Moore Threads
Moore Threads Technology Co. Ltd is a Beijing-based Chinese fabless semiconductor company that specializes in GPU manufacturing. Zhang Jianzhong,Nvidia former global VP and China GM, founded it in October 2020.the first in China to introduce a "fully featured" domestic GPU solution. [1]
Specification
- MTT S1000M
MTT S1000M adopts 12NM process, uses 1024 MUSA cores, single-precision computing power can reach up to 2TFlops, configures 32GB video memory, supports H.264, H.265, AV1 multi-channel high-definition video encoding, and multi-channel AV1, H.264, UHD video decoding in H.265, VP9, VP8, MPEG1/2/4, AVS2 and other formats, and can support up to 8K resolution. MTT S1000M is a half-height, half-length, single-slot PCIE card optimized for video scenarios. It adopts passive heat dissipation and consumes a maximum of 35W.
Moore Threads integrates Moore Threads first-generation intelligent multimedia engine MT Smart Media Engine for MTT S1000M, which can accelerate various audio and video applications on the cloud and edge side, such as security intelligence, video conferencing, live VOD, cloud gaming, cloud desktop, etc. Supports the audio and video processing ecosystem by being compatible with the FFmpegy audio and video framework and the VA-API application program interface, providing customers with the underlying GPU hardware encoding and decoding capabilities; supporting OpenGL, OpenGL ES, Vulkan and other graphics APIs; compatible with Pytorch, TensorFlow, PaddlePaddle and other artificial intelligence computing frameworks; through OpenCL to meet the program compatibility of AI and scientific computing.
Moore Threads MTT S1000M is compatible with X86, ARM and other CPU architectures and mainstream Linux operating system distributions.
Supports multiple audio and video frameworks and formats Support for modern graphics rendering engines Support a variety of artificial intelligence computing frameworks Support OpenCL 3.0 parallel computing Support X86, ARM architecture CPU Support Ubuntu, Kylin, Tongxin and other operating systems MT GMI Status and Performance Monitoring
- MTT S2000
MTT S2000 uses a 12NM process, uses 4096 MUSA cores, configures a maximum of 32GB of video memory, has a single-precision computing power of up to 12TFlops, supports H.264, H.265, AV1 multi-channel HD video encoding and decoding, and a wide range of AI model computing power acceleration. The MTT S2000 adopts passive cooling, single-slot design to meet the high-density GPU configuration mode of data center.
Moore Threads has launched a special unified programming model, runtime, driver and other software tools for hardware architecture for MTT S2000 series products, which can facilitate developers to complete the porting and adaptation of applications and fully call MTT OpenGL ES, DirectX, Vulkan and other graphics APIs; Support audio and video processing ecology through FFAMPEG and VA-API/DXVA compatibility; And through OpenCL and Vulkan to meet the AI and scientific computing program compatibility.
Moore Threads MTT S2000 is compatible with CPU architectures such as X86 and ARM and mainstream Linux operating system distributions, and has begun to cooperate with a number of server partners to adapt to a variety of OEM manufacturers' general-purpose server and GPU server models, which can be deployed in many hardware and application environments.[3]
Support for modern graphics rendering engines Support H.264, H.265 and AVI encoding formats Support AVI, H.264, H.265 and other encoding formats Supports AI computing such as Pytorch, TensorFlow, paddle, etc Supports OpenCL 3.0 parallel computing Support X86, ARM architecture CPU Support Ubuntu, Kirin, Tongxin and other operating systems MT GMI status and performance monitoring
- MTT S50
MTT S50 adopts 12NM process, uses 2048 MUSA cores, single-precision computing power can reach up to 5TFlops, is equipped with 8GB video memory, supports H.264, H.265, AV1 multi-channel high-definition video codec, supports 4K ultra-high-definition display, and a wide range of The computing power of the AI model is accelerated. The MTT S50 adopts a turbo fan for active cooling and a standard PCIE single-slot design.
Moore Threads has launched a unified programming model, runtime library, driver and other software tools for the MTT S50 series products for the hardware architecture, which can facilitate developers to complete the application porting and adaptation, and fully utilize the hardware resources and computing power of the MTT S50. MTT S50 supports OpenGL, OpenGL ES, DirectX, Vulkan and other graphics APIs; supports audio and video processing ecology through FFMPEG and VA-API/DXVA; and satisfies the program compatibility of AI and scientific computing through OpenCL and Vulkan.
Moore Threads MTT S50 is compatible with X86, ARM and other CPU architectures as well as process Linux, international Linux, Windows operating system distributions.
Support for modern graphics rendering engines Support AV1, H.264/H.265 and other encoding formats Support AV1, H.264, H.265, VP9,AVS2 and other decoding formats Support Pytorch, TensorFlow, Paddle and other Al computing frameworks Supports OpenCL parallel computing Support X86, ARM architecture CPU Support Ubuntu, Kirin, Tongxin and other operating systems PES control center integrates product information, software settings
Reviews
Reuters Analysis: U.S. ban on Nvidia, AMD chips seen boosting Chinese rivals Moore Threads. [4] Author of Semiconductor Deep Dive: Nvidia: Biden Targeting China On The AI Front.[5]
