Earth simulator is the fastest supercomputer in the world. Nec had first built this japanese machine. Earth simulator uses parallel vector architecture to achieve a peak performance of 40 f flops. This system configured in 640 nodes of 8 vector processors each connected together by crossbar switch. Each node has a shared memory of 16 gb (total 10 tb). This japanese machine was built to analyze climate change, including global warming, as well as weather and earthquake patterns. Earth simulator has the power to create a ?virtual planet earth? using its large processing capability. The vector processor used in this is fabricated in a single chip with 0.15-micron cmos technology. You cannot wait for results in weather predictions. ?we actually can predict the weather very accurately; the problem is it takes a week of computation to predict tomorrow?s weather?. This delay may cause considerable damage to human lives and economy. He earth simulator will answer the above problem. Using its high computational power it can predict weather fast and accurately. Within five years, scientists expect earth simulator?s advanced modeling and simulation capabilities to bear fruit. Thanks to the new supercomputer, scientists expect to find powerful new ways to deal with anomalous events such as e1 nino, global warming, and long-term changes in the earth?s crust and interior. According to jackdongorra ?in some sense we have a computer on our hands?, referring to the time when the u.s. Was surprised by sputnik, the world?s first satellite.
parallel vector architecture opens up a new way to develop future supercomputers. This technology has the advantages of both parallel and vector processing. We can connect a large number of vector modules to achieve more performance..
The Earth Simulator (ES) is a distributed memory parallel system which consists of 640
processor nodes connected by a single stage full crossbar network. Each processor node is a shared memory system composed of eight vector processors and a memory system of 16 GB. The total peak performance and main memory capacity are 40 Tﬂops and 10 TB, respectively.Its development was initiated in 1997 and the latest 0.15 m CMOS LSI technology was adopted in realizing a one-chip vector processor. The development has been successfully completed in February, 2002, and a remarkable sustained performance of 35.86 Tﬂops with 87.5% of the peak performance in the Linpack benchmark is obtained.
It is widely recognized that global phenomena such as global warming which affect social and economic activities of human beings should be analyzed. However, present computer capabilities are insufﬁcient to carry out high resolution simulations for global change and therefore the complicated phenomena cannot be pursued.
The Earth Simulator project had been initiated for aiming at understanding and elucidation of the global change as precisely as possible, and an ultra high-speed supercomputer called the Earth Simulator (ES) had been started to develop as a joint project by the National Space Development Agency of Japan (NASDA), the Japan Atomic Energy Research Institute (JAERI), and the Japan Marine Science and Technology Center (JAMSTEC). ES has been completed to fabricate and
installed at Yokohama Institute for Earth Sciences (YES/JAMSTEC) in the end of February 2002.
The Earth Simulator, which was developed, as a national project, by three governmental agencies, the National Space Development Agency of Japan (NASDA)*1, the Japan Atomic Energy Research Institute (JAERI), and Japan Marine Science and Technology Center (JAMSTEC)*2. The ES is housed in the Earth Simulator Building (approx; 50m x 65m x 17m). The upgrade of the Earth Simulator has been completed in March 2009. The renewed system(ES2) 160 nodes of NEC's SX-9E.
*1 Japan Aerospace Exploration Agency (JAXA)
*2 Japan Agency for Marine-Earth Science and Technology (JAMSTEC)
The ES is a highly parallel vector supercomputer system of the distributed-memory type, and consisted of 640 processor nodes (PNs) connected by 640x640 single-stage crossbar switches. Each PN is a system with a shared memory, consisting of 8 vector-type arithmetic processors (APs), a 16-GB main memory system (MS), a remote access control unit (RCU), and an I/O processor. The peak performance of each AP is 8Gflops. The ES as a whole thus consists of 5120 APs with 10 TB of main memory and the theoretical performance of 40Tflop
– Construction of Arithmetic Processor (AP)
Each AP consists of a 4-way super-scalar unit (SU), a vector unit (VU), and main memory access control unit on a single LSI chip. The AP operates at a clock frequency of 500MHz with some circuits operating at 1GHz. Each SU is a super-scalar processor with 64KB instruction caches, 64KB data caches, and 128 general-purpose scalar registers. Branch prediction, data prefetching and out-of-order instruction execution are all employed. Each VU has 72 vector registers, each of which has 256 vector elements, along with 8 sets of six different types of vector pipelines: addition/shifting, multiplication, division, logical operations, masking, and load/store. The same type of vector pipelines works together by a single vector instruction and pipelines of different types can operate concurrently. The VU and SU support the IEEE 754 floating-point data format.
1 Chip LSI : 8Gflops
• 5185 pins
• Clock Cycle: 500MHz(1GHz)
• Power Consumption0.15µm CMOS
• 8Layers copper interconnection
• 20.79mm x 20.79mm
• 60 million transistors
• : 140W (Typ.)