HomeAboutPoliciesContact Store Categories
- Automation
- Conference Equipment
- Desktop Components
- Desktops and Workstations
- Electrical
- Electronics
- Hard Drives
- KVM
- Laptop Accessories
- Laptop Components
- Laptops
- Memory
- Network Equipment
- Point of Sale (POS)
- Power Backup and Management
- Printer Parts
- Printers
- Server Parts
- Servers
- Solid State Drives
- Storage Equipment
- Surveillance Equipment
- Telecom Equipment
- Telephone Parts
- Testing Equipment
- Vintage
Store Newsletter
Add TechyParts to your Favorites to receive our email newsletters about new items & special promotions.
SIGN UP Lot of 10x NVIDIA
Tesla Referral K40m 12GB GDDR5 Passive CUDA GPU PCI-e Accelerator Card Product Description Lot of 10x NVIDIA
Tesla Referral K40m 12GB GDDR5 Passive CUDA GPU PCI-e 3.0 x16 Accelerator Card without Mounting Bracket
Condition: Clean, tested pull - Guaranteed 100% working!
NOTE: This not a video card. It does not have any video output. This is GPU accelerator card and it has a passive airflow heatsink which requires a proper cooling solution and adequate airflowfor proper operation.Please note this card does not come with a mounting bracket.
30-Day Warranty!
Manufacturer's description and specifications:
The Tesla Referral K40 GPU Accelerator with passive cooling from Nvidia is a GPU with no video outputs designed exclusively for providing acceleration to assist computational intensive tasks such as transcoding video, rendering 3D models, cryptography, and analysis of complex data sets. It features a 745 MHz core which can be boosted (overclocked) by the end user up to 875 MHz, and has 2880 Kepler generation CUDA cores (stream processors) which allow it to perform hundreds of computations simultaneously. To ensure data moves to and from the processors as efficiently as possible, the card features 12 GB of GDDR5 RAM over a 384-bit memory interface. A 750 MHz native memory clock speed gets effectively boosted to 3 GHz thanks to the fact GDDR5 type memory moves data at four words per cycle. Altogether this yields a memory bandwidth of 288 GB/s.
4.3 TFLOPs Single Precision Performance
The card boasts a double precision (64-bit length) benchmark of 1.43 TFLOPs (trillion floating point operations per second), and a single precision (32-bit length) benchmark of 4.3 TFLOPs. Floating point math is commonly found in applications such as 3D modeling as well as certain forms of data analytics
Supports CUDA and Other APIs
APIs provide the software interface that exposes applications to the compute power of the GPU for processing-intensive tasks, including transcoding video, cryptography, analysis of complex data sets, rendering 3D environments, CAD modeling, and more
SMX (Streaming Multiprocessor)
Redesigned architecture with more cores, delivers up to 3x more performance per watt than the SM technology in previous-generation Nvidia Fermi GPUs
Dynamic Parallelism
Enables GPU threads to automatically spawn new threads. By adapting to the data without going back to the CPU, this greatly simplifies parallel programming
Hyper-Q
Allows multiple CPU cores to simultaneously use the CUDA cores on a single Kepler GPU. This dramatically increases GPU utilization while reducing CPU idle times
Multi-Language SDKs
For software developers, SDKs are available for OpenACC, CUDA, C, C++ and Fortran
ECC Error Correction
Protects the data integrity from interference caused by cosmic background radiation
System Monitory Features
Integrates the GPU subsystem with the host system's monitoring and management capabilities, such as IPMI or OEM-proprietary tools. IT staff can now manage the GPU processors in the computing system using widely used cluster/grid management solutions
L1 and L2 Caches
Accelerates algorithms such as physics solvers, ray tracing, and sparse matrix multiplication where data addresses are not known beforehand
Tesla Referral GPUBoost
End-user can convert power headroom to higher clocks and achieve even greater acceleration for various computationally-intensive workloads on Tesla Referral K40
Quad Data Rate (QDR) GDDR5 RAM
Because GDDR5 RAM can transfer up to four words per cycle, as opposed to one word per cycle with traditional RAM, the effective data rate is quadrupled, allowing this card to process data transactions as quickly as if it had a 3.0 GHz memory clock speed
PCI Express 3.0 x16 Support
Provides twice the bandwidth of PCI Express 2.0; for example, an x8 PCI Express 3.0 slot has the same bandwidth as a x16 PCI 2.0 slot. In addition, the card remains backward-compatible with motherboards using earlier generations of PCI Express.
GPU GPU Model NVIDIA
Tesla Referral K40 Stream Processors 2880 CUDA Cores Boost Clock Speed 875 MHz Base Clock Speed 745 MHz Floating Point Performance Single Precision Performance: 4.29 TFLOPS
Double Precision Performance: 1.43 GFLOPS Interface PCI Express 3.0 x16 Memory Memory Speed 3 GHz (Effective) Memory Configuration 12 GB Memory Interface GDDR5 Memory Interface Width 384-Bit Memory Bandwidth 288 GB/s Power Requirements Max Power Consumption 235 W PCI Power Connectors 1 x6-Pin
1 x8-Pin Dimensions Height 4.4" / 11.1cm Length 10.5" / 26.7cm Width Dual-Slot Payment
We only accept PayPal as a method of payment. All credit card payments must be made through PayPal. We reserve the right to deny any payment that we consider fraudulent or suspicious.
Payment must be received within 4 days of the date of purchase. Otherwise, if no contact has been established, the listing will be void and non-paying buyer (NPB) reported to .
Shipping
All packages will be shipped the following business day after the payment is cleared via FedEx ground, FedEx SmartPost, USPS Parcel Post or USPS First Class with tracking information unless expedited or international shipping is requested.
Please note, all UPS quoted rates will be substituted for equivalent FedEx service unless requested otherwise.
For listings listed with free shipping option:We do not offer free shipping to Alaska, Hawaii and US territories. Buyers from Alaska, Hawaii and US territories please contact us for a shipping quote or choose USPS priority mail instead of the free shipping option.
Any merchandise sent to another country may be subject to duty under the customs regulations of that country. We do not maintain or provide information concerning the assessment of customs duty. Custom duties, carrier customs clearance brokerage fees and import taxes may apply to international buyers and are not included in shipping and handling charges you pay to us.
Returns
All sales are final.
All listed items are sold with a DOA warranty. This means if the item is dead on arrival, we will replace the item(s) or process a refund at our discretion. Unless otherwise noted, DOA warranty usually extends 30 days from the date you receive the product unless otherwise noted in our listing.
About Us
We are an established seller with 20,000+ positive responses. We buy and sells networking equipment, servers, workstations, laptops and and parts thereof. Storage solutions, power and testing equipment. We offer lowest prices on hard to find parts! Asset recovery and recycling services.
Contact Us
Open: Mo-Fri 10:00am - 07:00pm CST
Due to new policies we are not allowed to list our contact information, so if you have a question please use messaging system to contact us. At the bottom of the listing there is a "Ask a question" link. If it doesn't work for you, our contact information is published on the world wide web. Please use you imagination and investigative skills. The truth is out there! Home • About • Policies • Contact Us Copyright © 2019 TechyParts, LLC. All rights reserved. | Template Design by OCDesignsOnline
