953 technical terms and definitions
gpu explained, graphics processing unit, how does a gpu work, gpu vs cpu cores
A GPU, or graphics processing unit, is a chip built around a completely different design philosophy than a CPU: instead of a few powerful cores optimized to handle one complex…
hdl chip design explained, verilog vhdl meaning, hardware description language meaning, what does hdl mean in chip design
A hardware description language, or HDL, is a specialized programming language used to describe the exact structure and behavior of digital circuits, letting chip designers…
lithography scanner explained, chip lithography machine meaning, wafer stepper scanner, what does a lithography scanner do
A lithography scanner is the physical machine that actually performs the lithography process — precisely positioning the wafer, projecting light through the photomask…
memory controller explained, memory controller meaning, integrated memory controller, what does a memory controller do
A memory controller is the component that manages the flow of data between a processor and a device's memory, handling the detailed timing and signaling requirements memory chips…
modem chip explained, cellular modem meaning, 5g modem chip, what does a modem chip do
A modem chip is the specialized processor inside a phone, laptop, or other connected device that handles the job of translating data into radio signals for transmission…
motherboard explained, motherboard components, cpu socket compatibility, motherboard form factor
A motherboard is the large circuit board that physically connects every major component in a computer — the CPU, RAM, storage, graphics card, and power supply — and provides…
mpw semiconductor explained, multi project wafer meaning, shared wafer run chip prototyping, what does mpw mean
A multi-project wafer, or MPW, is a single wafer run shared by several different chip designs from different customers, splitting the fixed cost of a fabrication run across…
A network on chip, or NoC, is a communication system built directly into a chip that routes data between its many internal components — cores, memory, and other blocks — using…
process design kit, pdk explained, process design kit explained, what is a process design kit, pdk semiconductor, foundry pdk
A PDK, or process design kit, is the file package a foundry hands its customers so their chip designs actually work on that foundry's silicon: transistor models, standard-cell…
pellicle photomask, euv pellicle, what does a pellicle do, photomask protection
A pellicle is a thin, ultra-transparent membrane stretched over a taut frame and mounted just above the surface of a photomask, acting as a protective shield that keeps dust…
photomask explained, lithography mask meaning, how does a photomask work, euv photomask
A photomask is a precisely patterned plate — usually a sheet of quartz coated with an opaque chrome pattern — that lithography equipment uses like a stencil to project a chip's…
power management ic explained, pmic chip meaning, what does a pmic do, power management integrated circuit
A power management IC, or PMIC, is a dedicated chip responsible for taking a device's raw input power — such as a battery or wall adapter — and converting, regulating…
A probe card is a specialized test fixture covered with many fine, precisely positioned needle-like contacts that touch a wafer's bond pads directly, letting automated test…
rdl chip packaging, rdl explained, what does rdl mean semiconductor, redistribution layer packaging
A redistribution layer, or RDL, is a thin layer of extra wiring built on top of a finished chip that reroutes its native connection points to new, more convenient locations…
A reticle is the physical glass plate carrying a chip layer's pattern that a lithography scanner projects onto the wafer — closely related to a photomask, but specifically…
rf front end explained, rf front end meaning, phone rf module, what does rf front end do
An RF front-end module is the collection of specialized components — including power amplifiers, filters, and switches — that sits between a device's modem chip and its antenna…
wet scrubbing exhaust treatment, scrubber column design, gas absorption liquid treatment, acid gas neutralization fab, counterflow scrubber
A scrubber is the specific abatement technology that removes hazardous gases from process exhaust by passing them through a liquid — usually water, sometimes with added chemicals…
semiconductor explained, semiconductor definition, semiconductor vs conductor vs insulator, what is silicon used for
A semiconductor is a material — most commonly silicon — whose ability to conduct electricity sits between that of a true conductor (like copper) and a true insulator (like glass)…
chip ip core explained, ip licensing semiconductor meaning, what is ip core in chip design, processor ip licensing
A semiconductor IP core is a pre-designed, reusable block of chip circuitry — such as a processor core, a memory controller, or a communications interface — that a chip designer…
A solder bump is a small ball or dome of solder deposited directly onto a chip's bond pad, used in flip-chip packaging to create both the electrical connection and the mechanical…
gate spacer fabrication, self aligned source drain, anisotropic etch spacer formation, conformal deposition spacer, transistor spacer width
A spacer is a thin sidewall of insulating material formed against the edges of a transistor's gate, and it exists to precisely control where the source and drain regions begin…
Sub-resolution assist features, or SRAF, are extra shapes added to a photomask that are deliberately too small to print onto the wafer themselves, but which subtly reshape…
soc explained, system on chip meaning, what does soc mean in phones, soc vs cpu
A system on chip, or SoC, is a single chip that combines multiple major components of a computing system — typically a processor, memory controller, graphics, and other…
systolic array explained, systolic array tpu, systolic array meaning ai, what does systolic array mean
A systolic array is a grid-like arrangement of simple processing units that pass data to their immediate neighbors in a steady, rhythmic pattern, allowing an AI accelerator…
chip tape out explained, tape out meaning semiconductor, what does tape out mean, chip design tape out
Tape-out is the moment a chip's design is finalized and sent off to a foundry for manufacturing — the point of no return in chip development, after which making changes means…
tsv explained, through silicon via meaning, tsv chip packaging, what does tsv stand for
A through-silicon via, or TSV, is a microscopic vertical electrical connection drilled directly through a piece of silicon, allowing signals to pass straight up and down between…
tensor processing unit explained, tpu vs gpu, tpu meaning ai chip, what does tpu stand for
A TPU, or Tensor Processing Unit, is a type of AI accelerator chip designed specifically to speed up the tensor math — large-scale multi-dimensional array operations — that…
transistor explained, how does a transistor work, transistor switch, cmos transistor basics
A transistor is a tiny electronic switch that can flip between "on" and "off" billions of times per second, and it is the single building block that every modern chip is made…
turbo pump semiconductor fab, high vacuum pump explained, staged vacuum pump down, plasma chamber vacuum requirements, molecular flow vacuum pump
A turbomolecular pump is the workhorse vacuum pump that gets a process chamber down to the extremely low pressures nearly every fab process covered in this series actually…
vector processing explained, vector processor vs scalar, simd vector processor meaning, what does a vector processor do
A vector processor is a type of processor built to apply the same single operation to many data elements at once, rather than processing one value at a time — a design well suited…
silicon wafer explained, semiconductor wafer meaning, wafer fabrication, what is a die vs wafer
A wafer is a thin, round slice of ultra-pure silicon — typically about 300 millimeters across on modern production lines — that serves as the base material on which an entire…
what is WAT semiconductor
A wafer acceptance test, or WAT, is a standardized set of electrical measurements taken on special test structures scattered across a wafer to confirm the underlying fabrication…
fab exhaust treatment, thermal abatement vs catalytic, hazardous process gas treatment, wet scrubbing vs abatement, greenhouse gas fab exhaust
Abatement is the treatment of a fab's process exhaust before it ever leaves the facility, and it exists because nearly every reactive chemical process covered throughout this…
ai accelerator chip explained, ai accelerator vs gpu, ai accelerator meaning, types of ai accelerators
An AI accelerator is any chip built specifically to speed up the math behind artificial intelligence — mostly large-scale matrix multiplication — rather than to handle…
integrated device manufacturer meaning, idm vs fabless, idm semiconductor company, what does idm mean in chips
An IDM, or Integrated Device Manufacturer, is a chip company that both designs its chips and manufactures them in its own fabrication plants — the opposite of the fabless model…
npu explained, neural processing unit, npu vs gpu vs cpu, on-device ai chip
An NPU, or Neural Processing Unit, is a chip or chip block built specifically to run the repetitive math behind neural networks — mostly large batches of matrix multiplication…
osat semiconductor meaning, outsourced assembly and test explained, osat vs foundry, chip packaging and testing company
An OSAT — short for Outsourced Semiconductor Assembly and Test — is a company that specializes in packaging finished silicon dies and testing completed chips, handling…
transformer attention explained, query key value attention, kv cache explained, multi query attention, grouped query attention, self attention transformer
The attention mechanism is the calculation that lets a transformer decide, for every token it's producing, which earlier tokens actually matter right now — and it's exactly what…
what is BEOL
Back-end-of-line, or BEOL, refers to the later stage of chip fabrication where the metal wiring layers connecting all the transistors together are built up on top of the wafer…
beamforming explained, beamforming 5g meaning, how does beamforming work, beamforming antenna array
Beamforming is a wireless antenna technique that combines signals from multiple antenna elements so they reinforce each other in a specific direction, effectively focusing…
Branch prediction is a processor technique that guesses which way a program's conditional branch will go before that branch is actually evaluated, letting the processor keep…
what is burn in testing
Burn-in testing is a reliability screening step where chips are operated under elevated temperature and voltage stress for an extended period before shipment, deliberately…
Cache coherence is the property that guarantees every processor core in a multi-core chip sees a consistent, up-to-date view of shared memory, even though each core keeps its own…
Carrier aggregation is a wireless technology that combines multiple separate frequency bands, or carriers, into one effective connection, letting a device use more total bandwidth…
chip packaging explained, semiconductor packaging meaning, advanced packaging chiplets, what is a chip package
Chip packaging is the process of taking a finished, tested silicon die and encasing it in a protective housing with external connectors — the familiar black rectangle with metal…
clock speed explained, cpu ghz meaning, what is clock frequency, clock speed vs performance
Clock speed, measured in gigahertz (GHz), is how many times per second a chip's internal clock ticks, and each tick synchronizes one step of work across the chip's circuits — but…
chemical mechanical polishing explained, planarization semiconductor, cmp dishing erosion, copper damascene cmp, preston equation polishing
Chemical-Mechanical Polishing (CMP) is what flattens the wafer back out after deposition and etch leave it bumpy. Every layer built through the CVD-lithography-etch loop leaves…
compute in memory explained, in memory computing ai, compute in memory chip meaning, what does compute in memory mean
Compute-in-memory is a chip architecture approach that performs certain calculations directly inside memory itself, rather than following the traditional design of moving data out…
dynamic batching llm serving, in-flight batching explained, llm throughput scheduling, static vs continuous batching, ai serving scheduler
Continuous batching is the serving-system technique that decides which requests actually get processed together on any given decode step, and it's the layer where every…
damascene process explained, dual damascene semiconductor, copper electroplating BEOL, barrier metal liner copper, low-k dielectric interconnect
Copper interconnect is the wiring that connects millions or billions of individual transistors into an actual working circuit. Once the transistors themselves are built through…