Nvidia Drive

Nvidia Drive is a computer platform by Nvidia, aimed at providing autonomous car and driver assistance functionality powered by deep learning.^[1][2] The platform was introduced at the Consumer Electronics Show (CES) in Las Vegas in January 2015.^[3] An enhanced version, the Drive PX 2 was introduced at CES a year later, in January 2016.^[4]

The closely platform related software release program at some point in time was branded NVIDIA DRIVE Hyperion along with a revision number helping to match with the generation of hardware it is created for - and also creating ready to order bundles under those term. In former times there were only the terms Nvidia Drive SDK for the developer package and sub-included Nvidia Drive OS for the system software (aka OS) that came with the evaluation platforms or could be downloaded for OS switching and updating later on.

Hardware and semiconductors

Maxwell based

The first of Nvidia's autonomous chips was announced at CES 2015, based on the Maxwell GPU microarchitecture.^[5] The line-up consisted of two platforms:

Drive CX

The Drive CX was based on a single Tegra X1 SoC (System on a Chip) and was marketed as a digital cockpit computer, providing a rich dashboard, navigation and multimedia experience. Early Nvidia press releases reported that the Drive CX board will be capable of carrying either a Tegra K1 or a Tegra X1.^[6]

Drive PX

 

Drive PX

The first version of Drive PX is based on two Tegra X1 SoCs, and was an initial development platform targeted at (semi-)autonomous driving cars.

Pascal based

Drive PX platforms based on the Pascal GPU microarchitecture were first announced at CES 2016.^[7] This time only a new version of Drive PX was announced, but in multiple configurations.

Drive PX 2

The Nvidia Drive PX 2 is based on one or two Tegra X2 SoCs where each SoC contains 2 Denver cores, 4 ARM A57 cores and a GPU from the Pascal generation.^[8] There are two real world board configurations:

• for AutoCruise: 1× Tegra X2 + 1 Pascal GPU
• for AutoChauffeur: 2× Tegra X2 + 2 Pascal GPU's

There is further the proposal from Nvidia for fully autonomous driving by means of combining multiple items of the AutoChauffeur board variant and connecting these boards using e.g. UART, CAN, LIN, FlexRay, USB, 1 Gbit Ethernet or 10 Gbit Ethernet. For any derived custom PCB design the option of linking the Tegra X2 Processors via some PCIe bus bridge is further available, according to board block diagrams that can be found on the web.

All Tesla Motors vehicles manufactured from mid-October 2016 include a Drive PX 2, which will be used for neural net processing to enable Enhanced Autopilot and full self-driving functionality.^[9] Other applications are Roborace.^[10] Disassembling the Nvidia-based control unit from a recent Tesla car showed that a Tesla was using a modified single-chip Drive PX 2 AutoCruise, with a GP106 GPU added as a MXM Module. The chip markings gave strong hints for the Tegra X2 Parker as the CPU SoC.^[11][12]

Volta based

Systems based on the Volta GPU microarchitecture were first announced at CES 2017^[13]

Drive PX Xavier

The first Volta based Drive PX system was announced at CES 2017 as the Xavier AI Car Supercomputer.^[13] It was re-presented at CES 2018 as Drive PX Xavier.^[14][15] Initial reports of the Xavier SoC suggested a single chip with similar processing power to the Drive PX 2 Autochauffeur system.^[16] However, in 2017 the performance of the Xavier-based system was later revised upward, to 50% greater than Drive PX 2 Autochauffeur system.^[13] Drive PX Xavier is supposed to deliver 30 INT8 TOPS of performance while consuming only 30 watts of power.^[17] This spreads across two distinct units, the iGPU with 20 INT8 TOPS as published early and the somewhat later on announced, newly introduced DLA that provided an additional 10 INT8 TOPS.

Drive PX Pegasus

In October 2017 Nvidia and partner development companies announced the Drive PX Pegasus system, based upon two Xavier CPU/GPU devices and two post-Volta (Turing) generation GPUs. The companies stated the third generation Drive PX system would be capable of Level 5 autonomous driving, with a total of 320 INT8 TOPS of AI computational power and a 500 Watts TDP.^[18][19]

Ampere based

Drive AGX Orin

The Drive AGX Orin board family was announced on December 18, 2019, at GTC China 2019.^[20] On May 14, 2020, Nvidia announced that Orin would be utilizing the new Ampere GPU microarchitecture and would begin sampling for manufacturers in 2021 and be available for production in 2022.^[21] Follow up variants are expected to be further equipped with chip models and/or modules from the Tegra Orin SoC.

Ada Lovelace based

DRIVE Atlan (Cancelled)

Nvidia announced the SoC codenamed Atlan on April 12, 2021 at GTC 2021.^[22]

Nvidia announced the cancellation of Atlan on September 20, 2022, which was supposed to be equipped with a Grace-Next CPU, and an Ada Lovelace based GPU, and Nvidia announced that their next SoC was called Thor.^[23]

Blackwell based

DRIVE Thor

Announced on September 20, 2022,^[24] Nvidia DRIVE Thor comes equipped with an Arm Neoverse V3AE CPU,^[25] and a Blackwell based GPU, which was announced on March 18, 2024.^[26]

Software and bundling

With the label Hyperion^[27] added to their reference platform^[28] series Nvidia promotes their mass products so that others can easily test drive and then create their own automotive grade products on top. Especially the feature rich software part of the base system is meant to be a big help for these others to quickly go ahead into developing their application specific solutions. Third-party companies, such as DeepRoute.ai, have publicly indicated using these software platform as their base of choice.^[29] The whole design is concentrating on UNIX/Posix compatible or derived runtime environments (Linux,^[30] Android,^[31] QNX - aka the Drive OS variants) with special support for the semiconductors mentioned before in form of internal (CUDA, Vulkan) and external support (special interfaces and drivers for camera, lidar, CAN and many more) of the respective reference boards. For clearness Nvidia bundles the core of the developer needed software as Drive SDK that is sub-divided into DRIVE OS, DriveWorks, DRIVE AV, and DRIVE IX components.^[32]

Hyperion Version	Announced	Latest Chip Launch	Start of Road Usage	Target Use Case	Semiconductors	Reference Platforms / Developer Kits	Drive OS Version	Sensor Support
7.1^[33]		2020		Level 2+ autonomous driving	Xavier, Turing GPU	DRIVE AGX Xavier Developer Kit, DRIVE AGX Pegasus Developer Kit		vehicle external: 7x camera, 8x radar; vehicle internal: 1x camera
8^[34]^[30]		2020			Xavier, Turing GPU	DRIVE™ AGX Pegasus GV100, DRIVE™ AGX Xavier	5.0.13.2 (linux)	vehicle external: 12x camera, 9x radar, 1x lidar
8.1^[35]		2022	estimated for 2024		Orin, Xavier, Turing GPU	NVIDIA DRIVE AGX Orin™, DRIVE AGX Pegasus, DRIVE Hyperion 8.1 Developer Kits^[36]	Orin: 6.0 (latest: 6.0.4) Xavier/Pegasus:5.2.6^[32]	vehicle external: 12x camera, 9x radar, 1x lidar
9^[37]^[38]	March 2022	2024	estimated for 2026		Atlan (Cancelled)			vehicle external: 14x camera, 9x radar, 3x lidar, 20x ultrasonic; vehicle internal: 3x camera, 1x radar

Note: As of now the above table is still 'fresh' and thus might be incomplete.

Reference board comparison

Nvidia provided reference board	Drive CX	Drive PX	Drive PX 2 (AutoCruise)	Drive PX 2 (Tesla)	Drive PX 2 (AutoChauffeur)	Drive PX 2 (Tesla 2.5)	Drive PX Xavier^[15]	Drive PX Pegasus^[18]	Drive AGX Orin^[20]	Drive AGX Pegasus OA^[39]	Drive Atlan (Cancelled)	Drive Thor
GPU Microarchitecture	Maxwell (28 nm)		Pascal (16 nm)				Volta (12 nm)		Ampere (8 nm^[40])		Ada Lovelace (TSMC 4N)	Blackwell (TSMC 4NP^[41])
Announced	January 2015		September 2016^[42]	October 2016^[43]	January 2016	August 2017^[44]	January 2017	October 2017	December 2019		April 2021^[45]	September 2022^[46]
Launched	N/A		N/A	N/A	N/A	N/A	N/A	N/A	2022^[47]		Cancelled^[23]	2025^[46]
Chips	1x Tegra X1	2x Tegra X1	1x Tegra X2 (Parker) + 1x Pascal GPU		2x Tegra X2 (Parker) + 2x Pascal GPU	2x Tegra X2 (Parker) + 1x Pascal GPU^[48]	1x Tegra Xavier^[49]	2x Tegra Xavier + 2x Turing GPU	2x Tegra Orin	2x Tegra Orin + 2x Ampere GPU	?x Grace-Next CPU^[45] + ?x Ada Lovelace GPU^[23]	?x Arm Neoverse Poseidon AE CPU^[50] + ?x Blackwell GPU^[51]
CPU	4x Cortex A57 4x Cortex A53	8x Cortex A57 8x Cortex A53	2x Denver 4x Cortex A57		4x Denver 8x Cortex A57	4x Denver 8x Cortex A57	8x Carmel ARM64^[49]	16x Carmel ARM64	12x Cortex A78AE	24x Cortex A78AE	?x Grace-Next^[45]	?x Arm Neoverse Poseidon AE^[52]
GPU	2 SMM Maxwell 256 CUDA cores	4 SMM Maxwell 512 CUDA cores	1x Parker GPGPU (1x 2 SM Pascal, 256 CUDA cores)	1x Parker GPGPU (1x 2 SM Pascal, 256 CUDA cores on a MXM slot^[11])	2x Parker GPGPU (2x 2 SM Pascal, 512 CUDA cores) + 2x dedicated MXM modules^[53]	1x Parker GPGPU 1x 2 SM Pascal, 256 CUDA cores ^[44]^[48]	1x Volta iGPU (512 CUDA cores)^[49]	2x Volta iGPU (512 CUDA cores) 2x Turing dGPUs (? CUDA cores)	2x Ampere iGPU (?CUDA cores)	2x Ampere iGPU (? CUDA cores) 2x Ampere dGPU (? CUDA cores)	?x Ada Lovelace^[23]	?x Blackwell GPU^[54]
Accelerator							1x DLA 1x PVA^[49]	2x DLA 2x PVA	2x DLA 2x PVA	2x DLA 2x PVA	?	?
Memory			8GB LPDDR4^[55]		16GB LPDDR4^[55]		16GB LPDDR4^[49]		32GB LPDDR5		?	?
Storage			64GB eMMC^[55]		128GB eMMC^[55]						?	?
Performance			4 FP32 TFLOPS 10-12 DL TOPS^[56]^[57]	4 FP32 TFLOPS 10-12 DL TOPS ^[56]^[57]	16 FP16 TFLOPS 8 FP32 TFLOPS 20-24 DL TOPS ^[56]^[57]	4 FP32 TFLOPS 10-12 DL TOPS ^[56]^[57]	20 INT8 TOPS, 1.3 FP32 TFLOPS (GPU) 10 INT8 TOPS, 5 FP16 TFLOPS (DLA)^[49]	320 INT8 TOPS (total)^[58]	400 INT8 TOPS (total)	2000 INT8 TOPS (total)	1000 INT8 TOPS^[23]	2000 FP8 TOPS^[46]
TDP		20W^[57]	40W SoC portion: 10W^[42]	40W SoC portion: 10W^[42]	80W^[59]^[60]^[57]^[61] SoC portion: 20W^[42]	60W^[59]^[60]^[57] SoC portion: 20W^[42]	30W^[49]	500W^[58]	130W	750W	?	?

Note: dGPU and memory are stand-alone semiconductors; all other components, especially ARM cores, iGPU and DLA are integrated components of the listed main computing device(s)

References

1. Umar Zakir Abdul, Hamid; et al. (2016). "Current Collision Mitigation Technologies for Advanced Driver Assistance Systems–A Survey". PERINTIS eJournal. 6 (2). Retrieved 14 June 2017.
2. NVIDIA DRIVE
3. "Cars drive autonomously with Nvidia X1-based computer". Cnet. Cnet. 5 January 2015. Retrieved 29 March 2016.
4. "Nvidia Announces Another Car 'Supercomputer' at CES". The Wall Street Journal. 4 January 2016. Retrieved 29 March 2016.
5. Smith, Joshua Ho, Ryan. "NVIDIA Tegra X1 Preview & Architecture Analysis". Retrieved 2016-09-18.{{cite web}}: CS1 maint: multiple names: authors list (link)
6. NVIDIA ebnet den Weg für die Autos von Morgen mit den NVIDIA-DRIVE-Automotive-Computern
7. Smith, Ryan. "NVIDIA Announces DRIVE PX 2 – Pascal Power For Self-Driving Cars". Retrieved 2016-09-18.
8. "Autonomous Car Development Platform from NVIDIA DRIVE PX2". www.nvidia.com. Retrieved 2016-09-18.
9. Lambert, Fred (21 October 2016). "All new Teslas are equipped with NVIDIA's new Drive PX 2 AI platform for self-driving". Electrek. Retrieved 25 January 2017.
10. Dow, Jameson (20 May 2017). "Roborace debuts their driverless "Robocar" on track at the Paris ePrix". Electrek. Retrieved 21 May 2017.
11. Look inside Tesla’s onboard Nvidia supercomputer for self-driving
12. Why Tesla’s Nvidia Supercomputer for Self-Driving is not as Powerful as Expected
13. Cutress, Ian; Tallis, Billy (4 January 2016). "CES 2017: Nvidia Keynote Liveblog". Anandtech.com. Retrieved 9 January 2017.
14. Baldwin, Roberto (8 January 2018). "NVIDIA unveils its powerful Xavier SOC for self-driving cars". Engadget. Retrieved 8 January 2018.
15. Autonomous Car Development Platform from NVIDIA DRIVE PX2
16. Smith, Ryan (28 September 2016). "Nvidia Teases Xavier, A High Performance SoC for Drive PX & AI". Anandtech. Retrieved 22 June 2017.
17. "Autonomous Car Development Platform from NVIDIA DRIVE PX2". NVIDIA. Retrieved 2017-12-01.
18. Oh, Nate (October 10, 2017). "NVIDIA Announces Drive PX Pegasus at GTC Europe 2017: Level 5 Self-Driving Hardware, Feat. Post-Volta GPUs". AnandTech. Retrieved 2017-10-10.
19. Auchard, Eric (10 October 2017). . Reuters. Archived from the original on Oct 18, 2017. Retrieved 17 October 2017.
20. Smith, Ryan (December 18, 2019). "NVIDIA Details DRIVE AGX Orin: A Herculean Arm Automotive SoC For 2022". AnandTech. Retrieved 2019-12-21.
21. Eric Abent (May 14, 2020). "NVIDIA Drive upshifts to Ampere GPUs for a smoother self-driving roadmap". Slash Gear.
22. Tomazin, Tom (12 April 2021). "A Data Center on Wheels: NVIDIA Unveils DRIVE Atlan Autonomous Vehicle Platform". NVIDIA. Retrieved 18 March 2024.
23. Smith, Ryan (20 September 2022). "NVIDIA Drops DRIVE Atlan SoC, Introduces 2 PFLOPS DRIVE Thor for 2025 Autos". Anandtech. Retrieved 18 March 2024.
24. Kani, Ali (20 September 2022). "DRIVE Thor Unites AV and Cockpit on a Single SoC". NVIDIA. Retrieved 6 January 2023.
25. Kani, Ali (20 September 2022). "DRIVE Thor Unites AV and Cockpit on a Single SoC". NVIDIA. Retrieved 6 January 2023.
26. Labrie, Marie (18 March 2024). "NVIDIA DRIVE Powers Next Generation of Transportation — From Cars and Trucks to Robotaxis and Autonomous Delivery Vehicles". NVIDIA. Retrieved 18 March 2024.
27. "Drive-faq". 3 November 2021.
28. presentation from December 2019: https://on-demand.gputechconf.com/gtc-cn/2019/pdf/CN9618/presentation.pdf
29. "DeepRoute.ai to Integrate NVIDIA DRIVE Hyperion into L4 Autonomous Driving Solutions". 22 March 2022.
30. "Nvidia Drive Archives". 27 July 2017.
31. "Android installation on DRIVE AGX". 3 September 2021.
32. "Nvidia Drive SDK". 20 February 2019.
33. "NVIDIA DRIVE Hyperion 7.1". 10 March 2022.
34. "Nvidia Drive Hyperion 9: Plattform für autonomes Fahren mit Atlan startet 2026". 22 March 2022.
35. "Nvidia Drive Hyperion 9: Plattform für autonomes Fahren mit Atlan startet 2026". 22 March 2022.
36. "DRIVE Hyperion Autonomous Vehicle Development Platform". 31 January 2019.
37. "Nvidia Drive Hyperion 9: Plattform für autonomes Fahren mit Atlan startet 2026". 22 March 2022.
38. "NVIDIA Unveils Next-Gen DRIVE Hyperion Autonomous Vehicle Platform". 24 March 2022.
39. "DRIVE AGX Pegasus OA Developer Kit". NVIDIA Developer. 2022-05-26. Retrieved 2022-05-26.
40. Kennedy, Patrick (23 August 2022). "NVIDIA Orin Brings Arm and Ampere to the Edge at Hot Chips 34". ServeTheHome. Retrieved 6 January 2023.
41. Uchiyama, Kristin (18 March 2024). "NVIDIA Blackwell Platform Arrives to Power a New Era of Computing". NVIDIA. Retrieved 18 March 2024.
42. Nvidia unveils palm-sized single SoC version of the DRIVE PX2
43. "All Tesla Cars Being Produced Now Have Full Self-Driving Hardware". www.tesla.com. Retrieved 2017-12-01.
44. "Tesla has a new Autopilot '2.5' hardware suite with more computing power for autonomous driving". Electrek. 2017-08-09. Retrieved 2018-10-26.
45. Labrie, Marie. "NVIDIA Unveils NVIDIA DRIVE Atlan, an AI Data Center on Wheels for Next-Gen Autonomous Vehicles". nvidianews.nvidia.com. NVIDIA. Retrieved 6 January 2023.
46. Labrie, Marie. "NVIDIA Unveils DRIVE Thor — Centralized Car Computer Unifying Cluster, Infotainment, Automated Driving, and Parking in a Single, Cost-Saving System". NVIDIA. Retrieved 6 January 2023.
47. Abuelsamid, Sam. "Nvidia Launches 1,000 TOPS Automated Driving Chip, Volvo To Launch Orin-Powered System In 2022". Forbes. Retrieved 2021-09-10.
48. "First look at Tesla's latest Autopilot (2.5) computer in Model 3, S, and X vehicles". Electrek. 2018-03-28. Retrieved 2018-10-26.
49. NVIDIA Xavier SOC Is The Most Biggest and Complex SOC To Date
50. Kani, Ali (20 September 2022). "DRIVE Thor Unites AV and Cockpit on a Single SoC". NVIDIA. Retrieved 6 January 2023.
51. Labrie, Marie (18 March 2024). "NVIDIA DRIVE Powers Next Generation of Transportation — From Cars and Trucks to Robotaxis and Autonomous Delivery Vehicles". NVIDIA. Retrieved 18 March 2024.
52. Kani, Ali (20 September 2022). "DRIVE Thor Unites AV and Cockpit on a Single SoC". NVIDIA. Retrieved 6 January 2023.
53. NVIDIA Announces Pascal GPU Powered Drive PX 2 – 16nm FinFET Based, Liquid Cooled AI Supercomputer With 8 TFLOPs Performance
54. Labrie, Marie (18 March 2024). "NVIDIA DRIVE Powers Next Generation of Transportation — From Cars and Trucks to Robotaxis and Autonomous Delivery Vehicles". NVIDIA. Retrieved 18 March 2024.
55. "Hardware". NVIDIA Developer. 2017-03-30. Retrieved 2017-12-01.
56. Ho, Joshua. "Hot Chips 2016: NVIDIA Discloses Tegra Parker Details". Retrieved 2018-10-26.
57. Pirzada, Usman (2016-04-05). "Nvidia Drive PX 2 Uses Integrated and Discrete Pascal GPU Cores - 24 DL TOPS, 8 TFLOPs and Up To 4GB GDDR5 [Updated]". Wccftech. Retrieved 2018-10-26.
58. "Nvidia AI and multi-petaOps chips for class 5 automated cars within 4 years - NextBigFuture.com". NextBigFuture.com. 2017-10-27. Retrieved 2018-10-26.
59. Oberman, Stuart (October 2017). "Nvidia GPU computing: a journey from PC gaming to deep learning" (PDF). Stanford University Colloquium on Computer Systems EE380. (PDF) from the original on Sep 26, 2023.
60. SteveNV (19 April 2017). "Thermal Design Power". NVIDIA Developer Forums. from the original on Nov 19, 2018. Retrieved 2018-10-26.
61. Altavilla, Dave (Sep 28, 2016). "NVIDIA Doubles Down On Self-Driving Cars With Xavier AI Chip And A Hat Tip To Next Gen Volta GPU". Forbes. from the original on Sep 29, 2016. Retrieved 2018-10-26.