How the CPU and GPU work together when running application code.
Unified Memory Architecture
A
Application Specific Integrated Circuits (ASICs) is an integrated circuit (IC) chip customized for a particular use in embedded systems, mobile phones, personal computers, professional workstations, rather than intended for general use.
B
C
Central Processing Unit (CPU) is a circuit that's composed of multiple cores that executes instructions comprising a computer program. The CPU performs basic arithmetic, logic, controlling, and input/output (I/O) operations specified by the instructions in the program. This is different from other external components such as main memory, I/O circuitry, and graphics processing units (GPUs).
CMOS (Complementary Metal-Oxide Semiconductor) is a small amount of memory on a computer motherboard that stores the BIOS settings. These BIOS settings include the system time and date, as well as hardware settings.
D
E
Error Correction Code (ECC) memory is a method of detecting and then correcting single-bit memory errors. A single-bit memory error is a data error in server output or production, and the presence of errors can have a big impact on server performance. The two types of single-bit memory errors: hard errors and soft errors. Hard errors are caused by physical factors, such as excessive temperature variation, voltage stress, or physical stress brought upon the memory bits. Soft errors occur when data is written or read differently than originally intended, such as variations in voltage on the motherboard, to cosmic rays or radioactive decay that can cause bits in the memory to flip.
EEPROM (Electrically Erasable Programmable Read-Only Memory) is a type of non-volatile memory used in integrated in microcontrollers for smart cards/remote keyless systems, and other electronic devices to store relatively small amounts of data by allowing individual bytes to be erased and reprogrammed as needed in an application.
EPROM is a memory chip that does not lose data even when the power is switched off. This is a non-volatile memory type so it retains data even when the power is switched off. Each EPROM is individually programmed by an electronic device.
F
G
Graphics Processing Unit (GPU) is a circuit that's composed of hundreds of cores that can handle thousands of threads simultaneously. GPUS can rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device. They are used in embedded systems, mobile phones, personal computers, professional workstations, and game consoles.
Graphics Double Data Rate (GDDR) SDRAM is a type of synchronous graphics random-access memory (SGRAM) with a high bandwidth ("double data rate") interface designed for use in graphics cards, game consoles, and high-performance computing.
GPU-Z is a lightweight system utility designed to provide vital information about your video card and graphics processor.
H
HVM (Hardware Virtual Machine) is a virtualization type that provides the ability to run an operating system directly on top of a virtual machine without any modification, as if it were run on the bare-metal hardware.
I
Image Signal Processing (ISP) is the processs of converting an image into digital form by performing operations like noise reduction, auto exposure, autofocus, auto white balance, HDR correction, and image sharpening with a Specialized type of media processor.
J
K
KVM (for Kernel-based Virtual Machine) is a full virtualization solution for Linux on x86 hardware containing virtualization extensions (Intel VT or AMD-V). It consists of a loadable kernel module, kvm.ko, that provides the core virtualization infrastructure and a processor specific module, kvm-intel.ko or kvm-amd.ko.
L
M
Memory module is a printed circuit board on which memory integrated circuits are mounted. Memory modules permit easy installation and replacement in electronic systems such as personal computers, workstations, and servers.
N
Network interface cards (NICs) is a network interface controller, network adapter, or Local Area Network ( LAN) adapter. It provides network connections for devices like computers and servers.
Non-Transparent Bridging (NTB) is a process that enables a inter-domain communication, facilitating communication between devices in different switch partitions. This ability enables both hosts and EPs to initiate transactions to hosts and/or EPs in another switch partition. An NTB or NT Interconnection consists of two or more PCI functions each defined by a Type 0 PCI header that are interconnected by a bridging function. The Type 0 PCI functions are referred to as Non-Transparent EPs (NT EP). Each partition can have at most one NT EP.
O
oVirt is an open-source distributed virtualization solution, designed to manage your entire enterprise infrastructure. oVirt uses the trusted KVM hypervisor and is built upon several other community projects, including libvirt, Gluster, PatternFly, and Ansible.Founded by Red Hat as a community project on which Red Hat Enterprise Virtualization is based allowing for centralized management of virtual machines, compute, storage and networking resources, from an easy-to-use web-based front-end with platform independent access.
Open vSwitch(OVS)is an open source production quality, multilayer virtual switch licensed under the open source Apache 2.0 license. It is designed to enable massive network automation through programmatic extension, while still supporting standard management interfaces and protocols (NetFlow, sFlow, IPFIX, RSPAN, CLI, LACP, 802.1ag).
P
PV(ParaVirtualization) is an efficient and lightweight virtualization technique introduced by the Xen Project team, later adopted by other virtualization solutions. PV does not require virtualization extensions from the host CPU and thus enables virtualization on hardware architectures that do not support Hardware-assisted virtualization.
Q
QEMU is a fast processor emulator using a portable dynamic translator. QEMU emulates a full system, including a processor and various peripherals. It can be used to launch a different Operating System without rebooting the PC or to debug system code.
R
Random Access Memory (RAM) is a form of computer memory that can be read and changed in any order, typically used to store working data and machine code. A random access memory device allows data items to be read or written in almost the same amount of time irrespective of the physical location of data inside the memory, in contrast with other direct-access data storage media.
Remote Direct Memory Access(RDMA)fabrics is an extenion of the Direct Memory Acces (DMA) technology, which is the ability to access host memory directly without CPU intervention. RDMA allows for accessing memory data from one host to another. A key charateric for RDMA is that it greatly improves throughput and performance because less CPU cycles are needed to process the network packets.
RT (Real-time ray tracing) Cores is a hardware-based ray tracing acceleration accelerate Bounding Volume Hierarchy (BVH) traversal and ray/triangle intersection testing (ray casting) functions. RT Cores perform visibility testing on behalf of threads running in the SM, allowing it to handle another vertex, pixel, and compute shading work.
RTX Global Illumination (RTXGI) is a collection of algorithms that leverage GPU ray tracing to provide scalable solutions for rendering real-time Global Illumination (GI). The goal of RTXGI is to provide optimized implementations of global lighting algorithms that are flexible enough to be useful in both real-time and pre-computed lighting scenarios. Focusing on scalability allows RTXGI to be an effective tool across a wide range of platforms with varying computational capabilities.
Ray Marching is a class of rendering methods for 3D computer graphics process of iteratively extending or contracting the length or magnitude of some vector in order to probe or sample some space for information.
S
Single Instruction, Multiple Data (SIMD) is a type of parallel processing that describes computers with multiple processing elements that perform the same operation on multiple data points simultaneously.
Secure virtual memory is a technique used in macOS that encrypts the data in virtual memory. Secure virtual memory is always on, so data is kept secure while it’s swapped between your hard disk and RAM. The RAM on your Mac contains no information when it’s off.
Screen Space Reflections (SSR) is an effect which is enabled by default that alters the appearance of objects on the surface of Materials. This is an easy way to depict wet, shiny, or mirrored surfaces. They're commonly seen in science fiction art in the form of mirrored floors and rain puddles in wet asphalt.
Screen Space Ambient Occlusion (SSAO) is a computer graphics technique that works by examining an onscreen pixel, and then comparing its location in a depth buffer to the pixels around it. Pixels which are close together but not coplanar (on the same face) are shaded to simulate soft shadows. To maintain playable framerates, it is not possible to sample every pixel every frame, so random sampling is used, which will inevitably create noise/grain which may be more noticeable with movement. To counter this, the SSAO pass is often blurred to remove such grain.
T
Transaction Layer Packets (TLPs) is the starting point in the assembly of outbound Transaction Layer Packets (TLPs), and the end point for disassembly of inbound TLPs at the receiver. Along the way, the Data Link Layer and Physical Layer of each device contribute to the packet assembly and disassembly.
U
Universal Flash Storage (UFS) is an open standard, high-performance interface designed for use in applications where power consumption needs to be minimized, including mobile systems such as smartphones and tablets as well as automotive applications. Its high-speed serial interface and optimized protocol enable significant improvements in throughput and system performance.
V
Video Random Access Memory (VRAM) is the RAM allocated to store image or graphics related data. It functions in the same way as RAM, storing specific data for easier access and performance. Image data is first read by the processor and written on the VRAM. It is then converted by a RAMDAC or a RAM digital-to-analog converter and display as graphics output.
Vector Processor is a central processing unit (CPU) that implements an instruction set where its instructions are designed to operate efficiently and effectively on large one-dimensional arrays of data called vectors.
Virtual memory is a memory management technique that is implemented by using both hardware (central processing unit (CPU)) and software. It makes a program think it has available storage space or address space. When actually virtual memory usually is divided into several physical memory fragments, and stored on the disk storage(SSD or HDD) which can be used to exchange data when needed. On Windows this is called a Pagefile or on Linux a Swap space.
W
X
Y
Z