The knowledge assessment methodology (KAM) is "an interactive benchmarking tool created by the World Bank's Knowledge for Development Program to help countries identify the challenges and opportunities they face in making the transition to the knowledge-based economy." KAM does so by providing information on knowledge economy indicators for 146 countries. Its products include the Knowledge Economy Index and the Knowledge Index.
Tesla Dojo
Tesla Dojo is a series of supercomputers designed and built by Tesla for computer vision video processing and recognition. It was used for training Tesla's machine learning models to improve its Full Self-Driving (FSD) advanced driver-assistance system. It went into production in July 2023. Dojo's goal was to efficiently process millions of terabytes of video data captured from real-life driving situations from Tesla's 4+ million cars. This goal led to a considerably different architecture than conventional supercomputer designs. In August 2025, Bloomberg News reported that the Dojo project had been disbanded, though it was restarted in January 2026. == History == Tesla operates several massively parallel computing clusters for developing its Autopilot advanced driver assistance system. Its primary unnamed cluster using 5,760 Nvidia A100 graphics processing units (GPUs) was touted by Andrej Karpathy in 2021 at the fourth International Joint Conference on Computer Vision and Pattern Recognition (CCVPR 2021) to be "roughly the number five supercomputer in the world" at approximately 81.6 petaflops, based on scaling the performance of the Nvidia Selene supercomputer, which uses similar components. However, the performance of the primary Tesla GPU cluster has been disputed, as it was not clear if this was measured using single-precision or double-precision floating point numbers (FP32 or FP64). Tesla also operates a second 4,032 GPU cluster for training and a third 1,752 GPU cluster for automatic labeling of objects. The primary unnamed Tesla GPU cluster has been used for processing one million video clips, each ten seconds long, taken from Tesla Autopilot cameras operating in Tesla cars in the real world, running at 36 frames per second. Collectively, these video clips contained six billion object labels, with depth and velocity data; the total size of the data set was 1.5 petabytes. This data set was used for training a neural network intended to help Autopilot computers in Tesla cars understand roads. By August 2022, Tesla had upgraded the primary GPU cluster to 7,360 GPUs. Dojo was first mentioned by Elon Musk in April 2019 during Tesla's "Autonomy Investor Day". In August 2020, Musk stated it was "about a year away" due to power and thermal issues. Dojo was officially announced at Tesla's Artificial Intelligence (AI) Day on August 19, 2021. Tesla revealed details of the D1 chip and its plans for "Project Dojo", a datacenter that would house 3,000 D1 chips; the first "Training Tile" had been completed and delivered the week before. In October 2021, Tesla released a "Dojo Technology" whitepaper describing the Configurable Float8 (CFloat8) and Configurable Float16 (CFloat16) floating point formats and arithmetic operations as an extension of Institute of Electrical and Electronics Engineers (IEEE) standard 754. At the follow-up AI Day in September 2022, Tesla announced it had built several System Trays and one Cabinet. During a test, the company stated that Project Dojo drew 2.3 megawatts (MW) of power before tripping a local San Jose, California power substation. At the time, Tesla was assembling one Training Tile per day. In August 2023, Tesla powered on Dojo for production use as well as a new training cluster configured with 10,000 Nvidia H100 GPUs. In January 2024, Musk described Dojo as "a long shot worth taking because the payoff is potentially very high. But it's not something that is a high probability." In June 2024, Musk explained that ongoing construction work at Gigafactory Texas is for a computing cluster claiming that it is planned to comprise an even mix of "Tesla AI" and Nvidia/other hardware with a total thermal design power of at first 130 MW and eventually exceeding 500 MW. In August 2025, Bloomberg News reported that the Dojo project was disbanded, though Musk announced it would be restarted in January 2026 with a new chip iteration. == Technical architecture == The fundamental unit of the Dojo supercomputer is the D1 chip, designed by a team at Tesla led by ex-AMD CPU designer Ganesh Venkataramanan, including Emil Talpes, Debjit Das Sarma, Douglas Williams, Bill Chang, and Rajiv Kurian. The D1 chip is manufactured by the Taiwan Semiconductor Manufacturing Company (TSMC) using 7 nanometer (nm) semiconductor nodes, has 50 billion transistors and a large die size of 645 mm2 (1.0 square inch). Updating at Artificial Intelligence (AI) Day in 2022, Tesla announced that Dojo would scale by deploying multiple ExaPODs, in which there would be: 10 Cabinets per ExaPOD (1,062,000 cores, 3,000 D1 chips) 2 System Trays per Cabinet (106,200 cores, 300 D1 chips) 6 Training Tiles per System Tray (53,100 cores, along with host interface hardware) 25 D1 chips per Training Tile (8,850 cores) 354 computing cores per D1 chip According to Venkataramanan, Tesla's senior director of Autopilot hardware, Dojo will have more than an exaflop (a million teraflops) of computing power. For comparison, according to Nvidia, in August 2021, the (pre-Dojo) Tesla AI-training center used 720 nodes, each with eight Nvidia A100 Tensor Core GPUs for 5,760 GPUs in total, providing up to 1.8 exaflops of performance. === D1 chip === Each node (computing core) of the D1 processing chip is a general purpose 64-bit CPU with a superscalar core. It supports internal instruction-level parallelism, and includes simultaneous multithreading (SMT). It doesn't support virtual memory and uses limited memory protection mechanisms. Dojo software/applications manage chip resources. The D1 instruction set supports both 64-bit scalar and 64-byte single instruction, multiple data (SIMD) vector instructions. The integer unit mixes reduced instruction set computer (RISC-V) and custom instructions, supporting 8, 16, 32, or 64 bit integers. The custom vector math unit is optimized for machine learning kernels and supports multiple data formats, with a mix of precisions and numerical ranges, many of which are compiler composable. Up to 16 vector formats can be used simultaneously. ==== Node ==== Each D1 node uses a 32-byte fetch window holding up to eight instructions. These instructions are fed to an eight-wide decoder which supports two threads per cycle, followed by a four-wide, four-way SMT scalar scheduler that has two integer units, two address units, and one register file per thread. Vector instructions are passed further down the pipeline to a dedicated vector scheduler with two-way SMT, which feeds either a 64-byte SIMD unit or four 8×8×4 matrix multiplication units. The network on-chip (NOC) router links cores into a two-dimensional mesh network. It can send one packet in and one packet out in all four directions to/from each neighbor node, along with one 64-byte read and one 64-byte write to local SRAM per clock cycle. Hardware native operations transfer data, semaphores and barrier constraints across memories and CPUs. System-wide double data rate 4 (DDR4) synchronous dynamic random-access memory (SDRAM) memory works like bulk storage. ==== Memory ==== Each core has a 1.25 megabytes (MB) of SRAM main memory. Load and store speeds reach 400 gigabytes (GB) per second and 270 GB/sec, respectively. The chip has explicit core-to-core data transfer instructions. Each SRAM has a unique list parser that feeds a pair of decoders and a gather engine that feeds the vector register file, which together can directly transfer information across nodes. ==== Die ==== Twelve nodes (cores) are grouped into a local block. Nodes are arranged in an 18×20 array on a single die, of which 354 cores are available for applications. The die runs at 2 gigahertz (GHz) and totals 440 MB of SRAM (360 cores × 1.25 MB/core). It reaches 376 teraflops using 16-bit brain floating point (BF16) numbers or using configurable 8-bit floating point (CFloat8) numbers, which is a Tesla proposal, and 22 teraflops at FP32. Each die comprises 576 bi-directional serializer/deserializer (SerDes) channels along the perimeter to link to other dies, and moves 8 TB/sec across all four die edges. Each D1 chip has a thermal design power of approximately 400 watts. === Training Tile === The water-cooled Training Tile packages 25 D1 chips into a 5×5 array. Each tile supports 36 TB/sec of aggregate bandwidth via 40 input/output (I/O) chips - half the bandwidth of the chip mesh network. Each tile supports 10 TB/sec of on-tile bandwidth. Each tile has 11 GB of SRAM memory (25 D1 chips × 360 cores/D1 × 1.25 MB/core). Each tile achieves 9 petaflops at BF16/CFloat8 precision (25 D1 chips × 376 TFLOP/D1). Each tile consumes 15 kilowatts; 288 amperes at 52 volts. === System Tray === Six tiles are aggregated into a System Tray, which is integrated with a host interface. Each host interface includes 512 x86 cores, providing a Linux-based user environment. Previously, the Dojo System Tray was known as the Training Matrix, which includes six Training Tiles, 20 Dojo Interface Processor cards across four host servers, and Ethernet-l
Locative media
Locative media or location-based media (LBM) is a virtual medium of communication functionally bound to a location. The physical implementation of locative media, however, is not bound to the same location to which the content refers. Location-based media delivers multimedia and other content directly to the user of a mobile device dependent upon their location. Location information determined by means such as mobile phone tracking and other emerging real-time locating system technologies like Wi-Fi or RFID can be used to customize media content presented on the device. Locative media are digital media applied to real places and thus triggering real social interactions. While mobile technologies such as the Global Positioning System (GPS), laptop computers and mobile phones enable locative media, they are not the goal for the development of projects in this field. == Description == Media content is managed and organized externally of the device on a standard desktop, laptop, server, or cloud computing system. The device then downloads this formatted content with GPS or other RTLS coordinate-based triggers applied to each media sequence. As the location-aware device enters the selected area, centralized services trigger the assigned media, designed to be of optimal relevance to the user and their surroundings. Use of locative technologies "includes a range of experimental uses of geo-technologies including location-based games, artistic critique of surveillance technologies, experiential mapping, and spatial annotation." Location based media allows for the enhancement of any given environment offering explanation, analysis and detailed commentary on what the user is looking at through a combination of video, audio, images and text. The location-aware device can deliver interpretation of cities, parklands, heritage sites, sporting events or any other environment where location based media is required. The content production and pre-production are integral to the overall experience that is created and must have been performed with ultimate consideration of the location and the users position within that location. The media offers a depth to the environment beyond that which is immediately apparent, allowing revelations about background, history and current topical feeds. == Locative, ubiquitous and pervasive computing == The term 'locative media' was coined by Karlis Kalnins. Locative media is closely related to augmented reality (reality overlaid with virtual reality) and pervasive computing (computers everywhere, as in ubiquitous computing). Whereas augmented reality strives for technical solutions, and pervasive computing is interested in embedded computers, locative media concentrates on social interaction with a place and with technology. Many locative media projects have a social, critical or personal (memory) background. While strictly spoken, any kind of link to additional information set up in space (together with the information that a specific place supplies) would make up location-dependent media, the term locative media is strictly bound to technical projects. Locative media works on locations and yet many of its applications are still location-independent in a technical sense. As in the case of digital media, where the medium itself is not digital but the content is digital, in locative media the medium itself might not be location-oriented, whereas the content is location-oriented. Japanese mobile phone culture embraces location-dependent information and context-awareness. It is projected that in the near future locative media will develop to a significant factor in everyday life. == Enabling technologies == Locative media projects use technology such as Global Positioning System (GPS), laptop computers, the mobile phone, Geographic Information System (GIS), and web map services such as Mapbox, OpenStreetMap, and Google Maps among others. Whereas GPS allows for the accurate detection of a specific location, mobile computers allow interactive media to be linked to this place. The GIS supplies arbitrary information about the geological, strategic or economic situation of a location. Web maps like Google Maps give a visual representation of a specific place. Another important new technology that links digital data to a specific place is radio-frequency identification (RFID), a successor to barcodes like Semacode. Research that contributes to the field of locative media happens in fields such as pervasive computing, context awareness and mobile technology. The technological background of locative media is sometimes referred to as "location-aware computing". == Creative representation == Place is often seen as central to creativity; in fact, "for some—regional artists, citizen journalists and environmental organizations for example—a sense of place is a particularly important aspect of representation, and the starting point of conversations." Locative media can propel such conversations in its function as a "poetic form of data visualization," as its output often traces how people move in, and by proxy, make sense of, urban environments. Given the dynamism and hybridity of cities and the networks which comprise them, locative media extends the internet landscape to physical environments where people forge social relations and actions which can be "mobile, plural, differentiated, adventurous, innovative, but also estranged, alienated, impersonalized." Moreover, in using locative technologies, users can expand how they communicate and assert themselves in their environment and, in doing so, explore this continuum of urban interactions. Furthermore, users can assume a more active role in constructing the environments they are situated in accordingly. In turn, artists have been intrigued with locative media as a means of "user-led mapping, social networking and artistic interventions in which the fabric of the urban environment and the contours of the earth become a 'canvas.'" Such projects demystify how resident behaviors in a given city contribute to the culture and sense of personality that cities are often perceived to take on. Design scholars Anne Galloway and Matthew Ward state that "various online lists of pervasive computing and locative media projects draw out the breadth of current classification schema: everything from mobile games, place-based storytelling, spatial annotation and networked performances to device-specific applications." A prominent use of locative media is in locative art. A sub-category of interactive art or new media art, locative art explores the relationships between the real world and the virtual or between people, places or objects in the real world. == Examples == Notable locative media projects include Bio Mapping by Christian Nold in 2004, locative art projects such as the SpacePlace ZKM/ZKMax bluecasting and participatory urban media access in Munich in 2005 and Britglyph by Alfie Dennen in 2009, and location-based games such as AR Quake by the Wearable Computer Lab at the University of South Australia and Can You See Me Now? in 2001 by Blast Theory in collaboration with the Mixed Reality Lab at the University of Nottingham. In 2005, the Silicon Valley–based collaborators of C5 first exhibited the C5 Landscape Initiative, a suite of four GPS inspired projects that investigate perception of landscape in light of locative media. In William Gibson's 2007 novel Spook Country, locative art is one of the main themes and set pieces in the story. Narrative projects which engage with locative media are sometimes referred to as Location-Aware Fiction, as explored in "Data and Narrative: Location Aware Fiction" a 2003 essay by Kate Armstrong. This location-aware fiction is also known as locative literature, where locative stories and poems can be experienced via digital portals, apps, QR codes and e-books, as well as via analogue forms such as labelling tape, Scrabble tiles, fridge magnets or Post-It notes, and these are forms often used by the writer and artist Matt Blackwood. The Transborder Immigrant Tool by the Electronic Disturbance Theater is a locative media project aimed at providing life saving directions to water for people trying to cross the US / Mexico border. The project attracted global media attention in 2009 and 2010. Articles included a Los Angeles Times cover story focusing on Ricardo Dominguez and an AP story interviewing Micha Cárdenas and Brett Stalbaum. The articles focused on concerns over the legality of the project and the ensuing investigations of the group, which are still underway. The Transborder Immigrant Tool has recently been included in a number of major exhibitions including Here, Not There at the Museum of Contemporary Art San Diego and the 2010 California Biennial at the Orange County Museum of Art. Invisible Threads by Stephanie Rothenberg and Jeff Crouse is a locative media project aimed at creating embodied awareness of sweatshops and just-in-time production t
T.38
T.38 is an ITU recommendation for allowing transmission of fax over IP networks (FoIP) in real time. == History == The T.38 fax relay standard was devised in 1998 as a way to transport faxes across IP networks between existing Group 3 (G3) fax terminals. T.4 and related fax standards were published by the ITU in 1980, before the rise of the Internet. In the late 1990s, VoIP, or voice over IP, began to gain ground as an alternative to the conventional public switched telephone network (PSTN). However, because most VoIP systems are optimized (through their use of aggressive lossy bandwidth-saving compression) for voice rather than data calls, conventional fax machines worked poorly or not at all on them due to the network impairments such as delay, jitter, packet loss, and so on. Thus, some way of transmitting fax over IP was needed. == Overview == In practical scenarios, a T.38 fax call has at least part of the call being carried over PSTN, although this is not required by the T.38 definition, and two T.38 devices can send faxes to each other. This particular type of device is called Internet-Aware Fax device, or IAF, and it is capable of initiating or completing a fax call towards the IP network. The typical scenario where T.38 is used is – T.38 fax relay – where a T.30 fax device sends a fax over PSTN to a T.38 fax gateway which converts or encapsulates the T.30 protocol into a T.38 data stream. This is then sent either to a T.38-enabled end point such as fax machine or fax server or another T.38 gateway that converts it back to a PSTN PCM or analog signal and terminates the fax on a T.30 device. The T.38 recommendation defines the use of both TCP and UDP to transport T.38 packets. Implementations tend to use UDP, due to TCP's requirement for acknowledgement packets and resulting retransmission during packet loss, which introduces delays. When using UDP, T.38 copes with packet loss by using redundant data packets. T.38 is not a call setup protocol, thus the T.38 devices need to use standard call setup protocols to negotiate the T.38 call, e.g. H.323, SIP & MGCP. == Operation == There are two primary ways that fax transactions are conveyed across packet networks. The T.37 standard specifies how a fax image is encapsulated in e-mail and transported, ultimately, to the recipient using a store-and-forward process through intermediary entities. T.38, however, defines a protocol that supports the use of the T.30 protocol in both the sender and recipient terminals. (See diagram above.) T.38 lets one transmit a fax across an IP network in real time, just as the original G3 fax standards did for the traditional (time-division multiplexed (TDM)) network, also called the public switched telephone network or PSTN. A special protocol is needed for real-time fax over IP (Internet Protocol) since existing fax terminals only supported PSTN connections, where the information flow was generally smooth and uninterrupted, as opposed to the jittery arrival of IP packets. The trick was to come up with a protocol that makes the IP network “invisible” to the endpoint fax terminals, which would mean the user of a legacy fax terminal need not know that the fax call was traversing an IP network. The network interconnections supported by T.38 are shown above. The two fax terminals on either side of the figure communicate using the T.30 fax protocol published by the ITU in 1980. Interconnection of the PSTN with the IP packet network requires a “gateway” between the PSTN and IP networks. PSTN-IP Gateways support TDM voice on the PSTN side and VoIP and FoIP on the packet side. For voice sessions, the gateway will take in voice packets on the IP side, accumulate a few packets to ensure a smooth flow of TDM data upon their release, and then meter them out over TDM where they eventually are heard by a human or stored on a computer for later playback. The gateway employs packet-management techniques to enhance the quality of the speech in the presence of network errors by taking advantage of the natural ability of a listener to not really hear the occasional missing or repeated packet. But facsimile data are transmitted by modems, which aren't as forgiving as the human ear is for speech. Missing packets will often cause a fax session to fail at worst or create one or more image lines in error at best. So the job of T.38 is to “fool” the terminal into “thinking” that it's communicating directly with another T.30 terminal. It will also correct for network delays with so-called spoofing techniques, and missing or delayed packets with fax-aware buffer-management techniques. Spoofing refers to the logic implemented in the protocol engine of a T.38 relay that modifies the protocol commands and responses on the TDM side to keep network delays on the IP side from causing the transaction to fail. This is done, for example, by padding image lines or deliberately causing a message to be re-transmitted to render network delays transparent to the sending/receiving fax terminals. Networks that do not have packet loss or excessive delay can exhibit acceptable fax performance without T.38, provided the PCM clocks in all gateways are of very high accuracy (explained below). T.38 not only removes the effect of PCM clocks not being synchronized, but also reduces the required network bandwidth by a factor of 10, while it corrects for packet loss and delay. === Bandwidth reduction === As shown in the diagram below, a T.38 gateway is composed of two primary elements: the fax modems and the T.38 subsystem. The fax modems modulate and demodulate the PCM samples of the analog data, turning the sampled-data representation of the fax terminal's analog signal to its binary translation, and vice versa. The PSTN network samples the analog signal of a voice or modem signal (it doesn't know the difference) 8,000 times per second (SPS), and encodes them as 8-bit data bytes. This means 8000 samples-per-second times 8-bits per sample, or 64,000 bits per second (bit/s) to represent the modem (or voice) data in one direction. For both directions the modem transaction consumes 128,000 bits of network bandwidth. However, the typical modem in a fax terminal transmits the image data at 33,600 bit/s, so if the analog data are first converted to the digital content they represent, only 33,600 bits (plus network overhead of a few bytes) are needed. And since T.30 fax is a half-duplex protocol, the network is only needed for one direction at a time. Refer to RFC 3261 === PCM clock synchronization === In the diagram above, there is a sample-rate clock in the fax terminal and one in the gateway's modems that is used to trigger the sampling of the analog line 8,000 times per second. These clocks are usually quite accurate, but in some low-cost terminal adapters (a one or two-line gateway) the PCM clock can be surprisingly inaccurate. If the terminal is sending data to the gateway, and the gateway's clock is too slow, the buffers (jitter buffers) in the gateway will eventually overflow, causing the transaction to fail. Since the difference is often quite small, this problem occurs on long, detailed fax images giving the clocks more time to cause the jitter buffer in gateway to either underflow or overflow, which is just the same as missing or duplicated packets. === Packet loss === T.38 provides facilities to eliminate the effects of packet loss through data redundancy. When a packet is sent, either zero, one, two, three, or even more of the previously sent packets are repeated. (The specification does not impose a limit.) This increases the network bandwidth required (it's still much less than not using T.38) but it allows the receiving gateway to reconstruct the complete packet sequence, even with a fairly high level of packet loss. == Related standards == T.4 is the umbrella specification for fax. It specifies the standard image sizes, two forms of image-data compression (encoding), the image-data format, and references, T.30 and the various modem standards. T.6 specifies a compression scheme that reduces the time required to transmit an image by roughly 50-percent. T.30 specifies the procedures that a sending and receiving terminal use to set up a fax call, determine the image size, encoding, and transfer speed, the demarcation between pages, and the termination of the call. T.30 also references the various modem standards. V.21, V.27ter, V.29, V.17, V.34: ITU modem standards used in facsimile. The first three were ratified prior to 1980, and were specified in the original T.4 and T.30 standards. V.34 was published for fax in 1994. T.37 The ITU standard for sending a fax-image file via e-mail to the intended recipient of a fax. G.711 pass through - this is where the T.30 fax call is carried in a VoIP call encoded as audio. This is sensitive to network packet loss, jitter and clock synchronization. When using voice high-compression encoding techniques such as, but not limited to, G.729, some fax tonal signa
Hydration (web development)
In web development, hydration or rehydration is a technique in which client-side JavaScript converts a web page that is static from the perspective of the web browser, delivered either through static rendering or server-side rendering, into a dynamic web page by attaching event handlers to the HTML elements in the DOM. Because the HTML is pre-rendered on a server, this allows for a fast "first contentful paint" (when useful data is first displayed to the user), but there is a period of time afterward where the page appears to be fully loaded and interactive, but is not until the client-side JavaScript is executed and event handlers have been attached. Frameworks that use hydration include Next.js and Nuxt. React v16.0 introduced a "hydrate" function, which hydrates an element, in its API. == Variations == === Streaming server-side rendering === Streaming server-side rendering allows one to send HTML in chunks that the browser can progressively render as it is received. This can provide a fast first paint and first contentful paint as HTML markup arrives to users faster. === Progressive rehydration === In progressive rehydration, individual pieces of a server-rendered application are “booted up” over time, rather than the current common approach of initializing the entire application at once. This can help reduce the amount of JavaScript required to make pages interactive, since client-side upgrading of low priority parts of the page can be deferred to prevent blocking the main thread. It can also help avoid one of the most common server-side rendering rehydration pitfalls, where a server-rendered DOM tree gets destroyed and then immediately rebuilt – most often because the initial synchronous client-side render required data that wasn't quite ready, perhaps awaiting Promise resolution. === Partial rehydration === Partial rehydration has proven difficult to implement. This approach is an extension of the idea of progressive rehydration, where the individual pieces (components/views/trees) to be progressively rehydrated are analyzed and those with little interactivity or no reactivity are identified. For each of these mostly-static parts, the corresponding JavaScript code is then transformed into inert references and decorative functionality, reducing their client-side footprint to near-zero. The partial hydration approach comes with its own issues and compromises. It poses some interesting challenges for caching, and client-side navigation means it cannot be assumed that server-rendered HTML for inert parts of the application will be available without a full page load. One framework that supports partial rehydration is Elder.js, which is based on Svelte. === Trisomorphic rendering === Trisomorphic rendering is a technique which uses streaming server-side rendering for initial/non-JavaScript navigations, and then uses service workers to take on rendering of HTML for navigations after it has been installed. This can keep cached components and templates up to date and enables SPA-style navigations for rendering new views in the same session. This approach works best when one can share the same templating and routing code between the server, client page, and service worker.
Ray tracing (graphics)
In 3D computer graphics, ray tracing is a technique for modeling light transport for use in a wide variety of rendering algorithms for generating digital images. On a spectrum of computational cost and visual fidelity, ray tracing-based rendering techniques, such as ray casting, recursive ray tracing, distribution ray tracing, photon mapping and path tracing, are generally slower and higher fidelity than scanline rendering methods. Thus, ray tracing was first deployed in applications where taking a relatively long time to render could be tolerated, such as still CGI images, and film and television visual effects (VFX), but was less suited to real-time applications such as video games, where speed is critical in rendering each frame. Since 2018, however, hardware acceleration for real-time ray tracing has become standard on new commercial graphics cards, and graphics APIs have followed suit, allowing developers to use hybrid ray tracing and rasterization-based rendering in games and other real-time applications with a lesser hit to frame render times. Ray tracing is capable of simulating a variety of optical effects, such as reflection, refraction, soft shadows, scattering, depth of field, motion blur, caustics, ambient occlusion and dispersion phenomena (such as chromatic aberration). It can also be used to trace the path of sound waves in a similar fashion to light waves, making it a viable option for more immersive sound design in video games by rendering realistic reverberation and echoes. In fact, any physical wave or particle phenomenon with approximately linear motion can be simulated with ray tracing. Ray tracing–based rendering techniques that sample light over a domain typically generate multiple rays and often rely on denoising to reduce the resulting noise. == History == The idea of ray tracing comes from as early as the 16th century, when it was described by Albrecht Dürer, who is credited for its invention. Dürer described multiple techniques for projecting 3-D scenes onto an image plane. Some of these project chosen geometry onto the image plane, as is done with rasterization today. Others determine what geometry is visible along a given ray, as is done with ray tracing. Using a computer for ray tracing to generate shaded pictures was first accomplished by Arthur Appel in 1968. Appel used ray tracing for primary visibility (determining the closest surface to the camera at each image point) by tracing a ray through each point to be shaded into the scene to identify the visible surface. The closest surface intersected by the ray was the visible one. This non-recursive ray tracing-based rendering algorithm is today called "ray casting". His algorithm then traced secondary rays to the light source from each point being shaded to determine whether the point was in shadow or not. Later, in 1971, Goldstein and Nagel of MAGI (Mathematical Applications Group, Inc.) published "3-D Visual Simulation", wherein ray tracing was used to make shaded pictures of solids. At the ray-surface intersection point found, they computed the surface normal and, knowing the position of the light source, computed the brightness of the pixel on the screen. Their publication describes a short (30-second) film "made using the University of Maryland's display hardware outfitted with a 16mm camera. The film showed the helicopter and a simple ground-level gun emplacement. The helicopter was programmed to undergo a series of maneuvers including turns, take-offs, and landings, etc., until it eventually is shot down and crashed." A CDC 6600 computer was used. MAGI produced an animation video called MAGI/SynthaVision Sampler in 1974. Another early instance of ray casting came in 1976, when Scott Roth created a flip book animation in Bob Sproull's computer graphics course at Caltech. The scanned pages are shown as a video in the accompanying image. Roth's computer program noted an edge point at a pixel location if the ray intersected a bounded plane different from that of its neighbors. Of course, a ray could intersect multiple planes in space, but only the surface point closest to the camera was noted as visible. The platform was a DEC PDP-10, a Tektronix storage-tube display, and a printer which would create an image of the display on rolling thermal paper. Roth extended the framework, introduced the term ray casting in the context of computer graphics and solid modeling, and in 1982 published his work while at GM Research Labs. Turner Whitted was the first to show recursive ray tracing for mirror reflection and for refraction through translucent objects, with an angle determined by the solid's index of refraction, and to use ray tracing for anti-aliasing. Whitted also showed ray traced shadows. He produced a recursive ray traced film called The Compleat Angler in 1979 while an engineer at Bell Labs. Whitted's deeply recursive ray tracing algorithm reframed rendering from being primarily a matter of surface visibility determination to being a matter of light transport. His paper inspired a series of subsequent work by others that included distribution ray tracing and finally unbiased path tracing, which provides the rendering equation framework that has allowed computer-generated imagery to be faithful to reality. For decades, global illumination in major films using computer-generated imagery was approximated with additional lights. Ray tracing-based rendering eventually changed that by enabling physically based light transport. Early feature films rendered entirely using path tracing include Monster House (2006), Cloudy with a Chance of Meatballs (2009), and Monsters University (2013). == Algorithm overview == Optical ray tracing describes a method for producing visual images constructed in 3D computer graphics environments, with more photorealism than either ray casting or scanline rendering techniques. It works by tracing a path from an imaginary eye through each pixel in a virtual screen, and calculating the color of the object visible through it. Scenes in ray tracing are described mathematically by a programmer or by a visual artist (normally using intermediary tools). Scenes may also incorporate data from images and models captured by means such as digital photography. Typically, each ray must be tested for intersection with some subset of all the objects in the scene. Once the nearest object has been identified, the algorithm will estimate the incoming light at the point of intersection, examine the material properties of the object, and combine this information to calculate the final color of the pixel. Certain illumination algorithms and reflective or translucent materials may require more rays to be re-cast into the scene. It may at first seem counterintuitive or "backward" to send rays away from the camera, rather than into it (as actual light does in reality), but doing so is many orders of magnitude more efficient. Since the overwhelming majority of light rays from a given light source do not make it directly into the viewer's eye, a "forward" simulation could potentially waste a tremendous amount of computation on light paths that are never recorded. Therefore, the shortcut taken in ray tracing is to presuppose that a given ray intersects the view frame. After either a maximum number of reflections or a ray traveling a certain distance without intersection, the ray ceases to travel and the pixel's value is updated. === Calculate rays for rectangular viewport === On input we have (in calculation we use vector normalization and cross product): E ∈ R 3 {\displaystyle E\in \mathbb {R^{3}} } eye position T ∈ R 3 {\displaystyle T\in \mathbb {R^{3}} } target position θ ∈ [ 0 , π ] {\displaystyle \theta \in [0,\pi ]} field of view - for humans, we can assume ≈ π / 2 rad = 90 ∘ {\displaystyle \approx \pi /2{\text{ rad}}=90^{\circ }} m , k ∈ N {\displaystyle m,k\in \mathbb {N} } numbers of square pixels on viewport vertical and horizontal direction i , j ∈ N , 1 ≤ i ≤ k ∧ 1 ≤ j ≤ m {\displaystyle i,j\in \mathbb {N} ,1\leq i\leq k\land 1\leq j\leq m} numbers of actual pixel v → ∈ R 3 {\displaystyle {\vec {v}}\in \mathbb {R^{3}} } vertical vector which indicates where is up and down, usually v → = [ 0 , 1 , 0 ] {\displaystyle {\vec {v}}=[0,1,0]} - roll component which determine viewport rotation around point C (where the axis of rotation is the ET section) The idea is to find the position of each viewport pixel center P i j {\displaystyle P_{ij}} which allows us to find the line going from eye E {\displaystyle E} through that pixel and finally get the ray described by point E {\displaystyle E} and vector R → i j = P i j − E {\displaystyle {\vec {R}}_{ij}=P_{ij}-E} (or its normalization r → i j {\displaystyle {\vec {r}}_{ij}} ). First we need to find the coordinates of the bottom left viewport pixel P 1 m {\displaystyle P_{1m}} and find the next pixel by making a shift along directions parallel to viewport (vectors b → n {\displaystyle {\vec {b}}_{n
Bluelight (web forum)
Bluelight is a web-forum, research portal, online community, and non-profit organisation dedicated to harm reduction in drug use. Its userbase includes current and former substance users, academic researchers, drug policy activists, and mental health advocates. It is believed to be the largest online international drug discussion website in the world. As of November 2025, the website claims over 475,900 registered members, the Discord community claims over 11,900 members, and additional members utilise other platforms such as Telegram. Bluelight has been utilised by academic researchers as a primary source of data in numerous publications. Researchers also utilise the site to advertise research studies, recruit study participants, and better understand the world of substance use. Research groups and organisations that have partnered with Bluelight to recruit study participants include Imperial College London, Johns Hopkins University, Health Canada, Karlstad University, Curtin University, Macquarie University, Columbia University, University of Pennsylvania, University of Michigan, Toronto Metropolitan University (then known as Ryerson University), and MAPS. Researchers have found that the most common reasons for substance users to visit Bluelight.org and similar online communities are to learn "how to use drugs safely" and "how to help others use drugs safely." Bluelight neither condemns or condones drug use, instead advocating for the principle of responsible drug use; educating and allowing individuals to make informed decisions regarding their drug use, providing information on local drug misuse services, and providing them with other drug harm reduction resources and public safety notices. == History == Bluelight.org was originally formed in 1997 as a message board on bluelight.net called the MDMA Clearinghouse. The board was created as a side project by the owner of West Palm Beach design company Bluelight Designs. 200–300 users joined the site between 1998 and 1999, but the site's servers were heavily limited and could only store a few threads at a time; this led to the creation of 'The New Bluelight' forum in May 1999 and the registration of the bluelight.nu domain in June 1999. The site began to explode in popularity in the early 2000s with the rise of MDMA in the club scene, amassing nearly 7,000 members by the year 2000 and 59,000 by the start of 2006. The site switched to the bluelight.ru domain in October 2005, and switched again to bluelight.org in January 2014. In early 2024, Bluelight was re-structured and the forum became a subsidiary of the newly formed Australian non-profit organisation & registered charity Bluelight Communities Ltd. == Partnerships == In the early 2000s, Bluelight worked with reagent test supplier EZ-Test to promote the sale of drug checking kits. In 2007, Bluelight partnered with the Multidisciplinary Association for Psychedelic Studies (MAPS), a non-profit organisation working to raise awareness and understanding of psychedelic drugs through education, clinical research, and advocacy. MAPS utilised Bluelight to recruit participants for its first MDMA-assisted psychotherapy trial for PTSD. In 2013, the official MAPS forums were migrated to Bluelight. Bluelight's other partners include Erowid, a non-profit organisation dedicated to education surrounding psychoactive drugs; TripSit, a harm reduction education website; Pill Reports, a web-based database for drug checking results that was initially formed as an offshoot of the site; and the Global Drug Survey, an independent research organisation focused on collecting data about substance use. == Notable users == Alan Woods – funded the site's maintenance costs from 1999 until his death in 2008 Hamilton Morris John McAfee – created an infamous series of troll posts about the stimulant MDPV