(HPCWire) Inside Quantum Technology shares the latest announcement from Fujitsu explaining its development of the world’s fastest quantum computer simulator capable of handling 36 qubit quantum circuits on a cluster system.
Fujitsu has announced it successfully developed the world’s fastest quantum computer simulator capable of handling 36 qubit quantum circuits on a cluster system featuring Fujitsu’s “FUJITSU Supercomputer PRIMEHPC FX 700” (“PRIMEHPC FX 700”)(1), which is equipped with the same A64FX CPU(2) that powers the world’s fastest supercomputer, Fugaku.
The newly developed quantum simulator can execute the quantum simulator software “Qulacs”(3) in parallel at high speed, achieving approximately double the performance of other significant quantum simulators(4) in 36 qubit quantum operations. Fujitsu’s new quantum simulator will serve as an important bridge towards the development of quantum computing applications that are expected to be put to practical use in the years ahead.Based on this breakthrough, from April 1, 2022, Fujitsu and Fujifilm Corporation(5) (hereinafter Fujifilm) will start joint research on quantum computing applications in the field of materials science.
Moving forward, Fujitsu will accelerate its efforts to develop quantum computers with the aim of developing a 40 qubit simulator by September 2022 and conduct joint research and development of quantum applications with customers in fields including finance and drug discovery.
The PRIMEHPC FX 700 is equipped with the same A64FX CPU that powers the supercomputer Fugaku and can perform theoretical peak performance of 3.072 teraflops (TFLOPS) in double-precision floating-point format calculations. It further features 32 GB of memory with a high bandwidth of 1,024 gigabytes (GB) per second, and speeds of 12.5 GB per second by connecting nodes via InfiniBand(6).
The new quantum simulator utilizes “Qulacs,” one of the world’s fastest quantum simulator software developed by Osaka University and QunaSys Corporation, and the performance of memory bandwidth was maximized by executing multiple calculations simultaneously using SVE (Scalable Vector Extension) instructions(9) when ported to the A64FX.