System on a chip by Nvidia
Nvidia Tegra T20 (Tegra 2) and T30 (Tegra 3) chips A Tegra X1 inside a Shield TV Tegra is asystem on a chip (SoC) series developed byNvidia for mobile devices such assmartphones ,personal digital assistants , andmobile Internet devices . The Tegra integrates anARM architecture central processing unit (CPU),graphics processing unit (GPU),northbridge ,southbridge , andmemory controller onto one package. Early Tegra SoCs are designed as efficient multimedia processors. The Tegra-line evolved to emphasize performance for gaming andmachine learning applications without sacrificing power efficiency, before taking a drastic shift in direction towards platforms that providevehicular automation with the applied "Nvidia Drive Nvidia Jetson AI applications within e.g. robots or drones, and for various smart high level automation purposes.
The TegraAPX 2500 was announced on February 12, 2008. The Tegra 6xx product line was revealed on June 2, 2008,[ 1] smartbooks andmobile Internet devices (MID).[ 2]
The first product to use the Tegra wasMicrosoft 'sZune HD media player in September 2009, followed by theSamsung M1.[ 3] Kin was the first cellular phone to use the Tegra;[ 4] Opera Software announced that they would produce a version of theOpera 9.5 browser optimized for the Tegra onWindows Mobile andWindows CE .[ 5] [ 6] Mobile World Congress 2009, Nvidia introduced its port ofGoogle 'sAndroid to the Tegra.
On January 7, 2010, Nvidia officially announced and demonstrated its next generation Tegra system-on-a-chip, the Nvidia Tegra 250, atConsumer Electronics Show 2010 .[ 7] bootloader is accessible. Tegra 2 support for theUbuntu Linux distribution was also announced on the Nvidia developer forum.[ 8]
Nvidia announced the firstquad-core SoC at the February 2011Mobile World Congress event in Barcelona. Though the chip was codenamed Kal-El, it is now branded as Tegra 3. Early benchmark results show impressive gains over Tegra 2,[ 9] [ 10]
In January 2012,Nvidia announced thatAudi had selected the Tegra 3 processor for itsIn-Vehicle Infotainment systems and digital instruments display.[ 11] Audi 's entire line of vehicles worldwide, beginning in 2013. The process isISO 26262 -certified.[ 12]
In summer of 2012Tesla Motors began shipping theModel S all electric, high performancesedan , which contains two NVIDIA Tegra 3D Visual Computing Modules (VCM). One VCM powers the 17-inchtouchscreen infotainment system, and one drives the 12.3-inch alldigital instrument cluster ."[ 13]
In March 2015, Nvidia announced the Tegra X1, the first SoC to have a graphics performance of 1 teraflop. At the announcement event, Nvidia showed offEpic Games' Unreal Engine 4 "Elemental" demo, running on a Tegra X1.
On October 20, 2016, Nvidia announced that theNintendo Switch hybrid video game console will be powered by Tegra hardware.[ 14] [ 15]
Tegra APX 2500 Tegra APX 2600 Enhanced NAND flash Video codecs:[ 16] 720p H.264 Baseline Profile encode or decode 720p VC-1/WMV9 Advanced Profile decode D-1 MPEG-4 Simple Profile encode or decode Tegra 600 Targeted for GPS segment and automotive Processor: ARM11 700 MHz MPCore Memory:low-power DDR (DDR-333 , 166 MHz) SXGA, HDMI, USB, stereo jack HD camera 720p Tegra 650 Targeted for GTX of handheld and notebook Processor: ARM11 800 MHz MPCore Low power DDR (DDR-400 , 200 MHz)Less than 1 watt envelope HD image processing for advanced digital still camera and HD camcorder functions Display supports1080p at 24 frame/s, HDMI v1.3, WSXGA+ LCD and CRT, and NTSC/PAL TV output Direct support for Wi-Fi, disk drives, keyboard, mouse, and other peripherals A completeboard support package (BSP) to enable fast time to market for Windows Mobile-based designs Nvidia Tegra 2 T20 The second generation Tegra SoC has adual-core ARM Cortex-A9 CPU, an ultra low power (ULP) GeForce GPU,[ 17] [ 18] NEON . There is a version of the Tegra 2 SoC supporting 3D displays; this SoC uses a higher clocked CPU and GPU.
The Tegra 2 video decoder is largely unchanged from the original Tegra and has limited support for HD formats.[ 19]
Common features:
CPU cache: L1: 32 KB instruction + 32 KB data, L2: 1 MB 40 nm semiconductor technologyModel CPU GPU Memory Adoption Processor Cores Frequency Micro- Core config1 Frequency Type Amount Bus Band- Availability AP20H(Ventana/ Cortex-A9 2 1.0 GHz VLIW -based[ 20] 4:4:4:4[ 21] 300 MHz LPDDR2 DDR2 ? 32 bit 2.4GB/s Q1 2010 T20(Harmony/ 333 MHz AP25 1.2 GHz 400 MHz Q1 2011 T25
1 Pixel shaders :Vertex shaders :Texture mapping units :Render output units Nvidia Tegra 2 T20 die shot Model Devices AP20H Motorola Atrix 4G ,Motorola Droid X2 ,Motorola Photon ,LG Optimus 2X / LG Optimus Dual P990 / Optimus 2x SU660 (?) ,Samsung Galaxy R ,Samsung Captivate Glide ,T-Mobile G2X P999 ,Acer Iconia Tab A200 and A500,LG Optimus Pad ,Motorola Xoom ,[ 22] Sony Tablet S , Dell Streak Pro,[ 23] [ 24] T-Mobile G-Slate AP25 Fusion Garage Grid 10[citation needed T20 Avionic Design Tamonten Processor Board,[ 25] Adam tablet ,Olivetti OliPad 100,ViewSonic G Tablet ,ASUS Eee Pad Transformer ,Samsung Galaxy Tab 10.1 ,Toshiba AC100 , CompuLabTrim-Slice nettop,Velocity Micro Cruz Tablet L510,Acer Iconia Tab A100 Unknown Tesla Motors Model S 2012~2017 and Model X 2015~2017 instrument cluster (IC)[ 26] [ 27]
Nvidia Tegra 3 T30L NVIDIA's Tegra 3 (codenamed "Kal-El ")[ 28] ARM Cortex-A9 MPCore CPU, but includes a fifth "companion" core in what Nvidia refers to as a "variableSMP architecture".[ 29]
Tegra 3 is the first Tegra release to support ARM's SIMD extension,NEON .
The GPU in Tegra 3 is an evolution of the Tegra 2 GPU, with 4 additional pixel shader units and higher clock frequency. It can also output video up to 2560×1600 resolution and supports1080p MPEG-4 AVC/h.264 40 Mbit/s High-Profile, VC1-AP, and simpler forms of MPEG-4 such as DivX and Xvid.[ 30]
The Tegra 3 was released on November 9, 2011.[ 31]
Common features:
CPU cache: L1: 32 KB instruction + 32 KB data, L2: 1 MB 40 nm LPG semiconductor technology byTSMC Model CPU GPU Memory Adoption Processor Cores Frequency Micro- Core1 Frequency Type Amount Bus Band- Availability T30L Cortex-A9 4+1 1.2 GHz / VLIW -based[ 20] 8:4:8:8[ 32] 416 MHz DDR3-1333 ? 32 bit 5.3 GB/s[ 33] Q1 2012 T30 1.4 GHz / 520 MHz LPDDR2-1066 DDR3-L-1500 ? 4.3 GB/s[ 34] Q4 2011 AP33 T33 1.6 GHz /[ 33] DDR3-1600 ? 6.4 GB/s[ 33] Q2 2012
1 Pixel shaders :Vertex shaders :Texture mapping units :Render output units TheOuya uses a Tegra 3 T33-P-A3. Model Devices AP33 LG Optimus 4X HD ,HTC One X , XOLO Play T1000,[ 35] T30 Asus Eee Pad Transformer Prime (TF201) ,[ 36] IdeaTab K2 / LePad K2,[ 37] Acer Iconia Tab A510, Fuhu Inc. nabi 2 Tablet,[ 38] Microsoft Surface RT ,[ 39] [ 40] [ 41] T30I Tesla Model S 2012~2017 and Model X 2015~2017 media control unit (MCU)[ 27] [ 42] T30L Asus Transformer Pad TF300T ,Microsoft Surface ,Nexus 7 (2012) ,[ 43] Sony Xperia Tablet S ,Acer Iconia Tab A210, Toshiba AT300 (Excite 10),[ 44] [unreliable source? BLU Quattro 4.5,[ 45] T33 Asus Transformer Pad Infinity (TF700T), Fujitsu ARROWS X F-02E,HTC One X+ ,Ouya (T33-P-A3)
The Tegra 4 (codenamed "Wayne ") was announced on January 6, 2013, and is a SoC with a quad-core CPU, but includes a fifth low-power Cortex A15 companion core which is invisible to the OS and performs background tasks to save power. This power-saving configuration is referred to as "variable SMP architecture" and operates like the similar configuration in Tegra 3.[ 46]
The GeForce GPU in Tegra 4 is again an evolution of its predecessors. However, numerous feature additions and efficiency improvements were implemented. The number of processing resources was dramatically increased, and clock rate increased as well. In 3D tests, the Tegra 4 GPU is typically several times faster than that of Tegra 3.[ 47] WebM video (up to 1080p 60 Mbit/s @ 60fps).[ 48]
Along with Tegra 4, Nvidia also introduced i500, an optionalsoftware modem based on Nvidia's acquisition ofIcera , which can be reprogrammed to support new network standards. It supports category 3 (100 Mbit/s) LTE but will later be updated to Category 4 (150 Mbit/s).
Common features:
CPU cache: L1: 32 KB instruction + 32 KB data, L2: 2 MB 28 nm HPL semiconductor technology1 Pixel shaders :Vertex shaders :Pixel pipelines (pairs 1x TMU and 1x ROP)Model Devices T114 Nvidia Shield Portable ,Tegra Note 7 ,Microsoft Surface 2 , HP Slate 7 Extreme,[ 55] [ 56] [ 57] [ 58] [ 59] HP Slate 21 ,[ 60] Project Mojo ,Asus Transformer Pad TF701T , Toshiba AT10-LE-A (Excite Pro),Vizio 10" tablet, Wexler.Terra 7, Wexler.Terra 10, Acer TA272HUL AIO,Xiaomi Mi 3 (TD-LTE version),[ 61] Coolpad 8970L (大观 [ 62] [ 63] [ 64] [ 65] [ 66]
The Tegra 4i (codenamed "Grey ") was announced on February 19, 2013. With hardware support for the same audio and video formats,[ 48] Icera i500LTE /HSPA+ baseband processor onto the same die.
Common features:
28 nm HPM semiconductor technologyCPU cache: L1: 32 KB instruction + 32 KB data, L2: 1 MB Model CPU GPU Memory Adoption Processor Micro- Core config1 Frequency Type Amount Bus Band- Availability T148?[ 67] 4+1 x 2.0 GHzCortex-A9 "R4" VLIW -based[ 50] 60[ 50] 660 MHz[ 51] LPDDR3 32-bit 6.4–7.5 GB/s[ 53] Q1 2014
1 Pixel shaders :Vertex shaders :Pixel pipelines (pairs 1x TMU and 1x ROP)Nvidia 's Tegra K1 (codenamed "Logan ") features ARM Cortex-A15 cores in a 4+1 configuration similar to Tegra 4, or Nvidia's64-bit Project Denver dual-core processor as well as aKepler graphics processing unit with support for Direct3D 12, OpenGL ES 3.1, CUDA 6.5,OpenGL 4.4 /OpenGL 4.5 , andVulkan .[ 73] [ 74] [ 75]
SupportAdaptive Scalable Texture Compression .[ 76]
In late April 2014, Nvidia shipped the "Jetson TK1" development board containing a Tegra K1 SoC and runningUbuntu Linux .[ 77]
Processor: GPU consisting of 192 ALUs usingKepler technology 28 nm HPM processReleased in Q2 2014 Power consumption: 8 watts[ 75] Model number CPU GPU Memory Adoption Processor Micro- Core1 Frequency GFLOPS Type Amount Bus Band- Availability T124 [ 80] [ 81] 4+1x @ 2.3 GHzCortex-A15 R3 GK20AKepler ) 192:8:4 756–951 MHz 290–365 DDR3L ,LPDDR3 max 8 GB(with 40-bit2 ) 64 bit 17 GB/s Q2 2014 T132[ 82] [ 83] 2x @ 2.5GHzDenver max 8 GB ? ? Q3 2014
1 Unified Shaders :Texture mapping units :Render output units 2 ARM Large Physical Page Extension (LPAE) supports 1 TiB (240 bytes).The 8 GiB limitation is part-specific. Model Devices T124 Jetson TK1 development board,[ 84] Shield Tablet ,[ 85] [ 86] [ 87] [ 88] Project Tango tablet,[ 89] [ 90] [ 91] [ 92] T132 HTCNexus 9 [ 93] [ 94]
In December 2015, the web page of wccftech.com published an article stating that Tesla is going to use a Tegra K1 based design derived from the template of the Nvidia Visual Computing Module (VCM) for driving the infotainment systems and providing visual driving aid in the respective vehicle models of that time.[ 95]
Tegra X1 inNvidia Shield TV Die shot of the Tegra X1 Released in 2015, Nvidia's Tegra X1 (codenamed "Erista ") features two CPU clusters, one with fourARM Cortex-A57 cores and the other with fourARM Cortex-A53 cores, as well as aMaxwell -based graphics processing unit.[ 96] [ 97] Adaptive Scalable Texture Compression .[ 76] [ 98] [ 99] [ 100] [ 101]
A revision (codenamed "Mariko ") with greater power efficiency, known officially asTegra X1+ was released in 2019,[ 102]
CPU : ARMv8ARM Cortex-A57 quad-core (64-bit) + (unused?)ARM Cortex-A53 quad-core (64-bit)GPU :Maxwell -based 256 core GPU (Jetson Nano: only 128 cores)MPEG-4 HEVC VP8 encoding/decoding &VP9 decoding support[ 103] H.265 , H.264/Stereo,VP8 ,JPEG ; decoders areH.265 , H.264/Stereo,VP8 ,VP9 ,VC-1 ,MPEG-2 ,JPEG )TSMC 20 nm process for the Tegra X1TSMC16 nm process for the Tegra X1+. TDP :T210: 15 W,[ 104] [ 103] Jetson Nano: 10 W (mode 0);[ 105] 1 CPU frequency may be clocked differently than the maximum validated by Nvidia at the OEM's discretion2 Unified Shaders :Texture mapping units :Render output units 3 Maximum validated amount of memory, implementation is board specific4 Maximum validated memory bandwidth, implementation is board specificThe X1 is the basis for theNintendo Switch video game console. Nvidia's Tegra X2[ 113] [ 114] Parker ") features Nvidia's own custom general-purpose ARMv8-compatible core Denver 2 as well as code-named Pascal graphics processing core withGPGPU support.[ 115] FinFET process technology usingTSMC 's 16 nm FinFET+ manufacturing process.[ 116] [ 117] [ 118]
CPU: Nvidia Denver2 ARMv8 (64-bit) dual-core + ARMv8 ARM Cortex-A57 quad-core (64-bit) RAM: up to 8 GBLPDDR4 [ 119] GPU:Pascal -based, 256CUDA cores; type: GP10B[ 120] TSMC 16 nm,FinFET process TDP: 7.5–15 W[ 121] Model SoC CPU GPU Memory Adoption Processor Micro- Frequency1 ) GFLOPSFP32 ) GFLOPSFP16 ) Type Amount Bus Band- Availability T186 Tegra X2 2x 1.4–2.0 GHzDenver2 +Cortex-A57 GP10BPascal )[ 122] 854–1465 MHz[ 123] 437– 874– LPDDR4 8 GB 128 bit 59.7 GB/s
1 Unified Shaders :Texture mapping units :Render output units (SM count)The Xavier Tegra SoC, named after the comic book characterProfessor X , was announced on 28 September 2016, and by March 2019, it had been released.[ 131] TPU (Tensor Processing Unit) called DLA (Deep Learning Accelerator).[ 132] [ 133] 8K Ultra HD (7680×4320). Users can configure operating modes at 10 W, 15 W, and 30 W TDP as needed and the die size is 350 mm2 .[ 134] [ 135] [ 136] 12 nm FinFET at CES 2018.[ 137]
CPU: Nvidia custom Carmel ARMv8.2-A (64-bit), 8 cores 10-wide superscalar[ 138] GPU:Volta -based, 512CUDA cores with 1.4 TFLOPS;[ 139] [ 140] [ 120] TSMC12 nm ,FinFET process[ 137] 20 TOPS DL and 160SPECint @ 20 W;[ 134] [ 136] 20 TOPS DL via the GPU based tensor cores 10 TOPS DL (INT8) via the DLA unit that shall achieve 5 TFLOPS (FP16)[ 139] 1.6 TOPS in the PVA unit (Programmable Vision Accelerator,[ 141] 1.5 GPix/s in the ISP unit (Image Signal Processor, with native full-range HDR and tile processing support) Video processor for 1.2 GPix/s encoding and 1.8 GPix/s decode[ 139] [ 135] MIPI-CSI-3 with 16 lanes[ 142] [ 143] 1 Gbit/s Ethernet 10 Gbit/s Ethernet Module SoC Variant CPU GPU Deep Memory Adoption TDP W )Processor Micro- Frequency1 ) TFLOPSFP32 ) TFLOPSFP16 ) TOPS Type Amount Bus Band- Availability Xavier AGX 64 GB Carmel GV11BVolta ) 1377 MHz 1.41 2.82 32 LPDDR4X 64 GB 256-bit 136.5 GB/s 10-30 Xavier AGX 32 GB 32 GB Xavier AGX Industrial Carmel 1221 MHz 1.24 2.48 30 LPDDR4X 32 GB 256-bit 136.5 GB/s 20-40 Xavier NX 16 GB Carmel Volta 1100 MHz 0.84 1.69 21 LPDDR4X 16 GB 128-bit 59.7 GB/s 10-20 Xavier NX 8 GB 8 GB
1 CUDA cores :Tensor cores (SMs, TPCs, GPCs)On the Linux Kernel Mailing List, a Tegra194 based development board with type ID "P2972-0000" got reported:
The board consists of the P2888 compute module and the P2822 baseboard. [ 153] Nvidia announced the next-gen SoC codenameOrin on March 27, 2018, at GPU Technology Conference 2018.[ 154]
It contains 17 billion transistors and 12 ARM Hercules cores and is capable of 200 INT8 TOPs @ 65W.[ 155] TheDrive AGX Orin board system family was announced on December 18, 2019, atGTC China 2019 . Nvidia has sent papers to the press documenting that the known (from Xavier series) clock and voltage scaling on the semiconductors
and by pairing multiple such chips a wider range of application can be realized with the thus resulting board concepts.[ 156] In early 2021, Nvidia announced the Chinese vehicle companyNIO will be using an Orin-based chip in their cars.[ 157] The so far published specifications for Orin are:
CPU: 12×Arm Cortex-A78 AE (Hercules ) ARMv8.2-A (64-bit)[ 158] [ 159] GPU: Ampere -based, 2048[ 160] CUDA cores and 64 tensor cores1 ; "with up to 131 Sparse TOPs[ 161] 5.3 CUDA TFLOPs (FP32)[ 162] 10.6 CUDA TFLOPs (FP16)[ 162] Samsung8 nm process[ 162] 275 TOPS (INT8) DL[ 162] 170 TOPS DL (INT8) via the GPU 105 TOPS DL (INT8) via the 2xNVDLA 2.0 units (DLA , Deep Learning Accelerator) 85 TOPS DL (FP16)[ 162] 5 TOPS in the PVA v2.0 unit (Programmable Vision Accelerator for Feature Tracking) 1.85 GPix/s in the ISP unit (Image Signal Processor, with native full-range HDR and tile processing support) Video processor for ? GPix/s encoding and ? GPix/s decode 4× 10 Gbit/s Ethernet, 1× 1 Gbit/s Ethernet 1 Orin uses the double-rate tensor cores in the A100, not the standard tensor cores in consumer Ampere GPUs.Nvidia announced the latest member of the family, "Orin Nano" in September 2022 at the GPU Technology Conference 2022.[ 163]
The Orin product line now features SoC and SoM (System-On-Module) based on the core Orin design and scaled for different uses from 60W all the way down to 5W. While less is known about the exact SoC's that are being manufactured, Nvidia has publicly shared detailed technical specifications about the entire Jetson Orin SoM product line. These module specifications illustrate how Orin scales providing insight into future devices that contain an Orin derived SoC.
Module SoC Variant CPU GPU Deep Memory Adoption TDP W )Processor Micro- Frequency1 ) TFLOPSFP32 ) TFLOPSFP16 ) TOPS Type Amount Bus Band- Availability Orin AGX[ 164] [ 165] Cortex-A78AE Ampere 1300 MHz 5.32[ 161] 10.649 275 LPDDR5 64 GB 256-bit 204.8 GB/s Sample 2021, 15-60 Orin AGX[ 166] Cortex-A78AE 930 MHz 3.365[ 161] 6.73 200 32 GB Oct 2022 15-40 Orin NX[ 167] TE980-M[ 168] Cortex-A78AE 918 MHz 1.88 3.76 100 16 GB 128-bit 102.4 GB/s Dec 2022 10-25 Orin NX[ 166] TE980-M[ 168] Cortex-A78AE 765 MHz 1.57 3.13 70 8 GB Jan 2023 10-20 Orin Nano[ 166] Cortex-A78AE 625 MHz 1.28 2.56 40 68 GB/s 7-15 Orin Nano[ 166] 625 MHz 0.64 1.28 20 4 GB 64-bit 34 GB/s 5-10
1 CUDA cores :Tensor cores :RT cores (SMs, TPCs, GPCs)Model Devices Comments T234[ 169] Nvidia Jetson AGX Orin[ 170] [ 161] comes in 32 GB and 64 GB RAM configurations, available as standalone module or devkit; Unknown Nvidia Jetson Orin NX[ 167] mid-power SODIMM-form factor Orin-series module, available only as standalone module; Unknown Nvidia Jetson Orin Nano[ 171] low-power, cost-effective SODIMM-form factor Orin-series module, available Unknown NvidiaDRIVE AGX Orin used in automotive ADAS applications. 1×Orin 12×A78AE 32GB LPDDR5 @100W, 167+87 INT8 TOPS Unknown Nio Adam[ 172] [ 173] built from 4× Nvidia Drive Orin, totals to 48 CPU cores and 8,192 CUDA cores;ET7 in March 2022 andET5 in September 2022 T239 Nintendo Switch 2 octa-core ARM Cortex-A78C CPU, 12 SM Ampere GPU, 128-bit LPDDR5x memory interface
TheGrace CPU is an NVIDIA-developed ARM Neoverse CPU platform, targeted at large-scale AI and HPC applications, available within several NVIDIA products. The NVIDIA OVX platform combines the Grace Superchip (two Grace dies on one board) with desktop NVIDIA GPUs in a server form-factor, while the NVIDIA HGX platform is available with either the Grace Superchip or the Grace Hopper Superchip.[ 174] Hopper -based GPU, announced by NVIDIA on March 22, 2022.[ 175] [ 176]
Model CPU Memory Adoption Processor Cores Frequency Cache TFLOPS(FP64)
Type Amount Bus Band- Availability T241[ 177] Grace 72ARM Neoverse V2 Cores (ARMv9 )[ 178] ? L1: 64 KB I-cache + 64 KB D-cache per coreL2: 1 MB per coreL3: 117 MB shared[ 178]
3.551 [ 178] LPDDR5X ECC[ 178] Up to 480 GB1 [ 178] ? 500 GB/s[ 178] H2 2023[ 179]
1 Figures cut in half from full Grace Superchip specification
Nvidia announced the next-gen SoC codenameAtlan on April 12, 2021, at GPU Technology Conference 2021.[ 180] [ 181]
Nvidia announced the cancellation of Atlan on September 20, 2022, and their next SoC will be Thor.[ 182]
Functional units known so far are:
Grace Next CPU[ 183] Ada Lovelace GPU[ 184] Bluefield DPU (Data Processing Unit) other Accelerators Security Engine Functional Safety Island On-Chip-Memory External Memory Interface(s) High-Speed-IO Interfaces Model CPU GPU Deep Learning Memory Adoption Processor Cores Frequency Micro- Core1 Frequency GFLOPSFP32 ) GFLOPSFP16 ) TOPS(INT8)
Type Amount Bus Band- Availability T254? Grace-Next[ 183] ? ? Ada Lovelace[ 185] ? ? ? ? >1000[ 186] ? ? ? ? Cancelled[ 187]
Nvidia announced the next-gen SoC codename Thor on September 20, 2022, at GPU Technology Conference 2022, replacing the cancelled Atlan.[ 182] [ 188]
Model CPU GPU Deep Learning Memory Adoption Processor Cores Frequency Micro- Core1 Frequency GFLOPSFP32 ) GFLOPSFP16 ) TOPS(FP8)
Type Amount Bus Band- Availability T264? Arm Neoverse V3AE[ 191] ? ? Blackwell ? ? ? ? 2000[ 182] ? 128 GB ? ? 2025[ 182]
Generation Tegra 2 Tegra 3 Tegra 4 Tegra 4i Tegra K1 Tegra X1 Tegra X1+ Tegra X2 Xavier Orin Thor CPU Instruction set ARMv7‑A (32‑bit)ARMv8‑A (64‑bit)ARMv8.2‑A (64‑bit)ARMv9.2‑A (64‑bit)Cores 2A9 4+1A9 4+1A15 4+1A9 4+1A15 2Denver 4A53 (disabled) +A57 2Denver2 + 4A57 8Carmel 12A78 AE Neoverse V3AEL1 cache (I/D) 32/32 KB 128/64 KB 32/32 KB + 64/32 KB 128/64 KB + 48/32 KB 128/64 KB 64/64 KB L2 cache 1 MB 2 MB 128 KB + 2 MB 2 MB + 2 MB 8 MB 3 MB ? L3 cache N/A 4 MB 6 MB ? GPU Architecture Vec4 Kepler Maxwell Pascal Volta Ampere Blackwell CUDA cores 4+4* 8+4* 48+24* 48+12* 192 256 512 2048 ? Tensor cores N/A 64 ? RT cores N/A 8 ? RAM Protocol DDR2/LPDDR2 DDR3/LPDDR2 DDR3/LPDDR3 LPDDR3/LPDDR4 LPDDR4/LPDDR4X LPDDR5 ? Max. size 1 GB 2 GB 4 GB 8 GB 64 GB 128 GB Bandwidth 2.7 GB/s 6.4 GB/s 7.5 GB/s 14.88 GB/s 25.6 GB/s 34.1 GB/s 59.7 GB/s 136.5 GB/s 204.8 GB/s ? Process 40 nm 28 nm 20 nm 16 nm 12 nm 8 nm 4 nm
*VLIW -based Vec4:Pixel shaders +Vertex shaders . Since Kepler, Unified shaders are used.
FreeBSD supports a number of different Tegra models and generations, ranging from Tegra K1,[ 192] [ 193]
Nvidia distributes proprietary device drivers for Tegra throughOEMs and as part of its "Linux for Tegra" (formerly "L4T") development kit, also Nvidia provides JetPack SDK with "Linux for Tegra" and other tools with it. The newer and more powerful devices of the Tegra family are now supported by Nvidia's ownVibrante Linux distribution. Vibrante comes with a larger set of Linux tools plus several Nvidia provided libraries for acceleration in the area of data processing and especially image processing for driving safety and automated driving up to the level ofdeep learning and neuronal networks that make e.g. heavy use of the CUDA capable accelerator blocks, and viaOpenCV can make use of theNEON vector extensions of the ARM cores.
As of April 2012[update] GeForce line of graphics cards, Nvidia and one of their Embedded Partners, Avionic Design GmbH from Germany, are also working on submittingopen-source drivers for Tegra upstream to the mainlineLinux kernel .[ 194] [ 195] GPU Technology Conference 2013.[ 196] [unreliable source?
By end of 2018 it is evident that Nvidia employees have contributed substantial code parts to make the T186 and T194 models run for HDMI display and audio with the upcoming official Linux kernel 4.21 in about Q1 2019. The affected software modules are the open source Nouveau and the closed source Nvidia graphics drivers along with the Nvidia proprietary CUDA interface.[ 197] [unreliable source?
As of May, 2022, NVIDIA has open-sourced their GPU kernel modules for both Jetson and desktop platforms, allowing all but proprietary userspace libraries to be open-source on Tegra platforms with official NVIDIA drivers starting with T234 (Orin).[ 198]
The Drive PX2 board was announced withQNX RTOS support at the April 2016 GPU Technology Conference.[ 199]
SoCs and platforms with comparable specifications (e.g. audio/video input, output and processing capability, connectivity, programmability, entertainment/embedded/automotive capabilities & certifications, power consumption) are:
^ "Techtree.com India > News > Hardware > Nvidia Rolls out "Tegra" Chips" . June 4, 2008. Archived fromthe original on June 4, 2008.^ "NVIDIA Tegra FAQ" (PDF) .Nvidia.com .Archived (PDF) from the original on March 20, 2012. RetrievedJune 4, 2008 .^ "Nvidia prepara Tegra 3 a 1,5 GHz" . TugaTech. January 27, 2011.Archived from the original on October 16, 2017. RetrievedJuly 10, 2016 .^ "Microsoft's Kin are the first Tegra smartphones – PC World Australia" .Pcworld.idg.com.au . April 13, 2010. Archived fromthe original on October 16, 2017. RetrievedJuly 10, 2016 .^ "Nvidia and Opera team to accelerate the full Web on mobile devices" (Press release).Opera Software . September 9, 2008.Archived from the original on March 30, 2012. RetrievedJanuary 9, 2009 .^ "Nvidia And Opera Team To Accelerate The Full Web On Mobile Devices" (Press release). NVIDIA. September 9, 2008.Archived from the original on December 24, 2011. RetrievedApril 17, 2009 .^ "New Nvidia Tegra Processor Powers The Tablet Revolution" .Nvidia . January 7, 2010.Archived from the original on December 24, 2018. RetrievedMarch 19, 2010 .^ "What operating systems does Tegra support?" (Press release). NVIDIA. August 17, 2011.Archived from the original on September 3, 2011. RetrievedSeptember 14, 2011 .^ "Why nVidia's Tegra 3 is faster than a Core 2 Duo T7200" . Brightsideofnews.com. February 21, 2011.Archived from the original on August 23, 2011. RetrievedAugust 12, 2011 .^ Hruska, Joel (February 22, 2011)."Nvidia's Kal-El Demonstration Marred By Benchmark Confusion" . HotHardware. Archived fromthe original on February 26, 2012. RetrievedJuly 15, 2016 . ^ "Audi selects Tegra processor for infotainment and dashboard" . EE Times. January 18, 2012.Archived from the original on January 20, 2012. RetrievedJuly 15, 2016 .^ "What Is Automotive Grade? Here's What It Means" .The Official NVIDIA Blog . July 15, 2016.Archived from the original on October 11, 2016. RetrievedOctober 11, 2016 .^ "Tegra Automotive Infotainment and Navigation" . NVIDIA.Archived from the original on January 23, 2013. RetrievedJanuary 4, 2013 .^ "NVIDIA Gaming Technology Powers Nintendo Switch | NVIDIA Blog" .The Official NVIDIA Blog . October 20, 2016.Archived from the original on January 26, 2017. RetrievedOctober 20, 2016 .^a b techinsights.com."Nintendo Switch Teardown" .www.techinsights.com .Archived from the original on March 13, 2017. RetrievedMarch 15, 2017 . ^ "Nvidia Tegra APX Specifications" .Archived from the original on January 27, 2011. RetrievedFebruary 17, 2011 .^ "LG Optimus 2X & Nvidia Tegra 2 Review: The First Dual-Core Smartphone" . AnandTech.Archived from the original on April 26, 2014. RetrievedAugust 12, 2011 .^ "NVidia Tegra 2 Product Information" . NVidia.Archived from the original on May 4, 2012. RetrievedSeptember 5, 2011 .^ "NVidia Tegra 2 Product Information" . NVidia.Archived from the original on May 8, 2012. RetrievedNovember 1, 2015 .^a b c Shimpi, Anand Lal ."The Tegra 4 GPU, NVIDIA Claims Better Performance Than iPad 4" .AnandTech Archived from the original on January 21, 2019. RetrievedNovember 5, 2015 .^ "NVIDIA Tegra 2 GPU Specs" . July 25, 2023.^ "Motorola Xoom Specifications Table" . Motorola Mobility, Inc. February 16, 2011. Archived fromthe original on February 20, 2011. RetrievedFebruary 16, 2011 .^ Savov, Vlad (May 19, 2011)."Dell Streak Pro Honeycomb tablet pictured, likely to be with us in June" .Engadget .Archived from the original on October 24, 2017. RetrievedFebruary 5, 2016 . ^ "Toshiba Thrive Review" .TabletPCReview . TechTarget, Inc. August 3, 2011.Archived from the original on November 6, 2013. RetrievedNovember 21, 2013 .^ "Avionic Design Tegra 2 (T290) Tamonten Processor Module — Product Brief" (PDF) . Avionic Design. Archived fromthe original (PDF) on May 21, 2014. RetrievedMay 25, 2012 .^ Nvidia inside: Hands on with Audi, Lamborghini, and Tesla Archived March 15, 2018, at theWayback Machine by Megan Geuss in May 2014^a b Processors Analysis and Count Archived March 15, 2018, at theWayback Machine in May 2013^ "Nvidia announces the Tegra 3 – Kal-El brings PC class performance to Android" . Android Central. November 9, 2011.Archived from the original on July 16, 2012. RetrievedJuly 10, 2016 .^ "Tegra 3 Multi-Core Processors" . NVIDIA.Archived from the original on April 28, 2012. RetrievedJuly 15, 2016 .^ "ASUS Transformer Prime introduced and examined" . HEXUS.net. November 9, 2011.Archived from the original on November 11, 2011. RetrievedNovember 11, 2011 .^ "NVIDIA Quad-Core Tegra 3 Chip Sets New Standards of Mobile Computing Performance, Energy Efficiency – NVIDIA Newsroom" . January 11, 2012. Archived fromthe original on January 11, 2012.^ "NVIDIA Tegra 3 GPU Specs" . July 25, 2023.^a b c "A Faster Tegra 3, More Memory Bandwidth – ASUS Transformer Pad Infinity (TF700T) Review" .Anandtech.com .Archived from the original on June 27, 2012. RetrievedJuly 10, 2016 .^ "Tegra 3 Multi-Core Processors" . NVIDIA.Archived from the original on April 28, 2012. RetrievedJuly 10, 2016 .^ "XOLO – The Next Level" . July 21, 2013. Archived fromthe original on July 21, 2013.^ "Asus Eee Pad Transformer Prime (Nvidia Tegra 3 Processor; 10.1-inch display) Review" . December 30, 2011. Archived fromthe original on April 2, 2013.^ "GFXBench – unified graphics benchmark based on DXBenchmark (DirectX) and GLBenchmark (OpenGL ES)" .Glbenchmark.com .Archived from the original on January 22, 2012. RetrievedJuly 15, 2016 .^ Summerson, Cameron (June 19, 2012)."Fuhu Nabi 2 Review: A Quad-Core Android 4.0 Tablet Designed Just For Your Kids – And It's Surprisingly Awesome" .Androidpolice.com .Archived from the original on June 22, 2012. RetrievedJuly 15, 2016 . ^ "Microsoft Announces New Surface Details | News Center" .Microsoft.com . October 16, 2012.Archived from the original on July 12, 2014. RetrievedJuly 15, 2016 .^ "Lenovo Introduces The IdeaPad Yoga 11 and 13, The First Tablet & Laptop Ultrabook Hybrid" . TechCrunch. October 9, 2012.Archived from the original on December 22, 2017. RetrievedJuly 15, 2016 .^ Jackson, Jerry (October 9, 2012)."Lenovo Launches IdeaPad Yoga 11, Yoga 13" .Notebookreview.com .Archived from the original on October 18, 2012. RetrievedJuly 15, 2016 . ^ Hacking a Tesla Model S: What we found and what we learned Archived December 20, 2017, at theWayback Machine by Kevin Mahaffey on August 7, 2015^ "Nexus 7 tablet hands-on" . Engadget. June 27, 2012.Archived from the original on June 29, 2012. RetrievedJune 27, 2012 .^ "Toshiba Excite 10 Benchmark Test" . YouTube. May 29, 2012.Archived from the original on July 27, 2013. RetrievedNovember 25, 2012 .^ "Blu Products: Quattro45" . April 20, 2013. Archived fromthe original on April 20, 2013.^ "Tegra 4 Processors" . NVIDIA.Archived from the original on January 27, 2013. RetrievedJuly 15, 2016 .^ Parrish, Kevin (November 12, 2013)."Results: GPU Benchmarks – EVGA Tegra Note 7 Review: Nvidia's Tegra 4 For $200" .Tomshardware.com . RetrievedJuly 15, 2016 . ^a b "NVIDIA Tegra Multi-processor Architecture" (PDF) .Archived (PDF) from the original on March 20, 2013. RetrievedJuly 10, 2013 .^ Larabel, Michael (December 20, 2012)."NVIDIA Publishes Their Next-Gen Tegra 4 Code" . phoronix.com.Archived from the original on May 14, 2013. RetrievedAugust 2, 2013 . ^a b c d Walrath, Josh (February 26, 2013)."NVIDIA Details Tegra 4 and Tegra 4i Graphics" .PC Perspective .Archived from the original on December 23, 2014. RetrievedSeptember 2, 2013 . ^a b Angelini, Chris (February 24, 2013)."Nvidia's Tegra 4 GPU: Doubling Down On Efficiency" .Tom's Hardware . RetrievedSeptember 2, 2013 . ^ "Tegra 4 Processors" . NVIDIA.Archived from the original on January 27, 2013. RetrievedJuly 10, 2013 .^a b "NVIDIA Tegra 4 Architecture Deep Dive, Plus Tegra 4i, Icera i500 & Phoenix Hands On" . AnandTech.Archived from the original on February 27, 2013. RetrievedJuly 10, 2013 .^ "Tegra 4 Shipment Date: Still Q2 2013" . AnandTech.Archived from the original on February 17, 2013. RetrievedJuly 10, 2013 .^ "HP Slate 7 Extreme 4400CA Tablet Product Specifications" . .hp.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "HP Slate7 Beats Special Edition 4501 Tablet Product Specifications" . .hp.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "HP Slate 8 Pro 7600us Tablet Product Specifications" . hp.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "HP SlateBook x2 Overview – Android Tablet Notebook | HP Official Site" . .hp.com.Archived from the original on July 12, 2013. RetrievedJuly 10, 2013 .^ "HP SlateBook 14-p010nr Product Specifications" . hp.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "HP Slate 21-s100 All-in-One Desktop PC – Product Specifications" . hp.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "Cintiq Companion Hybrid – Wacom" . August 23, 2013. Archived fromthe original on August 23, 2013.^ "用户太多，系统繁忙" .Shop.coolpad.cn .Archived from the original on December 31, 2013. RetrievedJuly 15, 2016 .^ Shapiro, Danny."Audi Offers Taste of Tegra-Powered Future at Geneva Motor Show | NVIDIA Blog" .Blogs.nvidia.com .Archived from the original on April 2, 2015. RetrievedJuly 10, 2016 . ^ "Le Pan – TC1020" . Lepantab.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "[Test] Matrimax iPlay" . Open-consoles-news.com.Archived from the original on September 23, 2016. RetrievedSeptember 22, 2016 .^ "Kobo Arc 10 HD Specs" . C-Net.Archived from the original on March 15, 2018. RetrievedJuly 8, 2017 .^ Cunningham, Andrew (February 19, 2013)."Project Grey becomes Tegra 4i, Nvidia's latest play for smartphones" . Ars Technica.Archived from the original on December 2, 2017. RetrievedJuly 10, 2013 . ^ "Wiko Mobile – HIGHWAY 4G" . September 17, 2014. Archived fromthe original on September 17, 2014.^ "Explay 4Game | Четырехъядерный смартфон на базе Tegra 4i | NVIDIA" .Blogs.nvidia.com .Archived from the original on December 5, 2014. RetrievedJuly 10, 2016 .^ Han, Mike (February 24, 2014)."NVIDIA LTE Modem Makes Landfall in Europe, with Launch of Wiko Tegra 4i LTE Smartphone | The Official NVIDIA Blog" .Blogs.nvidia.com .Archived from the original on February 28, 2014. RetrievedJuly 10, 2016 . ^ "Wiko WAX" . DeviceSpecifications.Archived from the original on May 21, 2014. RetrievedMay 21, 2014 .^ "QMobile Noir LT-250" . DeviceSpecifications.Archived from the original on February 10, 2015. RetrievedFebruary 10, 2014 .^ Park, Will (May 15, 2014)."NVIDIA's Tegra K1 Powers Xiaomi's First Tablet | The Official NVIDIA Blog" .Blogs.nvidia.com .Archived from the original on July 12, 2014. RetrievedJuly 15, 2016 . ^ "NVIDIA Shield Tablet K1 gets Vulkan support with Android 6.0.1 update" .Archived from the original on May 9, 2016. RetrievedMay 3, 2016 .^a b Kelion, Leo (January 6, 2014)."CES 2014: Nvidia Tegra K1 offers leap in graphics power" . BBC.Archived from the original on January 11, 2014. RetrievedJanuary 11, 2014 . ^a b "Vulkan API" (PDF) .Archived (PDF) from the original on December 22, 2015. RetrievedDecember 11, 2015 .^ Larabel, Michael (April 29, 2014)."NVIDIA's Tegra TK1 Jetson Board Is Now Shipping" .Phoronix .Archived from the original on April 25, 2016. RetrievedSeptember 14, 2016 . ^ Anthony, Sebastian (January 6, 2014)."Tegra K1 64-bit Denver core analysis: Are Nvidia's x86 efforts hidden within?" . ExtremeTech.Archived from the original on January 7, 2014. RetrievedJanuary 7, 2014 . ^ NVIDIA CEO confirms Tegra roadmap, building all now: Kal-El, Wayne, Logan, Stark Archived March 16, 2017, at theWayback Machine , October 21, 2011:Finally, he confirmed that the inner workings we've heard about in Project Denver will first be present in the Tegra line with the introduction of Stark(...) ^ "Tegra K1 Next-Gen Mobile Processor | NVIDIA Tegra" . NVIDIA.Archived from the original on January 9, 2014. RetrievedJuly 15, 2016 .^ Klug, Brian;Shimpi, Anand Lal (January 6, 2014)."NVIDIA Tegra K1 Preview & Architecture Analysis" .AnandTech Archived from the original on April 19, 2014. RetrievedMay 2, 2014 . ^ Stam, Nick."Mile High Milestone: Tegra K1 "Denver"? Will Be First 64-bit ARM Processor for Android | The Official NVIDIA Blog" .Blogs.nvidia.com .Archived from the original on August 12, 2014. RetrievedJuly 15, 2016 . ^ Ho, Joshua (5 January 2015)."NVIDIA Tegra X1 Preview & Architecture Analysis" .Anandtech .Archived from the original on December 4, 2018. RetrievedDecember 3, 2018 . {{cite web }}: CS1 maint: numeric names: authors list (link )^ "Jetson TK1 development board" . Archived fromthe original on September 5, 2015. RetrievedMay 1, 2014 .^ "SHIELD Tablet, The Ultimate Tablet For Gamers" . GeForce. July 22, 2014.Archived from the original on July 25, 2014. RetrievedJuly 15, 2016 .^ "Tegra K1 Lands in Acer's Newest Chromebook" . Anandtech. August 11, 2014.Archived from the original on July 20, 2018. RetrievedAugust 11, 2014 .^ "HP Chromebook 14 G3 – Specifications" . HP. August 30, 2018.Archived from the original on August 30, 2018. RetrievedAugust 30, 2018 .^ "Xiaomi MiPad 7.9" . Techindeep. RetrievedMay 18, 2018 .^ "Google" .Archived from the original on March 16, 2014. RetrievedJuly 15, 2016 .^ Rothman, Chelsea."Fuze Tomahawk F1: The Chinese Android XStation 4" .Comics Gaming Magazine .Archived from the original on June 10, 2016. RetrievedJune 1, 2016 . ^ "NVIDIA Tegra K1 System/Computer on Module – Apalis TK1 SOM" .Toradex.com .Archived from the original on March 4, 2016. RetrievedJuly 15, 2016 .^ "JXD S192 "retro" gaming tablet is powered by Nvidia's Tegra K1 chipset" .GSMArena.com .Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 .^ "Nexus 9" .Archived from the original on October 21, 2014. RetrievedJuly 15, 2016 .^ "Google Nexus 9 Specs and Reviews | HTC United States" .Htc.com . Archived fromthe original on November 2, 2014. RetrievedJuly 15, 2016 .^ Exclusive: The Tesla AutoPilot – An In-Depth Look At The Technology Behind the Engineering Marvel Archived March 16, 2018, at theWayback Machine by Usman Pirzada on Dec 3, 2015^ "Tegra X1 Super Chip | NVIDIA Tegra" . NVIDIA.Archived from the original on January 5, 2015. RetrievedJuly 10, 2016 .^ "NVIDIA Tegra X1 Preview & Architecture Analysis" .Anandtech.com .Archived from the original on January 5, 2015. RetrievedJuly 10, 2016 .^ Tegra_X1_TRM_DP07225001_v1.0.pdf ^ "Tegra X1 advertised as four core to developers" . NVIDIA. December 19, 2015.Archived from the original on October 25, 2019. RetrievedApril 4, 2017 .^ "Tegra X1's A53 cores are disabled on the Pixel C" . Anandtech.Archived from the original on April 4, 2017. RetrievedApril 4, 2017 .^ Bittner, Otto; Krachenfels, Thilo; Galauner, Andreas; Seifert, Jean-Pierre (August 16, 2021). "The Forgotten Threat of Voltage Glitching: A Case Study on Nvidia Tegra X2 SoCs".2021 Workshop on Fault Detection and Tolerance in Cryptography (FDTC) . pp. 86– 97.arXiv :2108.06131v2 doi :10.1109/FDTC53659.2021.00021 .ISBN 978-1-6654-3673-1 S2CID 237048483 . ^ "NVIDIA Shield Android TV 2019 review" .Guru3D.com .Archived from the original on October 31, 2020. RetrievedMarch 25, 2020 .^a b Crider, Michael (January 5, 2015)."NVIDIA Announces The New Tegra X1 Mobile Chipset With 256-Core Maxwell GPU" .Androidpolice.com .Archived from the original on January 5, 2015. RetrievedJuly 10, 2016 . ^ "NVIDIA Jetson TX1 Supercomputer-on-Module Drives Next Wave of Autonomous Machines | Parallel Forall" .Devblogs.nvidia.com . November 11, 2015.Archived from the original on May 3, 2016. RetrievedJuly 15, 2016 .^ "Slide set from Jetson Nano webinar" (PDF) .Archived (PDF) from the original on May 3, 2019. RetrievedMay 3, 2019 .^ [1] Tegra T210 dfll table ^a b "Tegra X1 (SoC) Technical Reference Manual" .developer.nvidia.com (v1.2p ed.). RetrievedFebruary 20, 2018 .(registration required ) ^ Tegra T210b01 dfll table ^ Strings found in libnvrm_gpu.so and in glxinfo when driver is loaded in linux ^ Leadbetter, Richard (June 27, 2019)."Switch's next Tegra X1 looks set to deliver more performance and longer battery life" .Eurogamer .Archived from the original on July 25, 2019. RetrievedJuly 19, 2019 . ^ "3.3 Hardware Specifications" .dystify.com . Archived fromthe original on February 13, 2017. RetrievedFebruary 27, 2017 .^ "Embedded Systems Development Solutions from NVIDIA Jetson" . NVIDIA. March 18, 2015.Archived from the original on June 25, 2016. RetrievedJuly 10, 2016 .^ "DATA SHEET - NVIDIA Jetson TX2 System-on-Module.pdf" (PDF) .^ NVIDIA Jetson TX2 Delivers Twice the Intelligence to the Edge Archived February 27, 2018, at theWayback Machine by Dustin Franklin on March 7, 2017 at Nvidia Developer Blogs^ https://developer.nvidia.com/embedded/dlc/jetson-tx2-module-data-sheet (registration required ) ^ "NVIDIA Discloses Next-Generation Tegra SoC; Parker Inbound?" .Anandtech.com . January 5, 2016.Archived from the original on June 29, 2016. RetrievedJuly 10, 2016 .^ Ho, Joshua."Hot Chips 2016: NVIDIA Discloses Tegra Parker Details" .www.anandtech.com .Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 . ^ Ho, Joshua (August 25, 2016)."Hot Chips 2016: NVIDIA Discloses Tegra Parker Details" . Anandtech.Archived from the original on December 16, 2017. RetrievedAugust 25, 2016 . ^ "NVIDIA Jetson TX2: High Performance AI at the Edge" .NVIDIA .Archived from the original on April 7, 2019. RetrievedApril 9, 2019 .^a b "NVIDIA Bringing up Open-Source Volta GPU Support for Their Xavier SoC" .^a b NVIDIA Announces Jetson TX2: Parker Comes To NVIDIA's Embedded System Kit Archived January 8, 2018, at theWayback Machine , March 7, 2017^ NVIDIA Rolls Out Tegra X2 GPU Support In Nouveau Archived August 9, 2017, at theWayback Machine by Michael Larabel at phoronix.com on March 29, 2017^ "NVIDIA Jetson TX2 GPU Specs | TechPowerUp GPU Database" . Techpowerup.com. August 22, 2022. RetrievedAugust 22, 2022 .^ Shapiro, Danny (January 4, 2017)."ZF Launches ProAI, DRIVE PX 2 Self-Driving System for Cars, Trucks, Factories – NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on December 14, 2017. RetrievedDecember 13, 2017 . ^ NVIDIA Powers Mercedes-Benz MBUX, Its Next-Gen AI Cockpit Archived March 16, 2018, at theWayback Machine by Danny Shapiro on January 9, 2018 via Nvidia company blogs^ Look inside Tesla's onboard Nvidia supercomputer for self-driving Archived March 28, 2018, at theWayback Machine by Fred Lambert on May 22, 2017^ Tesla Working With AMD on Self-Driving Car Processor Archived March 15, 2018, at theWayback Machine by Joel Hruska on September 21, 2017^ "Magic Leap One will ship this summer with Nvidia Tegra X2 processor" .VentureBeat . July 11, 2018.Archived from the original on July 12, 2018. RetrievedJuly 11, 2018 .^ Magic Leap One teardown Archived August 24, 2018, at theWayback Machine at ifixit.com^ Skydio's second-gen drone, a $1,000 self-flying action cam, sells out for 2019 Archived April 12, 2020, at theWayback Machine by Stephen Shankland on October 2, 2019^ Franklin, Dustin (December 12, 2018)."NVIDIA Jetson AGX Xavier Delivers 32 TeraOps for New Era of AI in Robotics" .devblogs.nvidia.com .Archived from the original on March 30, 2019. RetrievedMarch 30, 2019 . ^ Smith, Ryan."The NVIDIA GPU Tech Conference 2017 Keynote Live Blog" .www.anandtech.com .Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 . ^ Huang, Jensen (May 24, 2017)."The AI Revolution Is Eating Software: NVIDIA Is Powering It | NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on August 22, 2017. RetrievedAugust 22, 2017 . ^a b Smith, Ryan."NVIDIA Teases Xavier, a High-Performance ARM SoC for Drive PX & AI" .Archived from the original on September 29, 2016. RetrievedSeptember 28, 2016 . ^a b Shapiro, Danny (September 28, 2016)."Introducing NVIDIA Xavier – NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on October 2, 2016. RetrievedSeptember 28, 2016 . ^a b Cutress, Ian; Tallis, Billy (January 4, 2016)."CES 2017: Nvidia Keynote Liveblog" . Anandtech.com.Archived from the original on January 10, 2017. RetrievedJanuary 9, 2017 . ^a b Baldwin, Roberto (January 8, 2018)."NVIDIA unveils its powerful Xavier SOC for self-driving cars" . Engadget.Archived from the original on January 8, 2018. RetrievedJanuary 8, 2018 . ^ NVIDIA Drive Xavier SOC Detailed Archived February 24, 2018, at theWayback Machine by Hassan Mujtaba on Jan 8, 2018 via WccfTech^a b c Abazovic, Fuad."Nvidia Xavier sampling in Q1 18" .www.fudzilla.com .Archived from the original on February 7, 2018. RetrievedFebruary 6, 2018 . ^ "Welcome — Jetson LinuxDeveloper Guide 34.1 documentation" .^ "Programmable Vision Accelerator" .Archived from the original on February 27, 2021. RetrievedMarch 3, 2021 .^ "Understanding MIPI Alliance Interface Specifications" .Electronic Design . April 1, 2014.Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 .^ Mujtaba, Hassan (January 8, 2018)."NVIDIA Xavier SOC Is The Most Biggest and Complex SOC To Date" .Archived from the original on February 24, 2018. RetrievedFebruary 7, 2018 . ^a b Schilling, Andreas (March 27, 2018)."Auf Pegasus folgt Orin: Drive-PX-Plattform mit Turing- oder Ampere-Architektur" .Hardwareluxx .Archived from the original on May 27, 2018. RetrievedMay 26, 2018 . ^ Sundaram, Shri (September 12, 2018)."Introducing NVIDIA DRIVE AGX Xavier Developer Kit – NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on December 24, 2018. RetrievedDecember 11, 2018 . ^a b "Jetson AGX Xavier Developer Kit" .NVIDIA Developer . July 9, 2018.Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 .^ "Jetson Xavier NX Developer Kit" .NVIDIA Developer . November 6, 2019.Archived from the original on November 6, 2019. RetrievedNovember 6, 2019 .^ Powell, Kimberly (September 12, 2018)."NVIDIA Clara Platform to Usher in Next Generation of Medical Instruments – NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on December 15, 2018. RetrievedDecember 11, 2018 . ^ "NVIDIA Rolls Out Tesla T4 GPUs, DRIVE AGX Xavier & Clara Platform – Phoronix" .www.phoronix.com .Archived from the original on December 15, 2018. RetrievedDecember 11, 2018 .^ Shilov, Anton (March 18, 2017)."Bosch and Nvidia Team Up for Xavier based Self-Driving Systems for Mass Market Cars" . Anandtech.com.Archived from the original on June 5, 2017. RetrievedJune 22, 2017 . ^ "Dream safety: 'Dream Car' learns to drive autonomously" .vision.zf.com .^ "Baidu, NVIDIA and ZF team to drive autonomous vehicles in China" .Tech Wire Asia . January 8, 2018.Archived from the original on March 25, 2019. RetrievedMarch 25, 2019 .^ Linux Kernel Mailing List: (PATCH v3 7/7) arm64: tegra: Add device tree for the Tegra194 P2972-0000 board Archived March 15, 2018, at theWayback Machine by Mikko Perttunen on Feb 15 2018^ Smith, Ryan."NVIDIA ARM SoC Roadmap Updated: After Xavier Comes Orin" .www.anandtech.com .Archived from the original on April 19, 2018. RetrievedApril 18, 2018 . ^ Smith, Ryan."NVIDIA Details DRIVE AGX Orin: A Herculean Arm Automotive SoC For 2022" .www.anandtech.com .Archived from the original on December 19, 2019. RetrievedDecember 21, 2019 . ^ online, heise (December 18, 2019)."Nvidia Orin: Next-Gen-Prozessor für autonome Fahrzeuge mit hoher Rechenleistung" .heise online .Archived from the original on January 31, 2021. RetrievedJanuary 26, 2021 . ^ Shapiro, Danny (January 9, 2021)."Chinese Automaker NIO Selects NVIDIA for Electric Vehicles | NVIDIA Blog" .The Official NVIDIA Blog .Archived from the original on January 26, 2021. RetrievedJanuary 26, 2021 . ^ Williams, Chris."Arm hasn't given up on self-driving car brains – its new Cortex-A78AE is going into Nvidia's Orin chip, for a start" .www.theregister.com .Archived from the original on October 1, 2020. RetrievedSeptember 29, 2020 . ^ Ltd, Arm."Cortex-A78AE – Arm" .Arm | The Architecture for the Digital World .Archived from the original on October 5, 2020. RetrievedOctober 3, 2020 . ^ https://blogs.nvidia.com/blog/2021/01/09/nio-selects-nvidia-intelligent-electric-vehicles/ Archived January 26, 2021, at theWayback Machine 8192 cores / 4 SoCs = 2048 cores / SoC^a b c d "NVIDIA Jetson AGX Orin Technical Brief.pdf" (PDF) .^a b c d e "NVIDIA Orin Brings Arm and Ampere to the Edge at Hot Chips 34" . August 23, 2022.^ Nvidia."NVIDIA Jetson Orin Nano Sets New Standard for Entry-Level Edge AI and Robotics With 80x Performance Leap" .nvidianews.nvidia.com .Archived from the original on September 23, 2022. RetrievedSeptember 23, 2022 . ^ "kernel/git/next/linux-next.git - The linux-next integration testing tree" .git.kernel.org . RetrievedSeptember 22, 2020 .^ "Linux 5.10 Has Initial Support For NVIDIA Orin, DeviceTree For Purism's Librem 5 - Phoronix" .www.phoronix.com .Archived from the original on January 31, 2021. RetrievedJanuary 26, 2021 .^a b c d Nvidia."Jetson Orin for Next-Gen Robotics NVIDIA" .nvidia .Archived from the original on September 23, 2022. RetrievedSeptember 23, 2022 . ^a b "Embedded Robotics Modules - Jetson Orin NX" .nvidia .Archived from the original on March 8, 2022. RetrievedMarch 8, 2022 .^a b "Jetson Orin NX Series - Thermal Design Guide" (PDF) . September 28, 2022. RetrievedSeptember 29, 2022 .[dead link ] ^ "Linux 5.18 Adding Audio Support for NVIDIA's Orin SoC" .^ "NVIDIA Jetson AGX Orin" .^ "Jetson Orin for Next-Gen Robotics" .nvidia.com . NVIDIA Corporation. RetrievedMay 8, 2023 .^ "NIO ET5 Designed for Autonomous Era with DRIVE Orin" . December 20, 2021.^ "Chinese Automaker NIO Selects NVIDIA for Electric Vehicles" . January 9, 2021.^ "Introducing Grace" .NVIDIA . RetrievedMay 8, 2023 .^ "NVIDIA Introduces Grace CPU Superchip" .NVIDIA Newsroom . RetrievedMay 8, 2023 .^ "LKML: Marc Zyngier: Re: [PATCH] irqchip/gicv3: Workaround for NVIDIA erratum T241-FABRIC-4" .lkml.org . RetrievedMay 8, 2023 .^ "[PATCH 0/2] gpio: Tegra186: Add support for Tegra241 - Thierry Reding" .^a b c d e f "NVIDIA Grace CPU Superchip Architecture In Depth" .NVIDIA Technical Blog . January 20, 2023. RetrievedMay 8, 2023 .^ Paul Alcorn (March 22, 2023)."Nvidia CEO Comments on Grace CPU Delay, Teases Sampling Silicon" .Tom's Hardware . RetrievedMay 8, 2023 . ^ "NVIDIA Unveils NVIDIA DRIVE Atlan, an AI Data Center on Wheels for Next-Gen Autonomous Vehicles" .^ "NVIDIA Unveils DRIVE Atlan Autonomous Vehicle Platform" . April 12, 2021.^a b c d e "NVIDIA Unveils DRIVE Thor — Centralized Car Computer Unifying Cluster, Infotainment, Automated Driving, and Parking in a Single, Cost-Saving System" .^a b Labrie, Marie."NVIDIA Unveils NVIDIA DRIVE Atlan, an AI Data Center on Wheels for Next-Gen Autonomous Vehicles" .nvidianews.nvidia.com . NVIDIA. RetrievedJanuary 6, 2023 . ^ Smith, Ryan."NVIDIA Drops DRIVE Atlan SoC, Introduces 2 PFLOPS DRIVE Thor for 2025 Autos" .Anandtech . RetrievedJanuary 6, 2023 . ^ Smith, Ryan."NVIDIA Drops DRIVE Atlan SoC, Introduces 2 PFLOPS DRIVE Thor for 2025 Autos" .Anandtech . RetrievedJanuary 6, 2023 . ^ Smith, Ryan."NVIDIA Drops DRIVE Atlan SoC, Introduces 2 PFLOPS DRIVE Thor for 2025 Autos" .Anandtech . RetrievedJanuary 6, 2023 . ^ Smith, Ryan."NVIDIA Drops DRIVE Atlan SoC, Introduces 2 PFLOPS DRIVE Thor for 2025 Autos" .Anandtech . RetrievedJanuary 6, 2023 . ^ " .marc.info . RetrievedMay 8, 2023 .^ "NVIDIA DRIVE Powers Next Generation of Transportation — from Cars and Trucks to Robotaxis and Autonomous Delivery Vehicles" .^ "NVIDIA Announces Project GR00T Foundation Model for Humanoid Robots and Major Isaac Robotics Platform Update" .^ "NVIDIA DRIVE Thor Strikes AI Performance Balance, Uniting AV and Cockpit on a Single Computer" . September 20, 2022.^ "FreeBSD on Jetson TK1 | FreeBSD developer's notebook" .kernelnomicon.org .Archived from the original on September 28, 2020. RetrievedDecember 26, 2020 .^ "src - FreeBSD source tree" .cgit.freebsd.org .^ Mayo, Jon (April 20, 2012)."[RFC 0/4] Add NVIDIA Tegra DRM support" .dri-devel (Mailing list).Archived from the original on December 25, 2014. RetrievedAugust 21, 2012 . ^ Larabel, Michael (April 11, 2012)."A NVIDIA Tegra 2 DRM/KMS Driver Tips Up" . Phoronix Media.Archived from the original on October 7, 2016. RetrievedAugust 21, 2012 . ^ "GTC 2013: NVIDIA's Tegra Roadmap (6 of 11)" . YouTube. March 19, 2013.Archived from the original on December 24, 2018. RetrievedJuly 10, 2013 .^ "NVIDIA Tegra X2 & Xavier Get HDMI Audio With Linux 4.21 – Phoronix" .www.phoronix.com .Archived from the original on December 23, 2018. RetrievedDecember 11, 2018 .^ "NVIDIA Releases Open-Source GPU Kernel Modules" .NVIDIA Technical Blog . May 19, 2022. RetrievedMay 8, 2023 .^ "DRIVE PX 2 Shows Next-Gen Nvidia Tegra, Pascal Processors" . April 5, 2016.Archived from the original on March 8, 2017. RetrievedMarch 8, 2017 .
Software and technologies
Multimedia acceleration Software Technologies GPU microarchitectures
Application ARM-based chips
Application
ARMv7-A
Cortex-A5 Cortex-A7 AllwinnerA2x, A3x, A83T, H3, H8 NXPi.MX7 ,QorIQ LS10xx , NXPi.MX6UL BroadcomVideoCore BCM2836, BCM23550 LeadcoreLC1813, LC1860/C, LC1913, LC1960 Marvell Armada PXA1920, 1500 mini plusMediaTek MT65xx QualcommSnapdragon 200, 205, 208, 210, 212 ,400 Cortex-A8 Cortex-A9 ActionsATM702x , ATM703x Altera Cyclone V, Arria V/10 AmlogicAML8726, MX, M6x, M801, M802/S802, S812, T86x Apple A5 ,A5X BroadcomVideoCore BCM21xxx, BCM28xxx Freescalei.MX6 HiSiliconK3V2 ,910's InfoTMiMAPx912 LeadcoreLC1810, LC1811 Marvell Armada 1500 miniMediaTek MT65xx NvidiaTegra ,2 ,3 ,4i NufrontNuSmart 2816M, NS115, NS115M Renesas EMMA EV2, R-Car H1, RZ/ARockchipRK292x , RK30xx , RK31xx SamsungExynos 4 421x , 441x ST-EricssonNovaThor TelechipsTCC8803 Texas InstrumentsOMAP 4 Texas InstrumentsSitara AM4xxx VIA WonderMediaWM88x0, 89x0 XilinxZynq-7000 ZiiLABSZMS-20, ZMS-40 Cortex-A15 Cortex-A17 Others ARMv7-A Apple A6 ,A6X ,S1 ,S1P ,S2 ,S3 Broadcom Brahma-B15 Marvell P4JQualcommSnapdragon S1, S2, S3, S4 Plus, S4 Pro, 600, 800 (Scorpion ,Krait )
ARMv8-A
Application
ARMv8-A
Cortex-A35 Cortex-A53 ActionsGT7, S900, V700 AllwinnerA64, H5, H64, R18 Altera Stratix 10 AmlogicS9 Family, T96x BroadcomBCM2837 EZchip TILE-Mx100HiSiliconKirin 620 ,650, 655, 658, 659 ,930, 935 Marvell Armada PXA1928, Mobile PXA1908/PXA1936MediaTekMT673x ,MT675x ,MT6761V ,MT6762 /V ,MT6763T ,MT6765 /G/H ,MT6795 ,MT8161, MT8163, MT8165, MT8732, MT8735, MT8752 NXP ARMS32 ,QorIQ LS1088, LS1043 ,i.MX8M QualcommSnapdragon 215 ,410, 412, 415, 425, 427, 429, 430, 435, 439, 450 ,610, 615, 616, 617, 625, 626, 630 Renesas RZ/V2M RockchipRK3328, RK3368 SamsungExynos 7570, 7578, 7580, 7870, 7880 Texas InstrumentsSitara AM6xxx UNISOC SC9820E ,SC9832E, SC9860/GV XilinxZynqMP Cortex-A57 Cortex-A72 AWS Graviton BroadcomBCM2711 HiSiliconKirin 950, 955 ,Kunpeng 916 MediaTekMT6797/D/T/X ,MT8173, MT8176, MT8693 MStar6A938 QualcommSnapdragon 650, 652, 653 RockchipRK3399 NXPQorIQ LS2088 ,QorIQ LS1046A ,QorIQ LX2160A ,QorIQ LS1028A ,i.MX8 Cortex-A73 QualcommSnapdragon 460 ,632, 636, 660, 662, 665, 680, 685 ,6s 4G Gen 1 ,835 SamsungExynos 7872, 7884, 7885, 7904, 9609, 9610, 9611 HiSiliconKirin 710 ,960 ,970 MediaTekMT6771/V ,MT6799 ,MT8183, MT8788 AmlogicS922X Others ARMv8-A
ARMv8.1-A
ARMv8.2-A
Cortex-A55 Cortex-A75 QualcommSnapdragon 670 ,710, 712 ,845 ,850 SamsungExynos 9820, 9825 MediaTekMT6769H/T/V/Z ,MT6768, MT6779V UNISOCT310, T606, T610, T615, T616, T618, T619, T620, T700, T710, T7200, T7225, T7250, T7255, T7280 ,T740 Cortex-A76 AllwinnerA733 Google Tensor HiSiliconKirin 810, 820 ,980, 985 ,990 QualcommSnapdragon 480(+) ,675, 678 ,720G, 730(G), 732G, 765(G), 768G ,855(+), 860 ,7c (Gen 2), 8c, 8cx (Gen 2) MicrosoftSQ1 and SQ2 MediaTekMT6781, MT6785V, MT6789 ,MT6833V/P, MT6853V/T ,MT6873, MT6875 ,Dimensity 6020, 6080, 6100+, 6300(+), 6400 ,MT8192 SamsungExynos 990 UNISOCT750, T760, T765, T770, T820, T8100, T8200, T8300, T9100 Cortex-A77 Cortex-A78 Google Tensor G2 MediaTekMT6877, MT6878 ,MT6879, MT6891, MT6893 ,Dimensity 7020, 7025 (Ultra), 7030, 7050, 7300 (Energy/Ultra/X) ,8000, 8020, 8050, 8100, 8200 ,Kompanio 900T, 1200, 1380, 1300T QualcommSnapdragon 4 Gen 1, 4(s) Gen 2 ,695 ,6 Gen 1, 6(s) Gen 3 ,778G(+), 780G, 782G ,888(+) SamsungExynos 1080, 1280, 1330, 1380, 1480 ,2100 Cortex-X1 Neoverse N1 Others Cortex-A65, Cortex-A65AE, Cortex-A76AE, Cortex-A78C, Cortex-X1C,Neoverse E1 ARMv8.2-A
ARMv8.3-A
ARMv8.4-A
ARMv8.5-A
ARMv8.6-A
ARMv8.7-A
ARMv9.0-A
ARMv9.2-A
Embeddedmicrocontrollers
Cortex-M0 CypressPSoC 4000, 4100, 4100M, 4200, 4200DS, 4200L, 4200M InfineonXMC1000 Nordic nRF51 NXPLPC1100, LPC1200 nuvoTon NuMicro Sonix SN32F700 STMicroelectronicsSTM32 F0 Toshiba TX00 Vorago VA108x0 Cortex-M0+ Cypress PSoC 4000S, 4100S, 4100S+, 4100PS, 4700S, FM0+ Holtek HT32F52000 Microchip (Atmel)SAM C2, D0, D1, D2, DA, L2, R2, R3 NXPLPC800, LPC11E60, LPC11U60 NXP (Freescale) Kinetis E, EA, L, M, V1, W0 Raspberry PiRP2040 Renesas Synergy S1 Silicon Labs (Energy Micro)EFM32 Zero, Happy STMicroelectronicsSTM32 L0 Cortex-M1 Altera FPGAs Cyclone-II, Cyclone-III, Stratix-II, Stratix-III Microsemi (Actel ) FPGAs Fusion, IGLOO/e, ProASIC3L, ProASIC3/EXilinx FPGAs Spartan-3, Virtex-2-3-4 Cortex-M3 ActelSmartFusion, SmartFusion 2 Analog Devices ADuCM300 CypressPSoC 5000, 5000LP, FM3 Fujitsu FM3 Holtek HT32F Microchip (Atmel)SAM 3A, 3N, 3S, 3U, 3X NXPLPC1300, LPC1700, LPC1800 ON Semiconductor Q32M210 Silicon Labs Precision32 Silicon Labs (Energy Micro)EFM32 Tiny, Gecko, Leopard, Giant STMicroelectronicsSTM32 F1, F2, L1 Texas Instruments F28, LM3, TMS470,OMAP 4 Toshiba TX03 Cortex-M4 Microchip (Atmel)SAM 4L, 4N, 4S NXP (Freescale) Kinetis K, W2 Renesas RA4W1, RA6M1, RA6M2, RA6M3, RA6T1 Cortex-M4F Cypress 6200, FM4 InfineonXMC4000 Microchip (Atmel)SAM 4C, 4E, D5, E5, G5 Microchip CEC1302 Nordic nRF52 NXPLPC4000, LPC4300 NXP (Freescale) Kinetis K, V3, V4 Renesas Synergy S3, S5, S7 Silicon Labs (Energy Micro)EFM32 Wonder STMicroelectronicsSTM32 F3, F4, L4, L4+, WB Texas Instruments LM4F/TM4C,MSP432 Toshiba TX04 Cortex-M7F Microchip (Atmel)SAM E7, S7, V7 NXP (Freescale) Kinetis KV5x, i.MX RT 10xx, i.MX RT 11xx, S32K3xx STMicroelectronicsSTM32 F7, H7 Cortex-M23 GigaDevice CD32E2xx Microchip (Atmel)SAM L10, L11, and PIC 32CM-LE 32CM-LS Nuvoton M23xx family, M2xx family, NUC1262, M2L31 Renesas S1JA, RA2A1, RA2L1, RA2E1, RA2E2 Cortex-M33F Analog Devices ADUCM4 Dialog DA1469x GigaDevice GD32E5, GD32W5 Nordic nRF91, nRF5340, nRF54 NXPLPC5500 , i.MX RT600 ON RSL15 Renesas RA4, RA6 STSTM32 H5, L5, U5, WBA Silicon Labs Wireless Gecko Series 2 Cortex-M35P Cortex-M55F Cortex-M85F
Real-time
Classic ARM-based chips
Classic
ARM7 AtmelSAM7L, SAM7S, SAM7SE, SAM7X, SAM7XC ,AT91CAP7 , AT91M, AT91R Cirrus Logic PS7xxx, EP7xxx Mediatek MT62xx NXPLPC2100, LPC2200, LPC2300, LPC2400 , LH7 STMicroelectronics STR7 ARM9 Aspeed AST2400 AtmelSAM9G, SAM9M, SAM9N, SAM9R, SAM9X, SAM9XE, SAM926x ,AT91CAP9 Cirrus Logic EP9xxx Freescalei.MX1x, i.MX2x Nuvoton NUC900 NXPLPC2900 ,LPC3000 , LH7A PhilipsNexperia PNX4008 RockchipRK27xx, RK28xx SamsungS3C24xx STMicroelectronicsNomadik STn881x STMicroelectronics STR9 Texas InstrumentsOMAP 1 ,AM1x ,DaVinci VIA WonderMediaWM8505/8650 ZiiLABSZMS-05 ARM11 ARMv2a ARMv4 ARMv5TE Intel/MarvellXScale Marvell Sheeva, Feroceon, Jolteon, MohawkFaraday FA606TE, FA616TE, FA626TE, FA726TE
.jpg)
_-_board_-_Nvidia_T30L-P-A3-4854.jpg)
_(cropped).jpg)
.jpg)
