Nvidia announced a personal supercomputer to run number crunching computing task. This computer is up to 250 times faster than standard PCs and workstations. The NVIDIA Tesla Personal Supercomputer is based on NVIDIA CUDA parallel computing architecture and powered by up to 960 parallel processing cores.
It is built by various computer vendors. It is meant to be a demonstration of the capabilities of Nvidia’s Tesla GPGPU brand; it utilizes NVIDIA’s CUDA parallel computing architecture. Priced around US $10,000, these PCs may look innocent, but they pack serious horsepower – a theoretical maximum of 4 TFlops of single-precision processing.
Nvidia Tesla personal supercomputer operating system support
The following operating systems are supported by this computer including Linux 32-bit and 64-bit:
- Microsoft Windows XP Professional X64 Edition
- Redhat Enterprise Linux 5.2 x86_64
- CentOS 5.2 x86_64
- Fedora 12
- RHEL 5.4 Desktop
- Ubuntu 9.10 Desktop
- RHEL 4.8 Desktop (64-bit only)
- RHEL 6
- OpenSUSE 11.2
- SLED 11
Nvidia Tesla Supercomputer Specs
- Tesla GPUs – 4
- Streaming Processor Cores: 960 (240 per GPU)
- Frequency of Processor Cores: 1.296 GHz
- Floating Point Precision: IEEE 754 single & double precision floating point
- Floating Point Performance: 3.7 Teraflops SP / 312 Gigaflops DP
- Total Dedicated GPU Memory: 16GB @ 800 MHz
- Memory Interface: 512-bit GDDR3
- Memory Bandwidth: 102 GB/sec peak
- Max Power Consumption: 820W typical
- GPU Interface: (4) PCI Express Gen2 x8
- Front End: AMD Phenom X4 9950, NVIDIA 780a SLI Chipset, GB DDR2-800 Memory,Serial ATA Hard Disk Interface,1 TB 7200RPM SATA HDD,20x DVD +/- RW etc
Plenty of research, educational, government organizations, and medium size business can take advantage of new personal super computer. You can also use popular apps like Mathematica, LabView, ANSYS Mechanical, and more.
More information about NVIDIA Tesla Personal Supercomputer available on the official NVIDIA site.