If you want to build open source, you can ̵1; if you’re talking about software. However, the processor under the hood is proprietary. RISC-V is an open source processor design that quickly gains traction and promises to change the computer landscape.
An alternative to Intel and ARM patterns
Currently, two processor designs are prevalent: those created by ARM and Intel’s x86. While both companies work on a huge scale, their business models are fundamentally different.
Intel designs and manufactures its own chips, while ARM licenses its designers to third-party designers, such as Qualcomm and Samsung, who then add their own enhancements. While Samsung has the infrastructure to manufacture its processors internally, Qualcomm (and other “fantastic” designers) outsource this important work.
In the case of ARM, this often requires licensors to sign confidentiality agreements that are designed to keep aspects of the chip’s design private. This is hardly surprising, given that its entire business model is not designed around manufacturing but rather intangible property.
Meanwhile, Intel has its own commercial design secrets under lock and key. Because both types of processors are commercial, it is difficult (if not completely impossible) for academics and open source hackers to influence design.
How RISC-V is different
RISC-V is very different. First, it is not a company. It was first conceived in 2010 by academics at the University of California at Berkeley as an open source, royalty-free alternative to existing ones.
It’s similar to installing Linux instead of Windows so you do not have to buy anything or accept any onerous license agreements. RISV-V aims to do the same for research and design of semiconductors.
ARM also licenses both the Instruction Setup Architecture (ISA), which refers to the commands that can be naturally understood by a processor, and the microarchitecture, which shows how it can be implemented.
RISC-V only offers ISA, so researchers and manufacturers can define how they actually want to use it. This makes it scalable for devices of all stripes, from low-efficiency, 16-bit chips for embedded systems, to 128-bit processors for supercomputers.
As the name suggests, the RISC-V uses the reduced instruction set (RISC) principles, the same as chips based on ARM, MIPS, SPARC and Power designs.
What does this mean? Well, at the heart of all computer processors, there are things called instructions. In the most basic terms, this small program is represented in hardware that tells the processor what to do.
RISC-based chips typically have fewer instructions than chips that use a complex instruction computer (CISC) design, such as those offered by Intel. In addition, the instructions themselves are much easier to implement in the hardware.
Simpler instructions mean that chip manufacturers can be much more efficient with their chip designers. The trade-off is that these relatively complex tasks are not performed by the processor. Instead, they are divided into several, smaller instructions of software.
As a result, RISC has been nicknamed Relegate the Important Stuff to the Compiler. Even if it sounds like a bad thing, it is not. To understand this, you must first understand what a computer processor really is.
The processor in your phone or computer consists of billions of small components called transistors. In the case of CISC-based chips, many of these transistors represent the various instructions available.
Because RISC chips have fewer, simpler instructions, you do not need many transistors. This means that you have more space to do many interesting things. For example, you can include more cache and memory registers or additional functionality for AI and graphics processing.
You can also physically make the chip smaller by using fewer total transistors. This is why RISC-based chips from MIPS and ARM are often found in Internet of Things (IoT) devices.
The need for speed
Of course, licensing is not the only motivation for RISC-V. David Patterson, who led the first research projects in RISC processor design, said that RISC-V was designed to handle the upcoming limits of CPU performance that can be achieved through manufacturing improvements.
The more transistors you can fit on a chip, the more capable a processor will eventually be. As a result, chipmakers such as TSMC and Samsung (which both manufacture third-party processors) are working hard to shrink the size of transistors even more.
The first commercial microprocessor, the Intel 4004, had only 2,250 transistors, each measuring 10,000 nanometers (about 0.01 mm). Small, really, but contrasts with Apple’s A14 Bionic processor, released 40 years later. That chip (which drives the new iPad Air) has 11.8 billion transistors, each measuring 5 nanometers above.
In 1965, Intel founder Gordon E. Moore theorized that the number of transistors that could be placed on a chip would double every two years.
“The complexity of minimum component costs has increased at a rate of about a factor of two per year,” Moore wrote in the 35th anniversary of Electronics journal. Of course, in the short term, this interest rate can be expected to continue, if not increase. In the longer term, the rate of increase is a little more uncertain, although there is no reason to believe that it will not remain almost constant for at least ten years. ”
Moore’s law is expected to expire this decade. There is also great doubt as to whether chip manufacturers can continue this trend towards miniaturization in the long run. This applies to both the basic scientific level and the economic level.
After all, smaller transistors are much more complicated and expensive to manufacture. For example, TSMC spent over $ 17 billion at its factory to create 5 nm chips. Given this brick wall, Risk-V aims to address the performance problem by looking at ways in addition to shrinking the size and number of transistors.
Companies already use RISC-V
The RISC-V project started in 2010 and the first chip using ISA was manufactured in 2011. Three years later, the project became public and commercial interest soon followed. The technology is already used by companies such as NVIDIA, Alibaba and Western Digital.
The irony is that there is no inherent pioneering about RISC-V. The foundation notes on its website: “RISC-V ISA is based on computer architecture ideas that go back at least 40 years.”
What is undoubtedly groundbreaking, however, is the business model – or the lack of one. This is what exposes the project to experimentation, development and potentially unlimited growth. As the RISC-V Foundation also notes on its website:
“The interest is that it is a standard free and open standard to which software can be ported, and which allows everyone to freely develop their own hardware to run the software.”
At the time of writing, RISC-V chips are largely behind the scenes in server farms and as microcontrollers. It remains to be seen if there is any potential to shake up the ARM / Intel ISA duopoly in consumer space.
But if the established masters stagnate, it is within the possibility that a dark horse can gallop in and change everything.