510.226.7366 | sales@exxactcorp.com |

Workstation Graphics and HPC Solutions  

Exxact Corp - Professional Graphics, Consumer Graphics, GPU Computing, Visual Computing, Other Products

NVIDIA Tesla GPU Clusters - Large Cluster Scaling for GPU-Accelerated Applications
Large clusters around the world are increasingly deploying GPUs to accelerate their workload. In the Top500 list, from June 2011 to June 2012, number of GPU-accelerated systems grew by over 400%. Many GPU-accelerated applications are scaling well as developers work on extracting more parallelism by allocating more parallel work within a node and use MPI to distribute GPU workloads.
Exxact GPU clusters deliver supercomputing architecture that provides both extreme scalability and sustained performance. The flexibility of the Exxact clustering platform ensures that users can configure the GPU machine to meet their specific requirements, and also remain confident they can upgrade and enhance their system to address the demands of the future.
NVIDIA Tesla Preferred Partner
As a leading Tesla Preferred Partner with NVIDIA, Exxact Corporation works closely with the NVIDIA Tesla GPU team to ensure seamless factory development and support. We pride ourselves on providing value-added service standards unmatched by our competitors.
  Quantum TXR111-1000R
3x NVIDIA Tesla GPUs
• 2x Intel Xeon processor Scalable family
• 1U Server, Up to 1TB DDR4
Quantum TXR110-0768R
4x NVIDIA Tesla GPUs
• 2x Intel Xeon processor Scalable family
• 1U Server, Up to 1TB DDR4
Quantum TXR230-0512R
4x NVIDIA Tesla GPUs
• 2x Intel Xeon E5-2600 v3/ v4 CPUs
• 2U Server, Up to 512GB DDR4
Quantum TXR216-1024R
4x NVIDIA Tesla GPUs
• 2x Intel Xeon processor Scalable family
• 2U Server, Up to 1TB DDR4
Quantum TXR410-1024R
4x NVIDIA Tesla GPUs
• 2x Intel Xeon processor Scalable family
• 4U Server, Up to 512GB DDR3
Quantum TXR430-0768R
8x NVIDIA Tesla GPUs
• 2x Intel Xeon E5-2600 v3/ v4 CPUs
• 4U Server, Up to 768GB DDR4
Intel® Omni-Path Card / Infiniband Card
• Single or Dual-Port
• 100GB
High Performance Computing - Supercomputing with NVIDIA Tesla GPUs
Based on the Kepler compute architecture, which is 3 times higher performance per watt of the previous “Fermi” compute architecture, the Tesla Kepler GPU Computing Accelerators make hybrid computing dramatically easier, and applicable to a broader set of computing applications.
Available NVIDIA Kepler-Based Tesla GPUs for cluster configurations:
  Number of GPUs Number of CUDA Cores Memory Size (GDDR5) Memory Bandwidth (ECC off) Peak Double precision Floating Point Peak Single Precision Floating Point
NVIDIA Tesla P100 for SXM2 1 x GP100 3584 16GB 720 GBytes/sec 5.3 teraflops 10.6 teraflops
NVIDIA Tesla P100 for PCIe 1 x GP100 3584 12GB or 16GB 540 or 720 GBytes/sec 4.7 teraflops 9.3 teraflops
NVIDIA Tesla P40 1 x GP102 3840 24GB 346 GBytes/sec 47 TOPs of INT8 performance 12 teraflops
NVIDIA Tesla P4 1 x GM104 2560 8GB 192 GBytes/sec 22 TOPs of INT8 performance 5.5 teraflops
NVIDIA Tesla M60 1 x GM205 4096 16GB 320 GBytes/sec 0.3 teraflops 9.7 teraflops
NVIDIA Tesla M40 1 x GM200 3072 12GB / 24GB 288 GBytes/sec 0.21 teraflops 7.0 teraflops
NVIDIA Tesla M4 1 x GM206 1024 4GB 88 GBytes/sec 0.07 teraflops 2.20 teraflops
NVIDIA Tesla K80 2 x GK210 4992 24GB 480 GBytes/sec 1.87 teraflops 5.60 teraflops
NVIDIA Tesla K40 1 x GK110B 2800 12GB 288 GBytes/sec 1.43 teraflops 4.29 teraflops
NVIDIA Tesla K20X 1 x GK110 2688 6GB 250 GBytes/sec 1.31 teraflops 3.95 teraflops
NVIDIA Tesla K20 1 x GK110 2496 5GB 208 GBytes/sec 1.17 teraflops 3.52 teraflops
NVIDIA Tesla K10 2 x GK104s 2x 1536 8GB 320 GBytes/sec 0.19 teraflops 3.95 teraflops
Exxact HPC Appliances
Cluster Management System
Bright Cluster Manager® includes powerful GPU management and monitoring capability that leverages functionality in NVIDIA®'s Tesla™ GPUs to take maximum control of the GPUs and gain insight in their status and activity over time. Bright also includes the necessary CUDA and OpenCL libraries.
Network Switching
NVIDIA GPUDirect technology provides the capability for direct communication between the NVIDIA GPU and the Mellanox ConnectX VPI adapter family through the host memory with zero copy and low latency RDMA (Remote Direct Memory Access). GPUDirect with Mellanox InfiniBand adapters accelerates local GPU to remote GPU communication by 30%, resulting in higher application performance.
Chelsio is delivering hardware and software solutions including Unified Wire Ethernet network adapter cards, unified storage software, high performance storage gateways, unified management software, bypass cards, and other solutions focused on specialized applications.
Smart Power
Intel® Cluster Ready
Intel® Cluster Ready is an industry-standard cluster architecture that makes high-performance clusters simpler to choose, deploy, and maintain. Exxact also offers specialized CPU clusters based on Intel Cluster Ready architecture to verify cluster components continuously working together throughout the cluster lifecycle.