005
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Stream processing In computer science, stream processing (also known as event stream processing, data stream processing, or distributed stream processing) is a programming…
- Coarse-grained reconfigurable array A coarse-grained reconfigurable array or coarse-grained reconfigurable architecture (CGRA) is a class of spatial computing hardware built from a relatively…
- Dataflow In computing, dataflow is a broad concept, which has various meanings depending on the application and context. In the context of software architecture…
- Dataflow architecture Dataflow architecture is a dataflow-based computer architecture that directly contrasts the traditional von Neumann architecture or control flow architecture…
- General-purpose computing on graphics processing units General-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles…
- Hardware/software co-design Hardware/software co-design (often shortened as HW/SW co-design) is a system-level design methodology in which hardware and software components are developed…
- Manycore processor Manycore processors are special kinds of multi-core processors designed for a high degree of parallel processing, containing numerous simpler, independent…
- Computing with memory Computing with memory (or in-memory computing, IMC) is a paradigm that performs computations directly within memory arrays (RAM, RRAM, PCM) rather than…