Volta (microarchitecture)

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Nvidia Volta
Release dateDecember 7, 2017
CodenameVolta
Transistors12 nm
Cards
EnthusiastTesla V100
Titan V
Titan V CEO Edition
Quadro GV100
History
PredecessorPascal
SuccessorTuring

Volta is the codename for a GPU microarchitecture developed by Nvidia, succeeding Pascal. It was first announced on a roadmap in March 2013.[1] However the first product was not announced until May 2017.[2] 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.[3]

The first graphics card to use it was the datacentre Tesla V100, e.g. as part of the Nvidia DGX-1 system.[2] It has also been used in the Quadro GV100 and Titan V. There were no mainstream GeForce graphics cards based on Volta. Volta was succeeded by the Turing architecture.

Details[edit]

Architectural improvements of the Volta architecture include the following:

  • CUDA Compute Capability 7.0
  • High Bandwidth Memory 2[4][5]
  • 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.[6] (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.[7] Tensor cores are intended to speed up the training of neural networks.[7]
  • PureVideo Feature Set I hardware video decoding

Products[edit]

Volta has been announced as the GPU microarchitecture within the Xavier generation of Tegra SoC focusing on self-driving cars.[8][9]

At Nvidia's annual GPU Technology Conference keynote on 10th May 2017, Nvidia officially announced the Volta microarchitecture along with the Tesla V100.[2] The Volta GV100 GPU is built on a 12 nm process size using HBM2 memory with 900 GB/s of bandwidth.[10]

Nvidia officially announced the NVIDIA TITAN V on December 7, 2017.[11][12]

Nvidia officially announced the Quadro GV100 on March 27, 2018.[13]

Model Launch Code Name (s) Fab
(nm)
Transistors
(billion)
Die size
(mm2)
Bus Interface Core config SM
Count[a]
Graphics
Processing
Clusters[b]
L2 Cache
Size (MiB)
Clock speeds Fillrate Memory Processing power (GFLOPS) TDP
(Watts)
NVLink Support Launch Price
(USD)
CUDA
core[c]
Tensor
Core[d]
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[14] December 7, 2017 GV100-400-A1 12 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[15] 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[16][17] June 21, 2018 1200 1455 1700 186.2 465.6 870.4 12288 (14899) 6144 (7450) 24576 (29798) N/A
  1. ^ One Streaming Multiprocessor encompasses 64 CUDA cores and 4 TMUs.
  2. ^ One Graphics Processing Cluster encompasses fourteen Streaming Multiprocessors.
  3. ^ CUDA cores : Texture mapping units : Render output units
  4. ^ A Tensor core is a mixed-precision FPU specifically designed for matrix arithmetic.

Application[edit]

Volta is also reported to be included in the Summit and Sierra supercomputers, used for GPGPU compute.[18][19] 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.[20][6][21]

See also[edit]

References[edit]

  1. ^ Gasior, Geoff (19 March 2013). "Nvidia's Volta GPU to feature on-chip DRAM". The Tech Report. Retrieved 14 March 2017.
  2. ^ a b c Smith, Ryan (2017-05-10). "The NVIDIA GPU Tech Conference 2017 Keynote Live Blog". Retrieved 2018-11-03.
  3. ^ "NVIDIA Volta AI Architecture | NVIDIA". NVIDIA. Retrieved 2018-04-11.
  4. ^ Killian, Zak (14 March 2017). "Report: TSMC set to fabricate Volta and Centriq on 12-nm process". The Tech Report. Retrieved 14 March 2017.
  5. ^ Gasior, Geoff (March 19, 2013). "Nvidia's Volta GPU to feature on-chip DRAM". The Tech Report.
  6. ^ a b Shah, Agam (22 August 2016). "Nvidia's NVLink 2.0 will first appear in Power9 servers next year". PC World. Retrieved 14 March 2017.
  7. ^ a b Harris, Mark (May 11, 2017). "CUDA 9 Features Revealed: Volta, Cooperative Groups and More". Retrieved August 12, 2017.
  8. ^ Cutress, Ian; Tallis, Billy (4 January 2016). "CES 2017: Nvidia Keynote Liveblog". AnandTech. Retrieved 9 January 2017.
  9. ^ "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.
  10. ^ Smith, Ryan (10 May 2017). "Nvidia Volta Unveiled". AnandTech. Retrieved 2 June 2017.
  11. ^ https://nvidianews.nvidia.com/news/nvidia-titan-v-transforms-the-pc-into-ai-supercomputer
  12. ^ https://www.nvidia.com/en-us/titan/titan-v/
  13. ^ https://nvidianews.nvidia.com/news/nvidia-reinvents-the-workstation-with-real-time-ray-tracing
  14. ^ "Introducing NVIDIA TITAN V: The World's Most Powerful PC Graphics Card". NVIDIA. Retrieved 2017-12-08.
  15. ^ "NVIDIA Quadro GV100". Retrieved 2018-03-27.
  16. ^ Smith, Ryan. "NVIDIA Unveils & Gives Away New Limited Edition 32GB Titan V "CEO Edition"". Retrieved 2018-07-06.
  17. ^ "NVIDIA TITAN V CEO Edition". TechPowerUp. Retrieved 2018-07-07.
  18. ^ Shankland, Steven (14 September 2015). "IBM, Nvidia land $325M supercomputer deal". CNET. Retrieved 29 December 2015.
  19. ^ Noyes, Katherine (16 March 2015). "IBM, Nvidia rev HPC engines in next-gen supercomputer push". PC World. Retrieved 29 December 2015.
  20. ^ Smith, Ryan (17 November 2014). "Nvidia Volta, IBM Power9 Land Contracts for New US Government Supercomputers". Anandtech. Retrieved 14 March 2017.
  21. ^ Lilly, Paul (January 25, 2017). "NVIDIA 12nm FinFET Volta GPU Architecture Reportedly Replacing Pascal In 2017". HotHardware.

External links[edit]