Yitian Настольные Суперкомпьютеры

l Collaborative computing acceleration architecture Creatively introduce GPU computing unit, which outperforms traditional single computing unit. It adopts the collaboration of the latest Nehalem processing core and NVIDIA Tesla accelerating computation. CPU and GPU fulfill their responsibilities respectively. CPU is competent for logical choice, judgment and jump and I/O communications, while GPU is competent for intensive, parallel computation. This makes the computing resource reasonably assigned and the computing power adequately released. Thus the calculated performance improves sharply. l Large-scale parallel computing processing core Compared with multi-core CPU providing less threads working together, GPU provides thousands of threads working concurrently. This enables the system to process more information flow. At present, Tesla processing unit is capable of supporting 240 processing cores, with a peak processing speed of 1 Tricro floating point calculation per second. By collaborative expandable architecture, the number of GPU can be expanded depending on customers’ requirement. Generally, the acceleration ratio of applications is between 1 to 2 magnitudes. l High-speed I/O switch between processing units Each device has the dedicated connection of its own and GPU does not need to request system bus for bandwidth. Further, the data transmission efficiency can be increased to a high value. Inspur Yitian supercomputer adopts PCI-E 2.0 X16 with a bandwidth of 16GB/s. Adopt the latest Intel QPI technology l To better the collaborative effect of CPU and GPU, Inspur Yitian supercomputer adopts Intel QPI (Quick Path Interconnect) technology, which provides a transmission rate of 6.4GT/s and makes the communication faster. Excellent programming environment CUDA (Compute Unified Device Architecture) common parallel computing architecture is capable of solving complicated computation. It consists of CUDA instruction set architecture (ISA) and parallel computation engine inside GPU. Developers may write C programs for CUDA architecture. Since C is one of the most popular advanced programming languages, the C-coded programs can operate effectively in processors compatible with CUDA. In the future, it will support other languages including FORTRAN and C++. l To better the collaborative effect of CPU and GPU, Inspur Yitian supercomputer adopts Intel QPI (Quick Path Interconnect) technology, which provides a transmission rate of 6.4GT/s and makes the communication faster.Excellent programming environment CUDA (Compute Unified Device Architecture) common parallel computing architecture is capable of solving complicated computation. It consists of CUDA instruction set architecture (ISA) and parallel computation engine inside GPU. Developers may write C programs for CUDA architecture. Since C is one of the most popular advanced programming languages, the C-coded programs can operate effectively in processors compatible with CUDA. In the future, it will support other languages including FORTRAN and C++. Yitian NF5588Yitian NP3588ProcessorIntel Xeon 2-way, 4-core 5500/5600 series processor Intel i7, 2.66 GHz/2.93 GHz/3.2 GHz Computing unitNVDIA Tesla C1060,computing speed up to 4 trillion NVDIA Tesla C1060,computing speed up to 4 trillion System busQuickPath Interconnect,up to 6.4GT/s QuickPath Interconnect,up to 6.4GT/s Memory12 DIMM , support DDR3,Support the three-channel inter-leaving, support the maximum memory capacity of 48GB 6 DIMM , support DDR3,Support the three-channel inter-leaving, support the maximum memory capacity of 24GB HDD controllerIntegrated SATA controller, support SAS controller Integrated SATA controller RAIDHost raid 1,0,10,support raid card Host raid 1,0,10,support raid card StorageSupport 8 pieces 3.5 inch SATA/SAS hot-swap hard drive Support 2 pieces large capacity SATA/SAS hot-swap hard drive I/O expansion slot4 PCI-E2.0 x16,2 PCI-E2.0 x4(x16 slot),1 PCI-E1.0 x4(x8 slot),2 PCI 33MHz 3 PCI-E2.0 x16 Network controllerIntegrated double Gigabyte network card Integrated double Gigabyte network card Power supply1400W high efficiency redundant power supply 1000W high efficiency power supply Video cardIntegrated Matrox G200eW,optional FX370LP /FX1800/ FX3800/ FX5800 FX370LP CD-romOptional USB DVD-rom Optional USB DVD-rom Chassis452×178×746 mm Tower and rack conversion 433×220×607mm Tower chassis OS supportedSupport Windows xp,Redhat Linux AS 5.0/5.2/5.3 RedHat Linux/Microsoft WinXP/Vista Programming environmentCUDA CUDA CDInspur Yitian CD can help users to easily build parallel CUDA development environment; guide users to develop their own CUDA programs; this CD contains video tutorials and documentation tutorial. Working temperature5°C 35°C 5°C 35°C Power supply200-240V 200-240V International certificationISO9001 ISO14001 ISO9001 ISO14001