compression-aware-neural-architecture-search machine learning
Compression-Aware Neural Architecture Search Introduction & Motivation Compression-Aware Neural Architecture Search addresses a central problem in reducing the size and cost…
29,230 technical terms and definitions
Compression-Aware Neural Architecture Search Introduction & Motivation Compression-Aware Neural Architecture Search addresses a central problem in reducing the size and cost…
Compression-Aware Neural Architecture Search (Extended Study) Introduction & Motivation Compression-Aware Neural Architecture Search (Extended Study) addresses a central problem…
Compression-Aware Neural Architecture Search (Extended Study) Introduction & Motivation Compression-Aware Neural Architecture Search (Extended Study) addresses a central problem…
compression codec algorithm, compression codec, codec algorithm
Compression Codec Algorithm Introduction & Motivation Compression Codec Algorithm addresses a central problem in systems process control and compression-ratio-cpu-trade-off…
Compression for Edge Deployment Introduction & Motivation Compression for Edge Deployment addresses a central problem in reducing the size and cost of compression models: how…
Compression for Edge Deployment (Extended Study) Introduction & Motivation Compression for Edge Deployment (Extended Study) addresses a central problem in reducing the size…
Compression for Edge Deployment (Extended Study) Introduction & Motivation Compression for Edge Deployment (Extended Study) addresses a central problem in reducing the size…
packaging
Compression molding is the encapsulation method that cures molding compound by compressing material directly over package arrays in a closed mold - it is widely used for thin…
compression molding flash defect prediction, compression molding flash, molding flash defect, flash defect prediction, compression molding, molding flash, flash defect
Compression Molding Flash Defect Prediction with Machine Learning Introduction & Motivation Compression Molding Flash Defect Prediction with Machine Learning addresses a central…
compression molding void prediction machine learning, compression molding, void prediction machine, compression molding void prediction, compression molding void, molding void
Compression Molding Void Prediction with Machine Learning Introduction & Motivation Compression Molding Void Prediction with Machine Learning addresses a central problem…
Compression of Transformer Models Introduction & Motivation Compression of Transformer Models addresses a central problem in reducing the size and cost of compression models: how…
Compression of Transformer Models (Extended Study) Introduction & Motivation Compression of Transformer Models (Extended Study) addresses a central problem in reducing the size…
Compression of Transformer Models (Extended Study) Introduction & Motivation Compression of Transformer Models (Extended Study) addresses a central problem in reducing the size…
compressive film stress, compressive strain, thin film compressive stress, compressive stress engineering
Compressive stress represents a fundamental physical and piezoresistive state in semiconductor thin films, characterized by internal stress vectors that push adjacent atomic…
llm architecture
Compressive Transformer is the long-range transformer architecture that extends context access through a hierarchical memory system — compressing older attention memories into…
optimization
Computation-communication overlap is the optimization technique that schedules data exchange concurrently with ongoing model computation - it reduces visible communication cost…
computational lithography, device modeling, semiconductor simulation, pde, ilt, opc
Semiconductor Manufacturing: Computational Challenges Overview Semiconductor manufacturing represents one of the most mathematically and computationally intensive industrial…
CFD Vacuum Gas Dynamics, Conductance, and Purge Kinetics 1. Why vacuum flow needs regime-aware modeling Semiconductor process chambers operate across a wide pressure range.…
cfd, simulation
Computational Fluid Dynamics for Cooling (CFD) is the numerical simulation of airflow and liquid flow patterns around and through electronic cooling systems — solving…
ilt inverse lithography, smo source mask optimization, curvilinear mask, gpu computational lithography, opc
Computational Lithography and Optical Proximity Correction constitute the mathematical and algorithmic backbone of sub-wavelength semiconductor patterning. Operating deep within…
computational lithography runtime prediction, computational lithography runtime, lithography runtime prediction, computational lithography, lithography runtime, runtime prediction
Computational Lithography Runtime Prediction with Machine Learning Introduction & Motivation Computational Lithography Runtime Prediction with Machine Learning addresses a central…
decomposition, pattern recognition, abstraction, algorithm design, pseudocode, recursion, problem solving
Computational thinking is the skill of turning a messy, real-world problem into a sequence of steps precise enough for the fetch-decode-execute cycle from Topic 1 to actually…
decomposition abstraction pattern recognition, pseudocode for beginners, algorithm design thinking, problem solving computer science
Computational thinking is the mental skill of turning a messy, real-world problem into something precise enough that a machine with no judgment or common sense can still carry it…
flops, training compute, model flops utilization, compute budget
Compute, in AI, means floating-point operations — FLOPs — the raw arithmetic a training run or inference request actually consumes, and it functions as the field's basic unit…
model optimization
Compute-Bound Operations is operators whose speed is limited by arithmetic capacity rather than memory transfer - They benefit most from vectorization and accelerator-specific…
compute-bound, arithmetic intensity, machine balance, roofline compute ceiling
Compute bound describes a workload whose elapsed time is limited primarily by available arithmetic execution rather than data movement or I/O. It tells engineers that more…
hardware
Compute capability is the GPU architecture version identifier that defines supported instructions, memory features, and performance behaviors - it determines what low-level…
Overlap, pipelining, latency
Compute-Communication Overlap Pipelining is an advanced GPU optimization technique enabling simultaneous execution of kernel computation on GPU with data transfer between host…
training
Compute-constrained regime is the training regime where available compute is the primary limiting factor on model and data scaling choices - it forces tradeoffs between model…
pcie gen5 cxl, memory disaggregation, cache coherent interconnect, cxl memory pooling
CXL (Compute Express Link) is an open interconnect standard that lets CPUs, accelerators, and memory devices share a coherent view of memory over the physical PCIe wire. Ordinary…
infrastructure
Compute fabric is the interconnection layer that links processors, accelerators, memory, and storage into composable pooled resources - it enables dynamic allocation and better…
chip export controls, compute thresholds, 10^25 flop, sastry et al 2024, computing power and the governance of ai, training compute reporting, executive order 14110
Compute governance is the use of control over computing resources, especially the specialized chips and data centers used to train and run large AI models, as a lever for shaping…
CIM, processing, architecture
Compute-in-memory (CIM), also called processing-in-memory (PIM), is a processor architecture that performs computation directly inside or right next to the memory that holds…
compute-in-memory adc quantization error prediction, compute-in-memory adc quantization, adc quantization error, quantization error prediction, adc quantization
Compute-in-Memory ADC Quantization Error Prediction with Machine Learning Introduction & Motivation Compute-in-Memory ADC Quantization Error Prediction with Machine Learning…
processing in memory, in-memory computing, CIM, PIM
Compute in memory. moves selected computation into or immediately beside memory arrays so that operands do not repeatedly traverse the conventional processor–memory boundary.…
model training
Scaling laws are the empirical power-law relationships that predict how a language model's loss falls as you add parameters, training data, and compute. They are the reason…
training
Scaling laws are the empirical power-law relationships that predict how a language model's loss falls as you add parameters, training data, and compute. They are the reason…
programmable machine, ENIAC 1945, Manchester Baby 1948, von Neumann architecture, general-purpose computer, embedded computer
A computer is a programmable machine that accepts input, processes it by executing stored instructions, produces output, and can keep results in storage — and, crucially, can be…
generative design, topology optimization, CAD copilot, AI chip floorplanning, EDA machine learning, Mirhoseini 2021, DSO.ai
AI in computer-aided design is the use of machine learning, optimization and generative models inside the software engineers use to design physical products and chips, so that…
cpu, instructions, assembly language, fetch decode execute, arithmetic logic unit, cache, memory hierarchy, registers
Computer architecture is where the previous topic's gates finally get assembled into a working CPU, and understanding that assembly explains why programs run at the speed they do.…
instructions, assembly language, fetch decode execute, arithmetic logic unit, cache, memory hierarchy, registers
Computer architecture is where the gates and registers from digital logic finally get assembled into a working CPU, and it also returns to the fetch-decode-execute cycle this…
processor architecture, cpu architecture, microarchitecture, hardware architecture
Computer architecture is the discipline of designing the structure, organization, and instruction-level behavior of a processor — defining how hardware executes software…
chess programs, Shannon 1950, Turochamp, Los Alamos chess, Deep Blue, Kasparov 1997, Stockfish, AlphaZero 2017
Computer chess is the long effort to make machines play chess, which became artificial intelligence's most visible benchmark for roughly half a century: from paper designs in…
cpu memory storage basics, how computers work, hardware and software layers, intro to computer science
A computer is, underneath every abstraction built on top of it, a piece of hardware that moves electrical charge through transistors to represent and manipulate numbers…
Computer Graphics: Rasterization, Ray Tracing, Shading, and Rendering Computer graphics turns mathematical descriptions of shape, material, light, and viewpoint into images.…
computer vision, images, pixels, geometry, rendering, image processing, visual recognition, convolutional neural network
Computer graphics and vision are two directions on the exact same path: graphics turns numbers into an image, and vision turns an image back into numbers a program can reason…
network, networking, packet switching, protocol, node, Ethernet, Paul Baran, Donald Davies
A computer network is a set of computers and other devices, called nodes, connected by wired or wireless links so that they can exchange data and share resources such as files…
packets, IP address, routing, TCP, UDP, DNS, HTTP, router
Computer networks take the previous topic's isolation, addressing, and controlled access and stretch them across many separate machines connected by nothing but a wire, a radio…
packets, IP address, routing, TCP, UDP, DNS, HTTP, router
Computer networks take the previous topic's isolation, addressing, and controlled access and scale every one of those ideas up from one machine sharing resources among its own…
Computer Networks: TCP/IP Protocol Stack, Routing Algorithms, and Congestion Control Computer networks connect billions of devices through a layered architecture of protocols that…