The Cray X1 is a non-uniform memory access, vector processor supercomputer manufactured and sold by Cray Inc. since 2003. The X1 is often described as the unification of the Cray T90, Cray SV1, and Cray T3E architectures into a single machine.

The Cray X1E supercomputer and its predecessor, the Cray X1™ supercomputer, are the first vector systems designed to scale to thousands of processors in a single system image.

Exploiting fine-grain parallelism with vectorization is #1 priority on X1E! Multistreaming takes additional advantage of loop-level parallelism. Additional wrinkle: When to stream vs. vectorize?

This paper helps the reader understand the characteristics of the Cray X1 vector supercomputer system, and provides hints and information to enable the reader to port codes to the system. It

Cray_SX5 Sales The Cray SX5 and SX6 were a product of NEC corporation that was resold by Cray. The Cray XD1 was a product created as a result of the acquisition of OctigaBay company. The Tera MTA-1 and MTA-2 were projects designed and created by Tera computers. When the Cray division of SGI was bought by Tera and renamed Cray Corporation.

The Cray X1 product is a major milestone en route to Cray's goal of delivering, by 2010, the world's first supercomputer able to sustain petaflop speeds (10E15 calculations/second) on a variety of challenging applications. Problems needing this extreme performance include drug discovery, energy and transportation modeling,

Cray X1 Overview, Copyright 2002-3, Cray Inc. 16 Address Translation • High translation bandwidth: scalar + four vector translations per cycle per P • Source translation using 256 entry TLBs with support for multiple page sizes • Remote (hierarchical) translation: – allows each node to manage its own memory (eases memory mgmt.)

custom benchmarks permit the unique architectural features of the Cray X1 (distributed vector units, and cache and global memory) to be tested with respect to the target applications. In the architectural-component evaluation we assess the following:

Each processor board an X1E contains 4 CPUs that can deliver a peak rate of 4 floating-point operations per cycle, amounting to a theoretical peak performance of 4.5 Gflop/s per CPU.

Jul 8, 2008 · When you first walk into the lab, you see a pretty impressive looking machine known as the Cray X1E. This is the world's 175th most powerful computer, clocking 18 teraflops, or 18 trillion...