We have already spoken on numerous occasions that architecture RISC-V is a serious rival to the standardized x86 on high performance processors. But now it seems that Google itself wants to boost the performance of all its devices. For this, nothing better replace the current Arm architecture with RISC-V.
In the past, during the Google I/Owhen asked about the advances of the RISC-V architecture, the company only said “we are observing, but it would be a big change for usIt seems they have been watching the market quite a bit, to the point that Google attended the “RISC-V Summit” proclaiming that RISC-V should be a first level platform on Android devices.
The transition from Android to RISC-V would take “a few years”
Specific, lars bergstromAndroid’s director of engineering, wants RISC-V to catch up with Arm in terms of to be a “tier 1” platform. That is, a main platform. In this way, Google’s focus in just 6 months since Google I/O has changed from “we are watching” to wanting to make everything easy for RISC-V to be adopted en masse.
One big drawback, is that getting optimized Android builds on RISC-V will take “busy“. In this way, a road map was outlined that will take “a few years” to bear fruit, but AOSP started releasing official patches for RISC-V last September. In this way, this work has already begun.
RISC-V fits perfectly with the future of Google, which happens to make Android is only 64 bit. Once Google gets Android to work with RISC-V, it will be up to manufacturers and the app ecosystem to support the platform. The fun thing about Android RunTime is that when ART supports RISC-V, a large part of the Android app ecosystem will come with it.
Android apps are shipped as Java code, and the way they become Arm apps is when the Android Runtime compiles them into Arm code. However, will soon be compiled into RISC-V code without the developer having to do any additional work. Native code not written in Java, such as games and component libraries, will need to be ported, but starting with Java code is a great start.
Arm is less interesting now: an unstable and volatile trading partner
Callista RedmondCEO of RISC-V International, said that “RISC-V is inevitable“. With an open business model and the wave of open chip design it can create, it’s getting harder to argue against. The main reason RISC-V seems inevitable is that Arm, the current CPU leader, is has turned in an unstable and volatile company. With this, one gets the feeling that any viable alternative would have a very good chance of succeeding at this time.
It is evident that the purchase by NVIDIA would have revitalized Armbut since Softbank hung the for sale sign in 2020, it’s all bad news. Qualcommone of the companies that testified for the Federal Trade Commission to finally veto the acquisition, was sued by Arm itself for the purchase of the company Nuvia chip design.
Both Qualcomm and Nuvia held the highest level Arm architecture license. This allowed them to design custom chips based on the Arm architecture. Arm claims that the two companies have breached their contracts. Arm wants Qualcomm to scrap Nuvia’s chip designs and start from scratch. Obviously, this won’t happen, and Nuvia will arrive to steal a piece of the pie from Arm.
Arm also has problems with the Chinese market
To this is added, that Arm is subject to US export law. This implies that it has lost the entire Chinese market. This up-and-down relationship has caused months of upheaval in business and future plans. This cost him losing what until then was his best partner: Huawei.
RISC-V is seen as a way to become less dependent on the West. Although the project started at UC Berkeley, RISC-V International claims that its architecture is not subject to US export law.
In 2019, the RISC-V Foundation moved from the United States to Switzerland and became “RISC-V International”. Thanks to this, he avoided getting involved in the trade war between the United States and China. The result is that Chinese tech companies are rallying around RISC-V as the future chip architecture.