It is becoming clearer that China’s plan to cut reliance on Western chip technology revolves around homegrown chips built using the open RISC-V architecture, which is also gaining popularity in […]
RISCV is an open instruction set. You don’t need to ask for the “code” from ARM / Intel etc for their MISC or CISC instructions.
This way, you can make it cheaper and easier from a set of “ingredients” and be more likely for collaboration and reusablitity (AFAIK) between vendors.
RISC is simpler than x86 and thus more resource efficient at the cost of compute power
And I don’t fully understand why but x86 is kinda shit because of how bloated it is amongst other reasons and modern Intel x86 chips actually translate the x86 ISA to RISC internally within the chip
RISC architectures aren’t necessarily more resource efficient or less computationally powerful than CISC architectures. The reason RISC architectures (or microarchitectures, in Intel’s case) took over is because they allow certain optimizations (simpler pipelining, simpler functional units for more superscalar processors, smaller processor cores so you can fit more cores in a single package, etc) that allow faster and more parallel execution of instructions. Eventually, this ended up being faster than having more complicated instructions that did more in a single operation (like in the x86 architecture). Also, programs written (or compiled) for RISC architectures tend to require more memory just because each instruction accomplishes less than on a CISC architecture.
Can I get a ELI5 about the pros and cons of RISC processors?
RISCV is an open instruction set. You don’t need to ask for the “code” from ARM / Intel etc for their MISC or CISC instructions.
This way, you can make it cheaper and easier from a set of “ingredients” and be more likely for collaboration and reusablitity (AFAIK) between vendors.
https://en.m.wikipedia.org/wiki/RISC-V#rationale
RISC is simpler than x86 and thus more resource efficient at the cost of compute power
And I don’t fully understand why but x86 is kinda shit because of how bloated it is amongst other reasons and modern Intel x86 chips actually translate the x86 ISA to RISC internally within the chip
RISC architectures aren’t necessarily more resource efficient or less computationally powerful than CISC architectures. The reason RISC architectures (or microarchitectures, in Intel’s case) took over is because they allow certain optimizations (simpler pipelining, simpler functional units for more superscalar processors, smaller processor cores so you can fit more cores in a single package, etc) that allow faster and more parallel execution of instructions. Eventually, this ended up being faster than having more complicated instructions that did more in a single operation (like in the x86 architecture). Also, programs written (or compiled) for RISC architectures tend to require more memory just because each instruction accomplishes less than on a CISC architecture.
noted.gif
Its like arm(aimed at more power efficient computation), but anyone is free to pick up its design without needing to license it.