The June 2025 Update of Adobe Premiere Pro, the industry standard video editing application, added support for GPU-accelerated 4:2:2 color format video encoding and decoding on NVIDIA "Blackwell" GPUs. It implements Video Codec SDK 13.0, which NVIDIA released in February. This adds 4:2:2 color format support for H.264 and HEVC. The 4:2:2 color format provides twice the amount of color detail as 4:2:0, but with a nominal increase in stream bitrate or file-size. Adobe says that the added color detail of 4:2:2 is ideal for "precise color grading, cleaner chroma keying, and crisper text rendering."

Adobe recently announced support for 4:2:2 video color formats with Premiere Pro and Adobe Media Encoder, and NVIDIA today announced that its GeForce RTX 50-series GPUs and RTX Pro Blackwell series GPUs will receive support and optimization for them. The 9th Gen NVENC and 6th Gen NVDEC video accelerators on Blackwell GPUs, as well as its display engine, come with support for 4:2:2 color formats, which help greatly reduce file-size in comparison to 4:4:4 formats, while also offering superior color depth compared to 4:2:0. 10 bits per cell 4:2:2 retains more color information compared to 4:2:0 with 8 bits per cell. For video professionals, this also offers superior chroma keying ("green screen" background replacements). GeForce RTX 50-series GPUs when paired with Windows 11, come hardware acceleration for H.264 and HEVC 10-bit 4:2:2 formats.

FFmpeg, the popular open-source multimedia library for compressed video and audio formats, just introduced a component to libavcodec that integrates AMD Accelerated Media Framework (AMF) SDK. This component is called AMFDEC, and it allows libavcodec to utilize hardware-accelerated decoding features on AMD Radeon RX GPUs and the integrated graphics of AMD Ryzen processors. On machines with compatible hardware, AMFDEC provides libavcodec with hardware acceleration for decoding of H.264, H.265 or HEVC, and AV1. FFmpeg also introduced filters that implement AMD FSR Video Super Resolution. This lets applications that use FFmpeg to take advantage of VSR features on Radeon RX GPUs to provide superior upscaling quality. The filter is labelled "ar_amf." The commit can be accessed here.

New GeForce RTX 5090 and RTX 5080 GPUs - built on the NVIDIA Blackwell architecture - are now available to power generative AI content creation and accelerate creative performance. GeForce RTX 5090 and RTX 5080 GPUs feature fifth-generation Tensor Cores with support for FP4, reducing the VRAM requirements to run generative AI models while doubling performance. For example, Black Forest Labs' FLUX models - available on Hugging Face this week - at FP4 precision require less than 10 GB of VRAM, compared with over 23 GB at FP16. With a GeForce RTX 5090 GPU, the FLUX.1 [dev] model can generate images in just over five seconds, compared with 15 seconds on FP16 or 10 seconds on FP8 on a GeForce RTX 4090 GPU.

GeForce RTX 50 Series GPUs also come equipped with ninth-generation encoders and sixth-generation decoders that add support for 4:2:2 and increase encoding quality for HEVC and AV1. Fourth-generation RT Cores paired with DLSS 4 provide creators with super-smooth 3D rendering viewports. The GeForce RTX 5090 GPU includes 32 GB of ultra-fast GDDR7 memory and 1,792 GB/sec of total memory bandwidth - a 77% bandwidth increase over the GeForce RTX 4090 GPU. It also includes three encoders and two decoders, reducing export times by a third compared with the prior generation.

Chinese GPU maker Moore Threads has prepared a professional graphics card called MTT X300, aimed at professional visualization workloads like CAD, BIM, GIS, and video editing. The Moore Threads X300 GPU utilizes second-generation MUSA architecture, featuring 4096 MUSA cores that deliver 14.4 TFLOPS of FP32 computing power. It comes equipped with 16 GB of GDDR6 memory on a 256-bit bus, achieving a memory bandwidth of 448 GB/s. The X300 takes advantage of PCIe Gen 5 x16 connectivity and offers versatile display options through three DisplayPort 1.4a ports and one HDMI 2.1 port, supporting resolutions up to 7680 x 4320. All of that comes on a 255 W TGP package.

While the X300 GPU may be a new SKU, it resembles Moore Threads MTT S80 gaming GPU with a different firmware and set of drivers. The new X300 features hardware accelerated decoding for AV1, H.264, H.265, VP8, VP9, AVS, AVS2, MPEG4, and MPEG2, while also providing hardware encoding capabilities for AV1, H.264, and H.265. Given the professional application, the X300 can simultaneously handle up to 36 channels of 1080p@30 FPS video for both encoding and decoding operations while supporting 4-way display output up to 8K resolution. Interestingly, Moore Threads developed drivers for all mainstream CPU architectures such as x86, Arm, and even LoongArch.

AMD today introduced the Radeon PRO V710, the newest member of AMD's family of visual cloud GPUs. Available today in private preview on Microsoft Azure, the Radeon PRO V710 brings new capabilities to the public cloud. The AMD Radeon PRO V710's 54 Compute Units, along with 28 GB of VRAM, 448 GB/s memory transfer rate, and 54 MB of L3 AMD Infinity Cache technology, support small to medium ML inference workloads and small model training using open-source AMD ROCm software.

With support for hardware virtualization implemented in compliance with the PCI Express SR-IOV standard, instances based on the Radeon PRO V710 can provide robust isolation between multiple virtual machines running on the same physical GPU and between the host and guest environments. The efficient RDNA 3 architecture provides excellent performance per watt, enabling a single slot, passively cooled form factor compliant with the PCIe CEM spec.

VIA Technologies, Inc., a leading innovator in the development of embedded platforms and systems, today announced the launch of three new high-performance edge AI solutions: the SOM-5000, VAB-5000, and ARTiGO A5000. These platforms are designed to meet the growing demand for intelligent edge computing across a wide range of industrial, commercial, and consumer applications.

"These new platforms represent a significant leap forward in edge AI technology," said Epan Wu, General Manager, VIA Intelligent Solutions. "With their advanced processing capabilities and versatile connectivity options, the SOM-5000, VAB-5000, and ARTiGO A5000 enable our customers to develop innovative and efficient edge AI applications."

Twitch, OBS and NVIDIA are leveling up livestreaming technology with the new Twitch Enhanced Broadcasting beta, powered by GeForce RTX GPUs. Available in a few days, streamers will be able to stream multiple encodes concurrently, providing optimal viewing experiences for all viewers. Today, many streamers must choose between higher resolution and reliable streaming. High-quality video provides more enjoyable viewing experiences but causes streams to buffer for viewers with low bandwidth or older viewing devices. Streaming lower-bitrate video allows more people to watch the content seamlessly, but introduces artifacts.

Twitch—the interactive livestreaming platform—provides server-side transcoding for top-performing channels, meaning it will create different versions of the same stream for different bandwidth levels, improving the viewing experience. But the audience of many channels are left with a single stream option. Twitch, OBS and NVIDIA have collaborated on a new feature to address this—Twitch Enhanced Broadcasting, releasing in beta later this month. Using the high-quality dedicated encoder (NVENC) in modern GeForce RTX and GTX GPUs, streamers will be able to broadcast up to three resolutions simultaneously at up to 1080p.

In April 2021, the Vulkan Working Group at Khronos released a set of provisional extensions, collectively referred to as Vulkan Video which provide seamless encoding and decoding of video streams using a variety of video coding standards. The December 2022 release of Vulkan 1.3.238 saw the finalization of the extensions to decode H.264 and H.265, and today, with the release of Vulkan 1.3.274, Khronos has finalized their counterpart: the extensions to enable encoding of H.264 and H.265 video streams. Leveraging the Vulkan framework, they provide a standardized, seamless, low-overhead, and highly controllable way to produce H.264 and H.265 video via hardware accelerators, with applications ranging from real-time, low-latency streaming to offline server-scale transcoding.

Incorporating industry feedback, the extensions saw many improvements since their introduction, from a bidirectional interface (overrides) to help with coding and exposing advanced hardware capabilities, to rate control configuration parameters and an interface to aid with quality vs. performance trade-offs. This feedback also prompted the release of the first video maintenance extension. In addition, given the high industry demand for AV1 codec support, an AV1 decode extension release is imminent, with an AV1 encode extension development also underway. Figure 1 depicts Vulkan Video extensions along with their status and relations.

QNAP Systems, Inc., a leading computing, networking, and storage solution innovator, today launched new NVR Network Surveillance Servers - the QVP-41C with four 3.5-inch SATA drive bays, and the QVP-21C with two 3.5-inch SATA drive bays. Incorporating Intel Celeron J6412 quad-core processors, QVR Pro surveillance software, and providing eight free IP camera channels, the QVP-41C and QVP-21C help SMBs and small offices to quickly upgrade to lightweight AI surveillance applications, offering an economic software and hardware integrated video surveillance solution. QNAP will provide long-term availability and support for the QVP-41C and QVP-21C, making them suitable for businesses requiring matching surveillance servers deployed in multiple locations.

"The high-performance QVP-41C and QVP-21C are specifically designed to fulfill small-and-medium-scale video surveillance analysis demands," said Andy Chuang, Product Manager of QNAP, adding "users can flexibly use QVR Face or QVR Smart Search to implement AI face recognition and smart events search to boost management effectiveness."

AMD today announced the AMD Alveo MA35D media accelerator featuring two 5 nm, ASIC-based video processing units (VPUs) supporting the AV1 compression standard and purpose-built to power a new era of live interactive streaming services at scale. With over 70% of the global video market being dominated by live content, a new class of low-latency, high-volume interactive streaming applications are emerging such as watch parties, live shopping, online auctions, and social streaming.

The Alveo MA35D media accelerator delivers the high channel density, with up to 32x 1080p60 streams per card, power efficiency and ultra-low-latency performance critical to reducing the skyrocketing infrastructure costs now required for scaling such compute intensive content delivery. Compared to the previous generation Alveo U30 media accelerator, the Alveo MA35D delivers up to 4x higher channel density, 4x max lower latency in 4K and 1.8x greater compression efficiency to achieve the same VMAF score—a common video quality metric.

In April 2021, the Vulkan Working Group at Khronos released a set of provisional extensions, collectively called "Vulkan Video," for seamlessly integrating hardware-accelerated video compression and decompression into the Vulkan API. Today, Khronos is releasing finalized extensions that incorporate industry feedback and expose core and decode Vulkan Video functionality to provide fully accelerated H.264 and H.265 decode.

Khronos will release an ongoing series of Vulkan Video extensions to enable additional codecs and accelerated encode as well as decode. This blog is a general overview of the Vulkan Video architecture and also provides details about the finalized extensions and links to important resources to help you create your first Vulkan Video applications.

Blackmagic Design today announced DaVinci Resolve 18, a major new cloud collaboration update which allows multiple editors, colorists, VFX artists and audio engineers to work simultaneously on the same project, on the same timeline, anywhere in the world. DaVinci Resolve 18 supports the Blackmagic Cloud for hosting and sharing projects, as well as a new DaVinci proxy workflow. This update also includes new Resolve FX AI tools powered by the DaVinci Neural Engine, as well as time saving tools for editors, Fairlight legacy fixed bus to FlexBus conversion, GPU accelerated paint in Fusion, and more! DaVinci Resolve 18 public beta is available for download now from the Blackmagic Design web site.

DaVinci Resolve 18 is a major release featuring cloud based workflows for a new way to collaborate remotely. Customers can host project libraries using Blackmagic Cloud and collaborate on the same timeline, in real time, with multiple users globally. The new Blackmagic Proxy generator automatically creates proxies linked to camera originals, for a faster editing workflow. There are new Resolve FX such as ultra beauty and 3D depth map, improved subtitling for editors, GPU accelerated Fusion paint and real time title template playback, Fairlight fixed to FlexBus conversion and more. DaVinci Resolve 18 supports Blackmagic Cloud, so customers can host their project libraries on the DaVinci Resolve Project Server in the cloud. Share projects and work collaboratively with editors, colorists, VFX artists and audio engineers on the same project at the same time, anywhere in the world.

Encoding video is one of the significant tasks that modern hardware performs. Today, we have some data of AMD and NVIDIA solutions for the problem that shows how good GPU hardware encoders are. Thanks to Chips and Cheese tech media, we have information about AMD's Video Core Next (VCN) encoder found in RDNA2 GPUs and NVIDIA's NVENC (short for NVIDIA Encoder). The site managed to benchmark AMD's Radeon RX 6900 XT and NVIDIA GeForce RTX 2060 GPUs. The AMD card features VCN 3.0, while the NVIDIA Turing card features a 6th generation NVENC design. Team red is represented by the latest work, while there exists a 7th generation of NVENC. C&C tested this because it means all that the reviewer possesses.

The metric used for video encoding was Netflix's Video Multimethod Assessment Fusion (VMAF) metric composed by the media giant. In addition to hardware acceleration, the site also tested software acceleration done by libx264, a software library used for encoding video streams into the H.264/MPEG-4 AVC compression format. The libx264 software acceleration was running on AMD Ryzen 9 3950X. Benchmark runs included streaming, recording, and transcoding in Overwatch and Elder Scrolls Online.Below, you can find benchmarks of streaming, recording, transcoding, and transcoding speed.

Chinese company Moore Threads has unveiled their MTT GPU series just 18 months after the company's establishment in 2020. The MT Unified System Architecture (MUSA) architecture is the first for any Chinese company to be developed fully domestically and includes support for DirectX, OpenCL, OpenGL, Vulkan, and CUDA. The company announced the MTT S60 and MTT S2000 single slot desktop graphics cards for gaming and server applications at a recent event. The MTT S60 is manufactured on a 12 nm node and features 2,048 MUSA cores paired with 8 GB of LPGDDR4X memory offering 6 TFLOPs of performance. The MTT S2000 is also manufactured on a 12 nm node and doubles the number of MUSA cores to 4096 paired with 32 GB of undisclosed video memory allowing it to reach 12 TFLOPs.

Moore Threads joins Intel in supporting AV1 encoding on a consumer GPU with MUSA cards featuring H.264, H.265, and AV1 encoding support in addition to H.264, H.265, AV1, VP8, and VP9 decoding. The company is also developing a physics engine dubbed Alphacore which is said to work with existing tools such as Unity, Unreal Engine, and Houdini to accelerate physics performance by 5 to 10 times. The only gaming performance shown was a simple demonstration of the MTT S60 running League of Legends at 1080p without any frame rate details.

EIZO Rugged Solutions Inc., a provider of ruggedized graphics and video products, has released the Condor NVP2009AxX - an XMC graphics and GPGPU card that supports various combinations of analog and digital outputs.

The new high-performance graphics card based on the NVIDIA Quadro P2000 GPU (chip-down GP107) supports four field customizable video output combinations of DisplayPort++, 3G-SDI, CVBS (NTSC/PAL/SECAM), and VGA (STANAG 3350, RS-170, RS-343) to provide flexibility and simplify inventory management for high-end surveillance customers. With multiple I/O configurations, the card can support a range of video resolutions up to 4K and custom resolutions under VGA configurations. It can be factory configured to customer specifications and/or field programmed to support complex, multi-video needs after deployment.

Xilinx, Inc., the leader in adaptive and intelligent computing, today introduced two real-time computing video appliances for easy-to-scale, ultra-high-density video transcoding applications. Based on the new Xilinx Real-Time (RT) Server reference architecture, these new appliances will enable service providers delivering applications such as eSports and game streaming platforms, social and video conferencing, live distance learning, telemedicine and live broadcast video to optimize video quality and bitrate at the lowest cost per channel for significant TCO savings over both software-based and fixed-architecture approaches.

Designed for edge and on-premise compute-intensive workloads where video channel density, throughput and latency are critical requirements, the new Xilinx Real-Time Video Appliances feature optimized hardware architectures and software to deliver the industry's highest channel density and lowest latency performance. The appliances are available in two pre-configured options integrating Xilinx Alveo data center accelerator cards - the High Channel Density Video Appliance and the Ultra-Low Bitrate Video Appliance.

Adobe is releasing an important feature update to Premiere Pro later this week, which promises to introduce significant improvements to video encoding performance by better leveraging GPU acceleration. The new version 14.2 of Premiere Pro will leverage NVENC to boost encoding by over 5 times compared to CPU. The suite leveraged shaders to accelerate video effects and improving export times, but until now hadn't leveraged NVIDIA's hardware encoder. For machines with GeForce and Quadro GPUs, this means improved export times on H.264, H.265, and HEVC codecs. Without getting into specifics, Adobe mentioned that Premiere Pro will tap into video hardware acceleration capabilities of AMD Radeon GPUs, too.

Update 07:55 UTC: Adobe posted release notes of the latest version 14.2 of Premiere Pro. The list of system requirements needed for hardware-accelerated H.264 and HEVC encoding appears vague beyond pointing out that you need a compatible graphics solution. The list of compatible GPUs includes a wide selection of NVIDIA GPUs covering both its professional Quadro and consumer GeForce brands. On the AMD front, however, only the professional Radeon Pro SKUs are listed, and no consumer Radeon RX series SKUs.

Two of the often overlooked components of a new graphics architecture are the I/O and multimedia capabilities. With its Radeon RX 5700-series "Navi 10" graphics processor, AMD gave the two their first major update in over two years, with the new Radeon Display Engine, and Radeon Multimedia Engine. The Display Engine is a hardware component that handles the graphics card's physical display I/O. The Radeon Multimedia Engine is a set of fixed-function hardware that provides CODEC-specific acceleration to offload your CPU.

The Navi Radeon Display Engine features an updated DisplayPort 1.4 HDR implementation that's capable of handling 8K displays at 60 Hz with a single cable. It can also handle 4K UHD at 240 Hz with a single cable. These also include HDR and 10-bit color. It achieves this by implementing DSC 1.2a (Display Stream Compression). The display controller also supports 30 bpp internal color-depth. The HDMI implementation remains HDMI 2.0. The multi-plane overlay protocol (MPO) implementation now supports a low-power mode. This should, in theory, reduce the GPU's power draw when idling or playing back video.

At The National Association of Broadcasters Show (NAB Show) today, Intel and Netflix announced a new high-performance video codec that is available as open source and royalty-free to content creators, developers and service providers. Scalable Video Technology for AV1 (SVT-AV1) offers performance and scalability in video processing.

"The SVT-AV1 codec offers both high performance and efficiency. And compared to today's most popular codec (H.264 AVC), SVT-AV1 can help service providers save up to half their bandwidth, delivering leading-edge user experiences that can be quickly and cost-effectively delivered at a global scale. This codec makes it possible for services ranging from video on demand to live broadcast of 4Kp60/10-bit content on Intel Xeon Scalable processors, including the recently launched 2nd-Generation Intel Xeon Scalable processor," said Lynn Comp, Intel vice president of the Network Platforms Group and general manager of the Visual Cloud Division.

Following the releases of the TS-328 (powered by a Realtek CPU) and the TS-332X (powered by an AnnapurnaLabs CPU), QNAP Systems, Inc. today completes the 3-bay RAID 5 NAS lineup with the introduction of the high-end home NAS TS-351. The TS-351 is powered by an Intel Celeron J1800 processor, and includes a wide range of features for media streaming, instant sharing, HDMI-output, and auto-tiering for optimal storage efficiency. The TS-351 provides homes and home offices with an excellent file management and multimedia entertainment center.

The high-performance TS-351 uses an Intel Celeron J1800 dual-core 2.41 GHz processor (burst up to 2.58 GHz), features 2 GB/4 GB DDR3L memory (upgradable to 8 GB), supports SATA 3Gb/s and 6Gb/s disks, and enables AES 256-bit encryption for both full volumes and shared folders. Featuring a minimalist design with effective airflow and cooling, the TS-351 can easily fit home space. Its tool-less 3.5-inch hard drive installation allows easy system setup and maintenance.

Expanding beyond its highly-acclaimed strengths in video capture and playout, Magewell will take the wraps off the company's first standalone, hardware-based streaming encoder in booth SU6324 at the 2018 NAB Show. Making live streaming production remarkably simple even for non-professional users, the new Ultra Stream HDMI enables customers to record or stream high-quality video from a variety of sources with one click using on-device buttons or an intuitive, accompanying smartphone app.

Magewell's capture products are renowned for outstanding ease of use, and the Ultra Stream HDMI continues this tradition. Designed for users who want to stream but may have very little technical knowledge, the encoder is ideal for everyone from church volunteers, teachers and gamers to corporate marketers and live event organizers.

Synology Inc. announced the official launch of the DiskStation DS418play, a 4-bay NAS ideal for serving as a home multimedia center. The DS418play is equipped with a dual-core 2GHz processor capable of bursting up to 2.5GHz. It comes with 2GB DDR3L memory by default, which is twice the size of its predecessor, and expands up to 6GB to enhance multi-tasking operations. Powered by a new hardware transcoding engine, DS418play supports up to two channels of H.265/H.264 4K video transcoding.

"Mobile devices supporting 4K video recording are becoming increasingly popular. However, since 4K video clips are capacity-consuming and not all TVs at home support 4K video playback, users tend to record videos with lower resolution as an alternative," said Michael Wang, product manager at Synology Inc. "With DS418play supporting up to 40TB of raw capacity, users can store their favorite videos in ultra-high definition, organize and share videos with families and friends effortlessly, and transcode videos on-the-fly to allow video playback on devices that do not support 4K."

Apple today previewed macOS High Sierra, the latest version of the world's most advanced desktop operating system, delivering new core storage, video and graphics technologies that pave the way for future innovation on the Mac. macOS High Sierra offers an all-new file system, support for High-Efficiency Video Coding (HEVC) and an update to Metal, Apple's advanced graphics technology that powers everything from machine learning to virtual reality content creation. macOS High Sierra also includes a number of refinements to the apps Mac users enjoy every day, including Photos, Safari and Mail.

"macOS High Sierra delivers important forward-looking technologies and new opportunities for developers wanting to tap into the power of machine learning and create immersive VR content on the Mac," said Craig Federighi, Apple's senior vice president of Software Engineering. "The core technology innovations in macOS High Sierra, combined with our advances in hardware, will continue to push the Mac forward in exciting new ways."

As the world's number one PC motherboard manufacturer by volume, it would be a shame if ASUS didn't pander to the budding engineers and electronics hobbyists among you with a product that rivals the Raspberry Pi and Intel Edison. That product is the TinkerBoard, a card-sized single-board computer with a ton of I/O, including support for 4K Ultra HD displays. At the heart of this board is a Rockchip RK3288 SoC, which embeds a 32-bit quad-core ARM Cortex-A17 CPU, and a Mali T764 GPU. This chip is topped off by 2 GB of dual-channel memory. The most prominent Raspberry Pi competitor to this board is the Pi 3 Model B, with its 64-bit Broadcom BCM2837 chip, and a starting price of just $35.

Other features of the TinkerBoard include a GPIO that rivals Raspberry Pi, 4K Ultra HD H.264 video decode capability, gigabit Ethernet, SDIO 3.0, 24-bit/192 kHz HD audio, and a swappable antenna for its 802.11 b/g/n WLAN. While the specifications check out well in favor of the TinkerBoard, it all comes down to pricing. Hobbyists working on robotics projects, for example, purchase Raspberries Pi by the dozens thanks to their low price. ASUS should do well to keep that in mind when pricing this board.