Tesla K80 Boost Up extended

14.12.2015
von Webadmin
TESLA K80 BOOST UP After the big success of K80 in deep learning research, NVIDIA® extended the “Boost Up” – program period! Use the chance and order now, with a discount!

Get your chance for upgrading!

After the big success of K80 in deep learning research, NVIDIA® extended the “Boost Up” – program period! Use the chance and order now, with a discount!


Three Reasons to Depoly Tesla K80 in Your Data Center

The path forward is parallel. Traditional CPUs no longer deliver generational performance gains like they used to, and HPC experts agree that only powerful accelerators like GPUs will deliver the performance required to drive future scientific discoveries.


The NVIDIA® Tesla® K80 is the world’s most powerful accelerator built for Machine Learning and HPC applications, offering three powerful reasons to add them to your data center.

Reason 1:
Top Applications are GPU Accelerated


Many of the compute-intensive applications running in your Machine Learning and HPC system are GPU-accelerated. In fact, an independent study by Intersect360 Research shows that 70% of the most popular HPC applications have built-in support for GPUs.


For example, chemistry applications consume a lot of compute cycles in a typical data center. According to the study, most computational chemistry applications offer support for GPUs today. The NVIDIA Tesla K80 GPU accelerator can deliver a significant performance boost for these applications.

Reason 2:
Replace up to Eight CPU Servers with One Tesla K80-Powered Server


While time to discoveries is critical, compute resources are often scarce. This limits the scale of science that researchers can achieve. The Tesla K80 redefines what’s possible for scientists and researchers. For Many GPU-optimized applications, a single K80 server can deliver higher throughput than eight dual-socket CPU servers.


For example, running a popular computational chemistry application - HOOMD-Blue a single server with two Tesla K80 accelerators delivers 1.7x faster performance compared to 8 servers with dual-socket Haswell CPUs and 3.4x faster performance than four servers with dual socket Haswell CPUs.

Reason 3:
Higher Throughput Leads to More Discoveries


Data center managers all face the same challenge: how to meet the demand for computer resources that often exceed cycles available in the system. Tesla K80 can dramatically boost the throughput of your data center, completing more compute jobs every day. When your key applications are accelerated by a third of the systems nodes having Tesla K80 accelerators, the data center would experience more than two-fold increase in overall throughput. Accelerated computing enables researchers to tackle problems that simply would not be possible with CPU-based approaches.


Start with a New System and save money on your Tesla Servers and Cards


To get started, we recommend our 1U GPU Server with up to 4x NVIDIA® Tesla® K80:


sysGen/SUPERMICRO Server SYS-1028GQ-TR
  1. Dual socket R3 (LGA 2011) supports Intel® Xeon® processor E5-2600 v3 family; QPI up to 9.6GT/s
  2. Up to 2TB ECC, up to DDR4 2400MHz; 16x DIMM slots
  3. 4x PCI-E 3.0 x16 (4 GPU cards opt.) and 2x PCI-E 3.0 x8 (in x16) LP slots
  4. Intel i350 Dual port GbE LAN
  5. System management: Built-in Server management tool (IPMI 2.0, KVM/media over LAN)
    with dedicated LAN port
  6. 2x 2.5" Hot-swap drive bays, 2x 2.5" internal drive bays
  7. 9x 4cm heavy duty counter-rotating fans w/ optimal fan speed control
  8. 2000W Redundant Power Supplies Platinum Level (94%+)

If you have further questions, don't hesitate to contact our support team at 0421-40966-0 or info@sysgen.de


sysGen Logo





Your sysGen Team