Specs Dictionary

A dictionary of all the most pertinent GPU / video card terminology. Learn about how video cards work with this definitions listing

Anisotropic Filtering

Anisotropic Filtering is a type of texture filtering (see: Texture Fill-Rate) that is often listed alongside bilinear and trilinear filtering techniques.


Graphics Processing Unit -- The physical "chip" (a semiconductor) that performs all graphics computations in a system. A GPU is comprised of a silicon processor -- not unlike a CPU -- atop a substrate, which is then mounted to the host video card (or directly to the motherboard, in the case of laptops, tablets, and phones). Modern CPUs will also contain an "IGP," or Integrated Graphics Processor, which is effectively a compartmentalized GPU that shares chip space with the CPU.

CUDA Cores

CUDA Cores -- Just a small part of the larger whole when it comes to an nVidia GPU. A "CUDA Core" is nVidia's equivalent to AMD's "Stream Processors." NVidia's proprietary parallel computing programming model, CUDA (Compute Unified Device Architecture), is a specialized programming language that can leverage the GPU in specific ways to perform tasks with greater performance. Each GPU can contain hundreds to thousands of CUDA cores.

Memory Interface

Memory Interface -- There are several memory interfaces throughout a computer system. As it pertains to the GPU, a Memory Interface is the physical bit-width of the memory bus. Every clock cycle (billions per second), data is transferred along a memory bus to and from the on-card memory. The width of this interface, normally defined as "384-bit" or similar, is the physical count of bits that can fit down the bus per clock cycle.

Stream Processors

Stream Processors -- Like nVidia's "CUDA Cores," AMD's Stream Processors are a more central component of the GPU. Stream Processors and CUDA Cores are not linearly comparable due to vast architectural differences, but can be thought of as similar when it comes to the primary function of each component. Stream Processing is focused intensely on parallelism of datasets to ensure efficient processing when performing tasks that are better-suited for parallel processing.

Memory Bandwidth (GPU)

Memory Bandwidth (GPU) -- Memory bandwidth is one of the most frequently showcased stats for any new GPU, often rating in hundreds of gigabytes per second of throughput potential. Memory Bandwidth is the theoretical maximum amount of data that the bus can handle at any given time, playing a determining role in how quickly a GPU can access and utilize its framebuffer. Memory bandwidth can be best explained by the formula used to calculate it:

Core Clock (GPU)

Core Clock (GPU) -- We sometimes refer to this as the Base Clock or BCLK of the GPU, a habit from working with the BCLK (CPU); the two can be used interchangeably, though "Core Clock" is more correct when referring specifically to a GPU. The Core Clock is the operating frequency of the graphics processing chip found on the video card. This is sometimes SuperClocked or pre-overclocked, depending on manufacturer.

Power Target

Power Target % - The target wattage over max TDP (represented as a percentage) to feed the GPU. Power Target was introduced with Maxwell overclocking on NVIDIA devices as a means to increase power consumption over the lower TDP base, thus allowing further headroom for overvolting and overclocking. A higher watt draw gives more room for more power consumption by the GPU, which gives more room for overclocking.

Texture Fill-Rate

The texture filter rate of the GPU is representative of how many pixels (specifically 'texels') the GPU can render per second. This value is always represented as a measurement over time (1s). A 144.1GT/s texture fill rate comes out to 144.1 billion texels (textured picture elements) per second.


Texture Mapping Unit (TMU) - A low-level GPU component that operates with some independence, entirely dedicated to manipulating bitmaps and texture filtration. TMUs modify bitmaps (resize, rotate, scale, skew, fit) for placement onto objects and filter textures; in video games, this would be represented as placing a texture onto an object, whereupon we have now created "texels" (textured pixels).


Render Output Units (ROPs) - Also known as "Raster Operations Pipeline," which is more useful in determining the application of a ROP. As with a Texture Map Unit or CPU's Floating Point Unit, a Render Output Unit is a specific component on a GPU that is responsible for the processing of final pixel values prior to drawing them to the screen.


Video Codec Engine (VCE) - AMD's on-die solution for live encoding of captured footage, to include gameplay capture. The VCE is exploited by software solutions to live-capture gameplay in a similar fashion to nVidia's ShadowPlay, which uses a Kepler (now Maxwell) encoder). The VCE is included on most modern AMD GPUs and enables live H.264, MPEG-4, ASP, MPEG-2, VC-1, and Blu-Ray 3D encoding.


TrueAudio (AMD) - Using a discrete DSP (Digital Signal Processor), AMD GPUs perform standalone audio processing for multi-channel simulation in gaming. TrueAudio has questionable use cases in the real-world, but in theory, it is capable of producing true 3D audio with upwards of 30+ channels simulated through audio playback devices. TrueAudio uses positional output through all of these channels to better simulate audio source locations in games.


PowerTune (AMD) - AMD's proprietary PowerTune technology has existed since December 2011, bringing dynamic frequency scaling to AMD graphics processors. "Dynamic frequency scaling" is the act of modifying the core clock speed (frequency) on-the-fly and can be thought of as similar in concept to TurboBoost or nVidia Boost. PowerTune scales the frequency based upon performance demands, thermals, and watt draw (using P-states).

Actuation Depth

The depth at which a switch will register a keystroke, usually measured in millimeters. For example, Cherry MX Brown switches have an actuation depth of 2mm. When such a key is depressed 2mm, the key will activate and electrically input the keystroke. Romer G switches have a shallower actuation depth of 1.5mm; this means they “trigger” at a shorter distance than MX Brown switches.

Other depths are defined in our additional glossary entries, as below.


Mechanical switches have stems that allow for aftermarket keycaps to be installed. Replaceable keycaps allow for novelty keycaps, full keycap set replacement, and general customization of keyboards without doing irreversible modding.

Actuation Behavior

Terms such as "linear," "tactile," and "clicky" refer to how a switch feels or sounds when actuated.


Hysteresis is a term used to describe the input gap between the actuation point and reset point. Most switch reset points are shallower than the actuation depth (higher up), so a key has to be released almost fully in order to reset for the next press in most instances.

Hysteresis can make double-tapping and rapid same-key typing difficult, so there's a trade-off in function.


Tenkeyless (TKL) -- The term "tenkeyless" refers to keyboards without a number pad. The term tenkeyless is a bit incorrect since the number pad has more keys than 0-9. Tenkeyless keyboards are usually referred to as tenkeyless/TKL, but are sometimes referred to as ~80% keyboards. The XX% format is also used to refer to other layouts of keyboards.

N-Key Rollover

N-Key Rollover (N-KEY) -- The ability for a keyboard to recognize any number of keys being actuated at once. Whereas a keyboard with 5-key rollover could only detect 5 keys being pressed at one time, in this case, “N” is indicative of any reasonable integer since there is no-key rollover. N-key rollover is sometimes referred to as anti-ghosting.

See Also

  • Repeat Acceleration
  • Actuation Behavior
  • Hysteresis


Repeat Acceleration

Repeat Acceleration -- The rate at which a letter repeats when a key is held down. Some keyboards may type 5 letters if a switch is held down for a second, whereas another may type 10. Many keyboards allow for this to be adjusted. Higher repeat acceleration allows for more rapid repeats of text, potentially enabling better "chat-spamming" ability.

See Also

  • N-Key Rollover
  • Actuation Behavior
  • Actuation Depth


Keyboard Backplate

Mechanical keyboards must have switches mounted to something, whether that's a PCB, metal plate, or plastic plate. Metal plate mounting is generally found in more expensive keyboards and provides a heavier and sturdier keyboard. PCB mounted switches are found in cheap keyboards and will have more flex and give to them, but they are lighter and cheaper. Plastic plate mounting provides a middle ground between PCB and metal plate mounting, but it’s not commonly used. 

USB Passthrough

A USB passthrough is referenced when a keyboard has female USB ports for other devices to be plugged into the keyboard. USB passthroughs requires more than one USB port to be used by the keyboard in order to pass the USB through to the PC, often requiring an additional connection to the host system for powered ports.

Multimedia Controls

Multimedia controls refer to media (movies, music, etc.) controls that are integrated into keyboards. This can include, but is not limited to, volume control, skipping, play/pause, and stop buttons. This is oftentimes done via a function key, with the controls on the F keys (often Fn+F1-F4).

Keyboard Sizes (%)

Keyboard Size -- Oftentimes referred to in percentages. A standard, full-sized keyboard usually has 104 keys and is considered to be a 100% keyboard. Most designs fall between the range of 80% (TKL) to 40% keyboards. 100%, ~80%, 75%, 60%, and 40% designs are the most prominent, but other sizes do exist.

Buckling Spring Switches

There were many different switch types used in the early days of computers, but buckling spring switches were very common. Buckling springs have springs which are depressed until they "buckle" and complete a circuit, this makes them loud and tactile.

Topre Switches

Topre switches use a spring and a rubber dome to make a low-force, tactile, and quiet switch. The spring is inside the rubber dome and is cone shaped. The rubber dome in the switch provides most of the resistance and tactile feel. When the spring in the switch is compressed, a capacitive sensing component on the keyboard senses the key press during actuation, which results in the switch being activated.

Rubber Dome Switches

Rubber dome switches are now the most common switch technology in keyboards. Rubber dome switches use small rubber coverings that are pushed down to complete a circuit. Their largest advantage is their considerably lower cost compared to mechanical switches. 

Alps Switches

Alps switches are interesting in that they are no longer officially produced, but clones exist. Hua-Jie, Kwanda, Tai-Hao, Xiang Min, Gaote, and some unknown manufacturers have all produced or continue to produce Alps clones. Alps switches function similar to Cherry MX/Kailh switches in terms of how they actuate, but one difference is that Alps switches use a metal leaf as the contact mechanism.

Cherry MX Switches

Cherry MX switches are some of the most common mechanical switches today. It should be noted that Kailh also manufactures Razer Switches and Cherry clones. All Cherry & Kailh switches use a spring in conjunction with a stem that lowers when pressed. When pressed, the stem pushes two contacts to touch, completing a circuit.