Russian supercomputing will use self-developed CPU: 28nm 8-core ARM
- An American company made 0.7nm chips: EUV lithography machines can’t do it
- CVE-2007-4559 Python vulnerability ignored for 15 years puts 350,000 projects at risk of code execution
- RISC-V only takes 12 years to achieve the milestone of 10 billion cores
- 14000 cores + 450W: RTX 4080 graphics card perfectly replaces the RTX 3080
- Big upgrade: The difference between Bluetooth 5.0 and 5.2
- Geeks Disappointed that RTX 4080/4090 doesn’t come with PCIe 5.0
- What are advantages and disadvantages of different load balancing?
Abandoning AMD/Intel: Russian supercomputing will use self-developed CPU: 28nm 8-core ARM
According to British media reports, Russia will develop its own high-performance supercomputing system RSK Tornado , instead of using AMD or Intel ‘s x86 processors, using ARM processors developed by local companies .
According to reports, this platform will be developed by the large system integrator RSC Group , which said that RSK Tornado can use two different processor architectures equally, switch from x86 to ARM is not affected, and work with the storage system developed in Russia, A rack can have 104 servers installed.
The core of this supercomputing is the ARM processor Elbrus series developed by a Russian company. Although the current report does not mention the details, it was reported two years ago. This is an ARM processor developed by the Russian MSCT company .
The Elbrus processor is the fourth generation of MCST 64 -bit ARM architecture, with a maximum of 8 cores, a frequency of 1.3GHz , equipped with 4MB L2 cache, 16MB L3 cache, 28nm process manufacturing, and floating-point performance of 250GFLOPS .
However , the performance of the Elbrus processor is a problem due to the long development time. The test results were announced before . It took 2 minutes and 52 seconds to run the rendering RyzenGraphic_27 model in Blender 2.8 3D .
In comparison, AMD ‘s Phenom II X4 965 processor took 2 minutes and 34 seconds to render the same test, which was a bit faster, while a processor like the Core i7-7700K only took 36 seconds to render , a performance gap of nearly 4- 5 times.
To put it simply, this processor has the performance level of x86 more than 10 years ago , and the 28nm process is relatively outdated. It is far from the current supercomputing chip in terms of energy efficiency, and the resulting supercomputing power consumption is also high. question.
- DIY a PBX (Phone System) on Raspberry Pi
- How to host multiple websites on Raspberry Pi 3/4?
- A Free Intercom/Paging system with Raspberry pi and old Android phones
- DIY project: How to use Raspberry Pi to build DNS server?
- Raspberry Pi project : How to use Raspberry Pi to build git server?