Home NVIDIA Tesla K40st

NVIDIA Tesla K40st

This is a GPU manufactured with TSMC 28nm process, based on Nvidia Kepler architecture and released on Nov 2013. It features 7.08 billion transistors, 2880 CUDA cores and 12GB GDDR5 memory, with 1536KB L2 cache, theoretical performance of 3.312TFLOPS, with total power consumption of 245W.

Graphics Card

[Report Issues]
Release Date
Nov 2013
Generation
Tesla
Type
Professional
Bus Interface
PCIe 3.0 x16

Clock Speeds

[Report Issues]
Memory Clock
1502MHz

Memory

[Report Issues]
Memory Size
12GB
Memory Type
GDDR5
Memory Bus
384bit
Bandwidth
288.4 GB/s

Render Config

[Report Issues]
Shading Units
2880
TMUs
240
ROPs
48
L1 Cache
16 KB (per SMX)
L2 Cache
1536KB

Theoretical Performance

[Report Issues]
Pixel Rate
34.50 GPixel/s
Texture Rate
138.0 GTexel/s
FP32 (float)
3.312 TFLOPS
FP64 (double)
1104 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GK110B
Architecture
Kepler
Foundry
TSMC
Process Size
28 nm
Transistors
7,080 million
Die Size
561mm²

Board Design

[Report Issues]
TDP
245W
Suggested PSU
550W
Outputs
No outputs

Graphics Features

[Report Issues]
DirectX
12 (11_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.1
CUDA
3.5
Shader Model
5.1

Rankings

[Report Issues]
FP32 (float)
3.318 TFLOPS
3.315 TFLOPS
3.315 TFLOPS
NVIDIA Tesla K40st 12 GB GDDR5
3.312 TFLOPS
3.297 TFLOPS
AMD FirePro W7100 8 GB GDDR5
3.297 TFLOPS
3.29 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy