Report an Error
NVIDIA Tesla K20s
- Graphics Processor
- GK110
- Cores
- 2496
- TMUs
- 208
- ROPs
- 40
- Memory Size
- 5 GB
- Memory Type
- GDDR5
- Bus Width
- 320 bit
GPU
The Tesla K20s was an enthusiast-class professional graphics card by NVIDIA, launched on February 18th, 2013. Built on the 28 nm process, and based on the GK110 graphics processor, the card supports DirectX 12. The GK110 graphics processor is a large chip with a die area of 561 mm² and 7,080 million transistors. Unlike the fully unlocked GeForce GTX TITAN, which uses the same GPU but has all 2688 shaders enabled, NVIDIA has disabled some shading units on the Tesla K20s to reach the product's target shader count. It features 2496 shading units, 208 texture mapping units, and 40 ROPs. NVIDIA has paired 5 GB GDDR5 memory with the Tesla K20s, which are connected using a 320-bit memory interface. The GPU is operating at a frequency of 575 MHz, memory is running at 1300 MHz (5.2 Gbps effective).
Being a dual-slot card, its power draw is rated at 225 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla K20s is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 3199 US Dollars.
Being a dual-slot card, its power draw is rated at 225 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla K20s is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 3199 US Dollars.
Graphics Processor
Graphics Card
- Release Date
- Feb 18th, 2013
- Generation
-
Tesla Kepler
(Kxx)
- Predecessor
- Tesla Fermi
- Successor
- Tesla Maxwell
- Production
- End-of-life
- Launch Price
- 3,199 USD
- Bus Interface
- PCIe 2.0 x16
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- GPU Clock
- 575 MHz
- Memory Clock
-
1300 MHz
5.2 Gbps effective
Memory
- Memory Size
- 5 GB
- Memory Type
- GDDR5
- Memory Bus
- 320 bit
- Bandwidth
- 208.0 GB/s
Render Config
- Shading Units
- 2496
- TMUs
- 208
- ROPs
- 40
- SMX Count
- 13
- L1 Cache
- 16 KB (per SMX)
- L2 Cache
- 1280 KB
Theoretical Performance
- Pixel Rate
- 29.90 GPixel/s
- Texture Rate
- 119.6 GTexel/s
- FP32 (float)
- 2.870 TFLOPS
- FP64 (double)
- 956.8 GFLOPS (1:3)
Board Design
- Slot Width
- Dual-slot
- Length
- 267 mm
10.5 inches
- TDP
- 225 W
- Suggested PSU
- 550 W
- Outputs
- No outputs
Graphics Features
- DirectX
- 12 (11_0)
- OpenGL
- 4.6
- OpenCL
- 3.0
- Vulkan
- 1.2.175
- CUDA
- 3.5
- Shader Model
- 6.5 (5.1)
GK110 GPU Notes
| NVENC: 1st Gen NVDEC: 1st Gen PureVideo HD: VP5 VDPAU: Feature Set D L1 Cache is configurable from 16 KB up to 48 KB per SMX GK110 has 5 GPCs each capable of 8 pixels per clock. This limits complete GPU to 40 pixels per clock and because of that it can't feed all 48 ROPs when they all require data at the same time. Additional ROPs however can be used for MSAA (because it doesn't require additional data from rasterizers, while giving more work to ROPs.) Latest Drivers: Windows XP / Server 2003 x64: Quadro Release R319 U2 (321.01) Windows Vista: GeForce Release 365.19 Quadro Release R346 U7 (348.40) / R352 BETA (352.86) Windows 7 / 8 / 8.1 / 10 / 11 (x32 / x64): GeForce Release 391.35 / 475.06 Quadro Release R390 U9 (392.37) / R470 U16 (474.82) Data Center Release 427.11 Tesla Release 441.22 Windows 10 / 11 x64: GeForce Release 475.06 Quadro Release R470 U16 (474.82) Data Center Release 474.82 |
Nov 21st, 2024 10:16 EST
change timezone
Latest GPU Drivers
New Forum Posts
- Scratched mobo traces with a screwdriver (8)
- It is Black Friday What are we looking to get? (1)
- Few PCIe lanes on home motherboards for how long? (33)
- New gaming PC build. (4)
- 9800x 3d vs 12900k - Battle of the Century (167)
- Different low reading (37)
- 3D Printer Club (299)
- New RTX 5090 + 9800X3D build: ASUS TUF GAMING X670E-PLUS WIFI a good choice? (117)
- Last game you purchased? (521)
- Build Upgrade (8)
Popular Reviews
- NVIDIA SFF-Ready System Build & Benchmark Review - Build Small, Play Big
- ARCTIC P12 PWM PST 120 mm Fan Review
- AMD Ryzen 7 9800X3D Review - The Best Gaming Processor
- Quick Look: Shanling M1 Plus Portable Audio Player
- APNX V1-W Review
- Quick Look: MOONDROP Quark2 Type-C In-Ear Monitors
- Upcoming Hardware Launches 2024 (Updated Nov 2024)
- NVIDIA App v1.0 Review
- DDR5 Memory Performance Scaling with AMD Zen 5
- Intel Core Ultra 9 285K Review
Controversial News Posts
- AMD Falling Behind: Radeon dGPUs Absent from Steam's Top 20 (222)
- AMD Ryzen 7 9800X3D Stocks Vaporized in Retail, Being Scalped (152)
- AMD Introduces Next-Generation AMD Ryzen 7 9800X3D Processor, $479, Nov 7 (124)
- Apple and Samsung in the Fray to Acquire Intel: Rumor (123)
- AMD Ryzen 7 9800X3D Comes with 120W TDP, 5.20 GHz Boost, All Specs Leaked (120)
- Microsoft Offers $30 Windows 10 Security Extension for Home Users (118)
- AMD Ryzen 7 9800X3D Has the CCD on Top of the 3D V-cache Die, Not Under it (110)
- TechPowerUp is Hiring a Power Supply (PSU) Reviewer (106)