27,049 technical terms and definitions
mosfet scaling 1970s step 13 confront velocity saturation limit, confront velocity saturation limit
MOSFET Scaling (1970s): Step 13 — Confronting the Velocity Saturation Limit The assumption Dennard's own paper flagged as eventually breaking. Dennard-style scaling assumes…
mosfet scaling 1970s step 9 control threshold voltage fundamentals, control threshold voltage fundamentals
MOSFET Scaling (1970s): Step 9 — Threshold Voltage Control Fundamentals Why Vt had to be set deliberately rather than inherited from doping alone. Threshold voltage, V_t, is…
mosfet scaling 1970s step 11 design depletion load nmos pair, design depletion load nmos pair
MOSFET Scaling (1970s): Step 11 — Designing the Depletion-Load NMOS Pair How enhancement switch plus depletion load became the standard 1970s NMOS logic cell. With independent…
mosfet scaling 1970s step 7 develop locos field isolation, develop locos field isolation
MOSFET Scaling (1970s): Step 7 — Developing LOCOS Field Isolation Recessed, selectively grown oxide replaces simple thick-field-oxide isolation. As transistor density rose…
mosfet scaling 1970s step 16 implement channel stop punchthrough control, implement channel stop punchthrough control
MOSFET Scaling (1970s): Step 16 — Implementing Channel-Stop and Punchthrough Control Two related leakage paths that scaling opened up between and within devices. Beyond…
mosfet scaling 1970s step 18 integrate scaling rules into manufacturable flow, integrate scaling rules into manufacturable flow
MOSFET Scaling (1970s): Step 18 — Integrating Scaling Rules Into a Manufacturable Flow Turning nine separate fixes into one coherent, repeatable process. By the mid-to-late 1970s…
mosfet scaling 1970s step 14 manage hot carrier degradation, manage hot carrier degradation
MOSFET Scaling (1970s): Step 14 — Managing Hot-Carrier Degradation High-field carriers start damaging the gate oxide they pass beneath. The same high longitudinal fields that…
mosfet scaling 1970s step 5 push channel length against litho limits, push channel length against litho limits
MOSFET Scaling (1970s): Step 5 — Pushing Channel Length Against Lithography Limits Mask alignment tolerance became the hard floor on channel length. Channel length is defined…
mosfet scaling 1970s step 19 push toward one micron node metrology, push toward one micron node metrology
MOSFET Scaling (1970s): Step 19 — Pushing Toward the 1-Micron Node, Metrology Limits Measurement control becomes as hard a problem as process control. As the integrated flow…
mosfet scaling 1970s step 3 rederive supply voltage under scaling, rederive supply voltage under scaling
MOSFET Scaling (1970s): Step 3 — Re-Deriving Supply Voltage Under Scaling Why dropping V_DD was the hardest part of the rule set to adopt. Of all the Dennard-rule parameters…
mosfet scaling 1970s step 20 set stage for fixed voltage scaling break, set stage for fixed voltage scaling break
MOSFET Scaling (1970s): Step 20 — Setting the Stage for the Fixed-Voltage Scaling Break Where this series ends and the next scaling era begins. This series has tracked 1970s…
mosfet scaling 1970s step 8 shrink source drain junction depth, shrink source drain junction depth
MOSFET Scaling (1970s): Step 8 — Shrinking Source/Drain Junction Depth Shallow junctions become necessary once channel length drops below a few micrometers. Dennard scaling calls…
mosfet scaling 1970s step 4 thin the gate oxide under control, thin the gate oxide under control
MOSFET Scaling (1970s): Step 4 — Thinning the Gate Oxide Under Control How thermal oxidation was pushed from ~120 nm toward the 50-70 nm range. Gate oxide thickness sets both…
mosfet scaling 1970s step 12 trace short channel threshold rolloff, trace short channel threshold rolloff
MOSFET Scaling (1970s): Step 12 — Tracing Short-Channel Threshold Rolloff The first clearly non-ideal effect scaled devices ran into. As channel lengths pushed below roughly 2-3…
mosfet switching loss prediction, mosfet switching loss, switching loss prediction, mosfet switching, switching loss, loss prediction
MOSFET Switching Loss Prediction with Machine Learning Introduction & Motivation MOSFET Switching Loss Prediction with Machine Learning addresses a central problem in power MOSFET…
moth-flame algorithm
Moth-Flame Algorithm Introduction & Motivation Moth-Flame Algorithm addresses a central problem in ml process control and convergence-speed-iterations prediction: how to Predict…
graph algorithms
Motif Detection (Network Motifs) is the graph mining task of finding statistically significant subgraph patterns — small connected subgraphs that appear in a network significantly…
video understanding
Motion compensation is the alignment process that maps neighboring frames into a common reference frame so temporal information can be fused without ghosting artifacts - it is…
multimodal ai
Motion Compensation is aligning frames using estimated motion to reduce temporal redundancy and improve reconstruction - It improves compression, interpolation, and restoration…
robotics
Motion Forecasting is a broader generalization of trajectory prediction — predicting the future state (position, velocity, pose, intention) of dynamic agents in an environment…
motion planning path finding, motion planning path, planning path finding, motion planning, planning path, path finding
Motion Planning Path Finding Introduction & Motivation Motion Planning Path Finding addresses a central problem in robotics process control and path-planning-collision-free…
path planning, rrt, rrt star, prm, a star, trajectory optimization, robot planning
Motion planning computes a feasible collision-free path or trajectory from a start state to a goal under geometry, dynamics, and constraints. Robots, autonomous vehicles, drones…
motion segmentation moving object, motion segmentation moving, segmentation moving object, motion segmentation, segmentation moving, moving object
Motion Segmentation Moving Object Introduction & Motivation Motion Segmentation Moving Object addresses a central problem in vision process control…
video generation
Motion transfer is a video generation technique that applies the motion patterns captured from a source video to a different target subject, enabling one character or object…
video generation
Motion transfer is the technique that applies movement patterns from a source sequence to a target subject or style representation - it enables controllable animation…
production
Motion waste is the unnecessary movement of people that does not add value to the product - it is a major source of lost labor time, ergonomic risk, and process inconsistency.…
manufacturing operations
Motion Waste is unnecessary movement by operators or equipment caused by poor workplace design or process sequencing - It increases fatigue, cycle time, and ergonomic risk. What…
field oriented control, FOC motor drive, vector control, direct torque control
Motor control. regulates electric-machine torque, speed, position or flux by coordinating sensing, real-time algorithms and a power inverter. A motor drive transforms DC-bus…
h bridge, gate driver, bldc driver, stepper motor driver, robot actuator driver, motor efficiency
motor driver is a power integrated circuit that translates low-energy control commands into controlled voltage and current for an electric motor. Motor drivers connect digital…
model optimization
Movement Pruning is a pruning method that removes weights based on optimization trajectory movement rather than magnitude alone - It is effective in transfer-learning…
Movement Pruning Introduction & Motivation Movement Pruning addresses a central problem in reducing the size and cost of compression models: how to Reduce the size and inference…
Movement Pruning (Extended Study) Introduction & Motivation Movement Pruning (Extended Study) addresses a central problem in reducing the size and cost of compression models: how…
Movement Pruning (Extended Study) Introduction & Motivation Movement Pruning (Extended Study) addresses a central problem in reducing the size and cost of compression models: how…
point-to-point, communication, blocking, non-blocking
MPI Point-to-Point Communication Advanced is a set of techniques for direct message exchange between pairs of processes in distributed systems — enabling efficient, scalable data…
collective, operations, optimization, barrier, broadcast, reduce
MPI Collective Operations Optimization is the enhancement of group communication primitives that involve multiple processes simultaneously, maximizing throughput and minimizing…
scalability, optimization, communication, efficiency
MPI Scalability Optimization at Scale is a performance engineering methodology optimizing Message Passing Interface communication efficiency at thousands to millions of processes…
mpi persistent request, mpi one sided rma, mpi window fence, mpi derived datatype
Advanced MPI Communication encompasses sophisticated messaging primitives beyond basic send/receive, including persistent requests for reduced overhead, one-sided…
message passing interface, distributed memory
MPI (Message Passing Interface) is the dominant standard programming model for distributed-memory high-performance computing. It defines portable APIs that let multiple processes…
allreduce broadcast, mpi optimization, collective algorithm
MPI Collective Communication Optimization is the design and tuning of group communication operations (broadcast, reduce, allreduce, allgather, alltoall) in MPI programs…
allreduce allgather, mpi broadcast, collective optimization, ring allreduce algorithm
MPI Collective Communication Operations are the coordinated multi-process communication patterns where all (or a defined subset of) processes in a communicator participate…
allreduce mpi, broadcast gather scatter, collective optimization, mpi communication pattern
MPI Collective Communication encompasses the coordinated communication operations where all processes in a communicator group participate — including broadcast, scatter, gather…
collective algorithm topology, butterfly allreduce, ring allreduce deep learning, recursive halving doubling
MPI Collective Communication Optimization: Algorithm Selection for Topology — specialized allreduce algorithms balancing latency and bandwidth optimized for different network…
mpi allreduce algorithm, mpi broadcast scatter gather, mpi non blocking collective, mpi topology aware communication
MPI Collective Communication Optimization is the practice of selecting, tuning, and implementing the most efficient algorithms for multi-node communication patterns (AllReduce…
broadcast scatter gather, mpi allreduce, mpi communication patterns
MPI Collective Operations are communication patterns where all processes in a communicator participate simultaneously — implementing broadcast, scatter, gather, reduce…
mpi type, non contiguous data, mpi struct, mpi vector datatype
MPI Derived Datatypes are the user-defined data layout descriptors that allow MPI to send and receive non-contiguous or heterogeneous data in a single communication operation…
mpi type struct, noncontiguous data communication, mpi pack unpack, custom mpi datatype
MPI Derived Datatypes are user-defined type descriptors that enable efficient communication of noncontiguous, heterogeneous, or structured data without manual packing into…
parallel, file, I/O, HDF5, collective, strided
MPI-IO Parallel File I/O is a standardized API for efficient coordinated file access by multiple processes, eliminating bottlenecks from centralized I/O and enabling scalable data…
isend irecv asynchronous, mpi request wait test, communication computation overlap mpi, mpi persistent communication
MPI Non-Blocking Communication is a message passing paradigm where send and receive operations return immediately without waiting for the message transfer to complete, allowing…
mpi rma, mpi put get, remote memory access mpi
MPI One-Sided Communication (RMA) is the MPI paradigm where a single process can directly read from (Get) or write to (Put) memory on a remote process without the remote process…
mpnn, graph neural networks
MPNN Framework is a formal graph neural network template defined by message, update, and readout operators - It standardizes how information moves along edges, is integrated…