Scale your science with NVIDIA® Tesla™ GPU SimCluster, an off-the-shelf and ready-to-deploy cluster solution with both hardware and software. Available in configurations that deliver 10 to 42 TeraFlops of HPC performance, it delivers the easiest way to buy, use and manage GPU-based research cluster. With the Tesla GPU SimCluster, academic research departments can take GPU-accelerated applications from workstation to multi-node cluster, speeding up research and discovery.
“Availability of many computationally efficient GPU nodes locally has allowed us to approach drug design in a new way, giving fresh insights into disease mechanisms.” Michael Kuiper, Computational Scientist at VPAC.
10 TFlops1
GPU: 8 Tesla M2090 GPUs
CPU: 8 Intel Westmere X5650 2.66GHz (6-core)
Nodes: 4 SuperMicro SuperServer 6016GT GPU Computing Nodes
Memory: 24GB per node
Networking: Infiniband with 18 port IB switch
Storage: 1TB per node
IPMI: 24 port 1GB Ethernet Switch
Master Node: No separate master node
Rack Size: 14u
$51,9992
20 TFlops1
GPU: 16 Tesla M2090 GPUs
CPU: 16 Intel Westmere X5650 2.66GHz (6-core)
Nodes: 8 SuperMicro SuperServer 6016GT GPU Computing Nodes
Memory: 24GB per node
Networking: Infiniband with 18 port IB switch
Storage: 1TB per node
IPMI: 24 port 1GB Ethernet Switch
Master Node: SuperMicro SuperServer 6016T-NTF3
Rack Size: 14u
$96,9992
42 TFlops1
GPU: 32 Tesla M2090 GPUs
CPU: 32 Intel Westmere X5650 2.66GHz (6-core)
Nodes: 16 SuperMicro SuperServer 6016GT GPU Computing Nodes
Memory: 48GB per node
Networking: Infiniband with 18 port IB switch
Storage: 2TB per node
IPMI: 24 port 1GB Ethernet Switch
Master Node: SuperMicro SuperServer 6016T-NTF3
$189,9992