Based on internal testing by Intel , the forthcoming dual-core Intel Itanium processor codenamed “Montecito” demonstrated a 60 percent performance increase over a previous technical computing benchmark posted by a four-way RISC-based system. The results can be found here.
Using the LINPACK benchmark, which measures floating point performance, a four-processor dual-core Itanium processor exceeded 45 GFLOPs (gigaflops), a measure of computer speed where a gigaflop is 1 billion floating-point operations per second. The previous record was 27.5 GFLOPs.1
“This performance result gives a peek into the advantage Montecito is expected to have over previous generations of the Itanium architecture for high-performance computing applications,” said Phil Brace, general manager of Intel’s Server Platform Group. “Three years ago we showed a four-processor Itanium-based system at 11.43 GFLOPs, and two years ago we hit 22.7 GFLOPs.2 We are approaching the ability to reach a TeraFlop in as few as a 20-server system cluster and helping to dramatically increase the affordability to the scientific community.”
Platforms using Montecito are expected to deliver up to twice the performance, up to three times the system bandwidth, and over 2 1/2 times as much on-die cache as the current generation of Itanium processors. While boosting performance, Montecito is expected to also deliver more than 20 percent lower power than previous generations of Itanium processors through new technologies for power management. Montecito will also have Intel Hyper-Threading technology, enabling four times the threads as the current generation.