Volta (microarchitecture)
Volta is the codename, but not the trademark,[1] for a GPU microarchitecture developed by Nvidia, succeeding Pascal. It was first announced on a roadmap in March 2013,[2] although the first product was not announced until May 2017.[3] The architecture is named after 18th–19th century Italian chemist and physicist Alessandro Volta. It was NVIDIA's first chip to feature Tensor Cores, specially designed cores that have superior deep learning performance over regular CUDA cores.[4] The architecture is produced with TSMC's 12 nm FinFET process. The Ampere microarchitecture is the successor to Volta.
Release date | December 7, 2017 |
---|---|
Codename | Volta |
Fabrication process | TSMC 12 nm (FinFET) |
Cards | |
Enthusiast |
|
History | |
Predecessor | Pascal |
Variant | Turing (consumer) |
Successor | Ampere (consumer, professional) |
Support status | |
Supported |
The first graphics card to use it was the datacenter Tesla V100, e.g. as part of the Nvidia DGX-1 system.[3] It has also been used in the Quadro GV100 and Titan V. There were no mainstream GeForce graphics cards based on Volta.
After two USPTO proceedings,[5][6] on Jul. 03, 2023 NVIDIA lost the Volta trademark application in the field of artificial intelligence. The Volta trademark [7] owner remains Volta Robots, a company specialized in AI and vision algorithms for robots and unmanned vehicles.
Details
Architectural improvements of the Volta architecture include the following:
- CUDA Compute Capability 7.0
- concurrent execution of integer and floating point operations
- TSMC's 12 nm FinFET process,[8] allowing 21.1 billion transistors.[9]
- High Bandwidth Memory 2 (HBM2),[8][10]
- NVLink 2.0: a high-bandwidth bus between the CPU and GPU, and between multiple GPUs. Allows much higher transfer speeds than those achievable by using PCI Express; estimated to provide 25 Gbit/s per lane.[11] (Disabled for Titan V)
- Tensor cores: A tensor core is a unit that multiplies two 4×4 FP16 matrices, and then adds a third FP16 or FP32 matrix to the result by using fused multiply–add operations, and obtains an FP32 result that could be optionally demoted to an FP16 result.[12] Tensor cores are intended to speed up the training of neural networks.[12] Volta's Tensor cores are first generation while Ampere has third generation Tensor cores.[13][14]
- PureVideo Feature Set I hardware video decoding
Comparison of Compute Capability: GP100 vs GV100 vs GA100[15]
GPU features | NVIDIA Tesla P100 | NVIDIA Tesla V100 | NVIDIA A100 |
---|---|---|---|
GPU codename | GP100 | GV100 | GA100 |
GPU architecture | NVIDIA Pascal | NVIDIA Volta | NVIDIA Ampere |
Compute capability | 6.0 | 7.0 | 8.0 |
Threads / warp | 32 | 32 | 32 |
Max warps / SM | 64 | 64 | 64 |
Max threads / SM | 2048 | 2048 | 2048 |
Max thread blocks / SM | 32 | 32 | 32 |
Max 32-bit registers / SM | 65536 | 65536 | 65536 |
Max registers / block | 65536 | 65536 | 65536 |
Max registers / thread | 255 | 255 | 255 |
Max thread block size | 1024 | 1024 | 1024 |
FP32 cores / SM | 64 | 64 | 64 |
Ratio of SM registers to FP32 cores | 1024 | 1024 | 1024 |
Shared Memory Size / SM | 64 KB | Configurable up to 96 KB | Configurable up to 164 KB |
Comparison of Precision Support Matrix[16][17]
Supported CUDA Core Precisions | Supported Tensor Core Precisions | |||||||||||||||
FP16 | FP32 | FP64 | INT1 | INT4 | INT8 | TF32 | BF16 | FP16 | FP32 | FP64 | INT1 | INT4 | INT8 | TF32 | BF16 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
NVIDIA Tesla P4 | No | Yes | Yes | No | No | Yes | No | No | No | No | No | No | No | No | No | No |
NVIDIA P100 | Yes | Yes | Yes | No | No | No | No | No | No | No | No | No | No | No | No | No |
NVIDIA Volta | Yes | Yes | Yes | No | No | Yes | No | No | Yes | No | No | No | No | No | No | No |
NVIDIA Turing | Yes | Yes | Yes | No | No | No | No | No | Yes | No | No | Yes | Yes | Yes | No | No |
NVIDIA A100 | Yes | Yes | Yes | No | No | Yes | No | Yes | Yes | No | Yes | Yes | Yes | Yes | Yes | Yes |
Legend:
- FPnn: floating point with nn bits
- INTn: integer with n bits
- INT1: binary
- TF32: TensorFloat32
- BF16: bfloat16
Comparison of Decode Performance
Concurrent streams | H.264 decode (1080p30) | H.265 (HEVC) decode (1080p30) | VP9 decode (1080p30) |
---|---|---|---|
V100 | 16 | 22 | 22 |
A100 | 75 | 157 | 108 |
Products
Volta has been announced as the GPU microarchitecture within the Xavier generation of Tegra SoC focusing on self-driving cars.[18][19]
At Nvidia's annual GPU Technology Conference keynote on May 10, 2017, Nvidia officially announced the Volta microarchitecture along with the Tesla V100.[3] The Volta GV100 GPU is built on a 12 nm process size using HBM2 memory with 900 GB/s of bandwidth.[20]
Nvidia officially announced the NVIDIA TITAN V on December 7, 2017.[21][22]
Nvidia officially announced the Quadro GV100 on March 27, 2018.[23]
Model | Launch | Code Name (s) | Fab (nm) |
Transistors (billion) |
Die size (mm2) |
Bus Interface | Core config | SM Count[lower-alpha 1] |
Graphics Processing Clusters[lower-alpha 2] |
L2 Cache Size (MiB) |
Clock speeds | Fillrate | Memory | Processing power (GFLOPS) | TDP (Watts) |
NVLink Support | Launch Price (USD) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CUDA core[lower-alpha 3] |
Tensor core[lower-alpha 4] |
Base core clock (MHz) |
Boost clock (MHz) |
Memory (MT/s) |
Pixel (GP/s) |
Texture (GT/s) |
Size (GiB) |
Bandwidth (GB/s) |
Bus Type |
Bus width (bit) |
Single precision (boost) |
Double precision (boost) |
Half precision (boost) | |||||||||||||
MSRP | ||||||||||||||||||||||||||
Nvidia Titan V[24] | December 7, 2017 | GV100-400-A1 | TSMC 12 nm | 21.1 | 815 | PCIe 3.0 ×16 | 5120:320:96 | 640 | 80 | 6 | 4.5 | 1200 | 1455 | 1700 | 139.7 | 465.6 | 12 | 652.8 | HBM2 | 3072 | 12288 (14899) | 6144 (7450) | 24576 (29798) | 250 | No | $2,999 |
Nvidia Quadro GV100[25] | March 27, 2018 | GV100 | 5120:320:128 | 6 | 1132 | 1628 | 1696 | 208.4 | 521 | 32 | 868.4 | 4096 | 11592 (16671) | 5796 (8335) | 23183 (33341) | Yes | $8,999 | |||||||||
Nvidia Titan V CEO Edition[26][27] | June 21, 2018 | 1200 | 1455 | 1700 | 186.2 | 465.6 | 870.4 | 12288 (14899) | 6144 (7450) | 24576 (29798) | N/A |
- One Streaming Multiprocessor encompasses 64 CUDA cores and 4 TMUs.
- One Graphics Processing Cluster encompasses fourteen Streaming Multiprocessors.
- CUDA cores : Texture mapping units : Render output units
- A Tensor core is a mixed-precision FPU specifically designed for matrix arithmetic.
Application
Volta is also reported to be included in the Summit and Sierra supercomputers, used for GPGPU compute.[28][29] The Volta GPUs will connect to the POWER9 CPUs via NVLink 2.0, which is expected to support cache coherency and therefore improve GPGPU performance.[30][11][31]
References
- "Nvidia Volta Trademark Status". United_States_Patent_and_Trademark_Office. 14 August 2023. Retrieved 14 August 2023.
- Gasior, Geoff (19 March 2013). "Nvidia's Volta GPU to feature on-chip DRAM". The Tech Report. Retrieved 14 March 2017.
- Smith, Ryan (2017-05-10). "The NVIDIA GPU Tech Conference 2017 Keynote Live Blog". Retrieved 2018-11-03.
- "NVIDIA Volta AI Architecture | NVIDIA". NVIDIA. Retrieved 2018-04-11.
- "Volta trademark Cancellation Proceeding". United_States_Patent_and_Trademark_Office.
- "Volta trademark Exparte Appeal Proceeding". United_States_Patent_and_Trademark_Office.
- "Volta Trademark status". United_States_Patent_and_Trademark_Office.
- Killian, Zak (14 March 2017). "Report: TSMC set to fabricate Volta and Centriq on 12-nm process". The Tech Report. Retrieved 14 March 2017.
- Durant, Luke; Giroux, Olivier; Harris, Mark; Stam, Nick (May 10, 2017). "Inside Volta: The World's Most Advanced Data Center GPU". Nvidia developer blog.
- Gasior, Geoff (March 19, 2013). "Nvidia's Volta GPU to feature on-chip DRAM". The Tech Report.
- Shah, Agam (22 August 2016). "Nvidia's NVLink 2.0 will first appear in Power9 servers next year". PC World. Retrieved 14 March 2017.
- Harris, Mark (May 11, 2017). "CUDA 9 Features Revealed: Volta, Cooperative Groups and More". Retrieved August 12, 2017.
- "NVIDIA Ampere Architecture In-Depth". 14 May 2020.
- https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/nvidia-ampere-architecture-whitepaper.pdf
- "NVIDIA A100 Tensor Core GPU Architecture: Unprecedented Accerlation at Every Scale" (PDF). Nvidia. Retrieved September 18, 2020.
- "NVIDIA Tensor Cores: Versatility for HPC & AI". NVIDIA.
- "Abstract". docs.nvidia.com.
- Cutress, Ian; Tallis, Billy (4 January 2016). "CES 2017: Nvidia Keynote Liveblog". AnandTech. Retrieved 9 January 2017.
- "NVIDIA DRIVE Xavier, World's Most Powerful SoC, Brings Dramatic New AI Capabilities | NVIDIA Blog". The Official NVIDIA Blog. 2018-01-07. Retrieved 2018-11-03.
- Smith, Ryan (10 May 2017). "Nvidia Volta Unveiled". AnandTech. Retrieved 2 June 2017.
- "NVIDIA TITAN V Transforms the PC into AI Supercomputer".
- "Introducing NVIDIA TITAN V: The World's Most Powerful PC Graphics Card".
- "NVIDIA Reinvents the Workstation with Real-Time Ray Tracing".
- "Introducing NVIDIA TITAN V: The World's Most Powerful PC Graphics Card". NVIDIA. Retrieved 2017-12-08.
- "NVIDIA Quadro GV100". Retrieved 2018-03-27.
- Smith, Ryan. "NVIDIA Unveils & Gives Away New Limited Edition 32GB Titan V "CEO Edition"". Retrieved 2018-07-06.
- "NVIDIA TITAN V CEO Edition". TechPowerUp. Retrieved 2018-07-07.
- Shankland, Steven (14 September 2015). "IBM, Nvidia land $325M supercomputer deal". CNET. Retrieved 29 December 2015.
- Noyes, Katherine (16 March 2015). "IBM, Nvidia rev HPC engines in next-gen supercomputer push". PC World. Retrieved 29 December 2015.
- Smith, Ryan (17 November 2014). "Nvidia Volta, IBM Power9 Land Contracts for New US Government Supercomputers". Anandtech. Retrieved 14 March 2017.
- Lilly, Paul (January 25, 2017). "NVIDIA 12nm FinFET Volta GPU Architecture Reportedly Replacing Pascal In 2017". HotHardware.