AI Chips · Product page

NVIDIA V100 (Volta): The Complete Guide

The chip that put Tensor Cores into a data-centre GPU for the first time, in 2017. Simple to expert, every number links to its source.

Ask an AI about this chip:CAGPX
NVIDIA V100 10 sections · 2 levels 4 linked sources Checked September 2026
How to read this page. Each section starts Simple, then goes to a Deep dive: stop wherever you have what you need. The small numbers are sources: click one to open the original document. Where the maker has not published a figure -- a price, a die size, a factory address -- this page says so rather than estimate it.

1.At a glance

SimpleStart here

The V100 is a data-centre graphics chip NVIDIA announced on 10 May 2017 1. It was the first NVIDIA chip built around Tensor Cores — circuits designed specifically to speed up deep learning — and it is the chip that started NVIDIA’s run as the default hardware for training AI models.

Deep diveThe technical detail

Codename GV100, architecture Volta. Announced at Jensen Huang’s GTC 2017 keynote 1; Volta-based DGX-1, DGX Station and HGX-1 systems were slated to ship in Q3 2017 2. It shipped in 16GB and 32GB HBM2 variants, in both PCIe and SXM2 form factors 3.

2.Launch and history

SimpleStart here

NVIDIA framed Volta’s launch around a single new idea: a GPU core built just for the matrix math behind neural networks. Before V100, NVIDIA’s data-centre chips were general-purpose number-crunchers first and AI accelerators second. V100 flipped that.

Deep diveThe technical detail

NVIDIA’s own release frames Volta’s generational gains as a “5x improvement over Pascal architecture” and “15x over Maxwell” 1, naming P100 (Pascal) as the direct predecessor generation. DGX-1 (8× V100 via NVLink) and DGX Station (4× V100) were announced alongside the chip as the systems meant to put it to work immediately 2.

3.What’s inside it

SimpleStart here

V100’s headline feature was Tensor Cores: dedicated circuits for the specific kind of matrix multiplication that deep learning training and inference run millions of times over. NVIDIA said they gave “up to 12x higher peak TFLOPS for training and 6x higher peak TFLOPS for inference” compared with the previous generation 4.

Deep diveThe technical detail

Three architectural claims from NVIDIA’s own whitepaper 4:

  • Tensor Cores — “new Tensor Cores designed specifically for deep learning deliver up to 12x higher peak TFLOPS for training and 6x higher peak TFLOPS for inference” versus the prior generation.
  • Independent Thread Scheduling — “Volta’s new independent thread scheduling capability enables finer-grain synchronization and cooperation between parallel threads.” This broke the lock-step warp execution model NVIDIA GPUs had used since the start of CUDA, and every architecture since (Turing, Ampere, Hopper, Blackwell) has kept it.
  • 2nd-generation NVLink — “delivers higher bandwidth, more links, and improved scalability for multi-GPU and multi-GPU/CPU system configurations.”

4.Full spec table

SimpleStart here

640 Tensor Cores, 5,120 CUDA cores, and either 16GB or 32GB of HBM2 memory, depending on the variant 3.

Deep diveThe technical detail
SpecV100 PCIeV100 SXM2V100S PCIe (2019 refresh)
Process nodeTSMC 12nm FFN (custom) 4
Transistors21.1 billion 3
Die size815 mm² 3
CUDA cores5,120 3
Tensor cores640 3
Memory16GB or 32GB HBM216GB or 32GB HBM232GB HBM2
Memory bandwidth900 GB/s1,134 GB/s1,134 GB/s
TDP250 W300 W250 W
FP647 TFLOPS7.8 TFLOPS8.2 TFLOPS
FP3214 TFLOPS15.7 TFLOPS16.4 TFLOPS
Tensor (FP16)112 TFLOPS125 TFLOPS130 TFLOPS
NVLinkNot present (PCIe Gen3, 32 GB/s)2nd gen, 300 GB/sNot present
Form factorPCIe (FHFL)SXM2PCIe

All figures per NVIDIA’s own datasheet and whitepaper 34. FP8 was not supported — the format did not exist on Volta. An official INT8 TOPS figure was not found in the reviewed datasheet.

5.Where it’s made

SimpleStart here

V100 was made by TSMC, on a custom process NVIDIA calls 12nm FFN 4. NVIDIA designs its chips but does not operate the factories that manufacture them (a “fabless” company) — this is true of every NVIDIA chip on this site.

Deep diveThe technical detail

Process: TSMC 12nm FFN (FinFET NVIDIA, a custom high-performance variant of TSMC’s 12nm node) 4. NVIDIA’s public materials name the foundry and the process name but do not publish which of TSMC’s individual fabs produced V100 wafers — that level of detail is not published by either company.

6.Which systems use it

SimpleStart here

NVIDIA’s own systems built around V100 were DGX-1 (8 chips) and DGX Station (4 chips) 2. NVIDIA also named AWS, Google Cloud and Microsoft Azure as launch cloud partners offering V100 instances 1.

Deep diveThe technical detail

DGX-1 combines 8× V100 GPUs connected by NVLink 2. Oak Ridge National Laboratory’s Summit supercomputer, completed in 2018, was cited by NVIDIA at launch as an adopter of the Volta platform 1. Cloud availability: Amazon Web Services (P3 instances), Google Cloud, and Microsoft Azure N-series, all named in NVIDIA’s own launch release 1.

7.Official pricing

SimpleStart here

NVIDIA has not published a standalone price for the V100 chip itself. Its May 2017 release does not state a system price either — it directs readers to nvidia.com for DGX-1 and DGX Station pricing 2.

Deep diveThe technical detail

NVIDIA’s own DGX-1 announcement says pricing is available at nvidia.com/dgx-1 and nvidia.com/dgx-station, rather than stating a figure in the release itself 2. Numbers circulated by press outlets at the time (commonly cited around $149,000 for DGX-1) could not be traced to an NVIDIA-owned document in this page’s research pass, so this page does not state them as fact. Cloud providers publish their own hourly rates for V100 instances on their own pricing pages, which change over time and are not reproduced here.

8.Real-world performance

SimpleStart here

NVIDIA’s own whitepaper claims “up to 12x higher peak TFLOPS for training and 6x higher peak TFLOPS for inference” over the prior generation 4 — a company-stated figure, not an independent benchmark.

Deep diveThe technical detail

All performance figures on this page (112–130 TFLOPS Tensor FP16 depending on variant) are NVIDIA’s own specification numbers 3, not third-party benchmark results. No independent MLPerf-style benchmark citation for V100 was confirmed in this research pass — MLPerf’s first round post-dates V100’s launch and V100 appears in later rounds as a reference point rather than this page’s primary performance source.

9.What came before, what came next

SimpleStart here

Came before: P100 (Pascal architecture). Came after: A100 (Ampere architecture), announced May 2020 1.

Deep diveThe technical detail

NVIDIA’s own release frames Volta’s gains against “Pascal architecture” and “Maxwell” by name, making P100 the direct predecessor generation 1. V100’s direct successor is the A100 (Ampere), the next data-centre GPU generation NVIDIA announced.

10.Hidden in plain sight

SimpleStart here

V100’s quiet feature outlived its headline one. Tensor Cores got the announcement; independent thread scheduling — barely mentioned at launch — changed how every NVIDIA GPU since has executed code.

Deep diveThe technical detail

NVIDIA’s architecture whitepaper describes independent thread scheduling as enabling “finer-grain synchronization and cooperation between parallel threads” 4. It broke a rigid lock-step execution model NVIDIA GPUs had used since the beginning of CUDA — letting threads inside the same warp diverge and interleave independently. Every NVIDIA architecture released since (Turing, Ampere, Hopper, Blackwell) has kept this model, even though it was not what V100 was marketed for.

11.Sources

4 sources, checked September 2026. Where NVIDIA or another maker has not published a figure, this page says so rather than estimate it.

  1. NVIDIA Newsroom: NVIDIA Launches Revolutionary Volta GPU Platform, Fueling Next Era of AI and High Performance ComputingOfficial
  2. NVIDIA Newsroom: NVIDIA Advances AI Computing Revolution with New Volta-Based DGX SystemsOfficial
  3. NVIDIA: Tesla V100 GPU DatasheetOfficial
  4. NVIDIA: NVIDIA Tesla V100 GPU Architecture Whitepaper (WP-08608-001_v1.1)Official