So is ARM. Every ARM processor is basically uniq, and that makes it efficient. That’s the point of it. RISC as a design philosophy doesn’t take over the industry, its specific implementations. My question is not what RISC is, but if ARM is based on RISC and how close it is in their designs to RISC-V. As I understand the company behind ARM took the RISC philosophy and created a closed source system.
ARM is a well-defined instruction set architecture (ISA), that in order to implement, must comply with that instruction set and be compatible with other implementations from other vendors.
RISC is not any sepcific ISA at all, but is rather a more generic term for any ISA that has a small amount of instructions.
RISC-V, on the other hand, is a well-defined ISA whose implementations are intercompatible with each other. RISC-V is a very specific, royalty-free ISA that comes out of UC Berkeley that adopts the RISC philosophy.
ARM is a well-defined instruction set architecture (ISA), that in order to implement, must comply with that instruction set and be compatible with other implementations from other vendors.
But that’s not true. ARM isn’t well defined and a single standard, like x86 are. ARM devices are not compatible to each other necessarily. I just had the genius idea to lookup online, I should have done that instead wondering what it is. According to Wikipedia: https://en.wikipedia.org/wiki/ARM_architecture_family
ARM (stylised in lowercase as arm)[a] is a family of RISC instruction set architectures for computer processors.
The original Berkeley RISC designs were in some sense teaching systems, not designed specifically for outright performance. To the RISC’s basic register-heavy and load/store concepts, ARM added a number of the well-received design notes of the 6502.
So I was correct after all. Also ARM is around since 41 years.
Yes, ARM is RISC but it is also well-defined. ARMv9 is backwards compatible with ARMv8. ARMv8 and v9 are 64-bit while ARMv7 and before were 32-bit. Even ARMv9 is technically compatible with ARMv7 because of Aarch32 but that’s optional. ARM’s versioning is more numerous than x86-64 (which also has v2, v3, etc) but that doesn’t mean it’s not well defined.
Not really. Unlike x86, an ARM implementation doesn’t have to be compatible to any of the existing CPUs. That’s because of its nature being RISC it can be adapted and changed. There is no core ARM set that has to be implemented by every ARM CPU like x86 does, so that base compatibility is guaranteed. Just because a few CPUs in the family were compatible, doesn’t make the entire architecture design well defined… it cannot be by nature being a RISC implementation.
ARM has multiple revisions that are incompatible with each other, such as ARMv7 being incompatible with AARCH64, but each ARMv7 implementation is compatible with other ARMv7 implementations, and each AARCH64 implementation is comaptible with other ARCH64 implementations, otherwise something like Android APKs or Linux binaries built for AARCH64 would only be able to be run on SoCs from a single company instead of being able to run on SoCs from Qualcomm, Samsung, Nvidia, and Mediatek just the same like they are.
Just because ARM does not maintain backwards compatability does not invalidate my point.
Just because ARM does not maintain backwards compatability does not invalidate my point.
It does. ARM is basically a set of RISC processors that each of them are different. There is no single ARM well defined instruction set, because every ARM CPU is incompatible and an implementation of the RISC idea. You cannot say ARM is well defined. But you can say x86 is well defined.
I mean 80s computers had ARM CPUs, that has nothing todo with todays ARM anymore. This is not what I would call “well-defined”.
If backwards compatibility bothers you, then replace it with “a series of well defined ISAs”, which still does not define the RISC philosophy as a whole, which is the entire point I’m trying to make.
If backwards compatibility bothers you, then replace it with “a series of well defined ISAs”
This is exactly what I’m saying, its not well defined architecture. You never know if the next ARM CPU will be compatible or not to any existing variants.
which still does not define the RISC philosophy as a whole
What do you mean? ARM is a RISC CPU. The entire philosophy of RISC is that anyone can implement this RISC system, and no guarantees are made to be compatible with any prior CPU. We have RISC CPUs since the beginning of 80s.
The official Acorn RISC Machine (ARM) project started in October 1983.
RISC literally just means reduced instruction set architecture. Any CPU that has a small amount of instructions (defined somewhat arbitrarilly) is considered to be a RISC CPU as opposed to a CISC (complex instruction set architecture) CPU. The idea behind RISC is to improve performance by reducing bloat, but the tradeoff is that performing more complex tasks takes more instructions to do.
RISC isn’t a specific architecture, but moreso a design philosophy.
So is ARM. Every ARM processor is basically uniq, and that makes it efficient. That’s the point of it. RISC as a design philosophy doesn’t take over the industry, its specific implementations. My question is not what RISC is, but if ARM is based on RISC and how close it is in their designs to RISC-V. As I understand the company behind ARM took the RISC philosophy and created a closed source system.
ARM is a well-defined instruction set architecture (ISA), that in order to implement, must comply with that instruction set and be compatible with other implementations from other vendors.
RISC is not any sepcific ISA at all, but is rather a more generic term for any ISA that has a small amount of instructions.
RISC-V, on the other hand, is a well-defined ISA whose implementations are intercompatible with each other. RISC-V is a very specific, royalty-free ISA that comes out of UC Berkeley that adopts the RISC philosophy.
But that’s not true. ARM isn’t well defined and a single standard, like x86 are. ARM devices are not compatible to each other necessarily. I just had the genius idea to lookup online, I should have done that instead wondering what it is. According to Wikipedia: https://en.wikipedia.org/wiki/ARM_architecture_family
So I was correct after all. Also ARM is around since 41 years.
Yes, ARM is RISC but it is also well-defined. ARMv9 is backwards compatible with ARMv8. ARMv8 and v9 are 64-bit while ARMv7 and before were 32-bit. Even ARMv9 is technically compatible with ARMv7 because of Aarch32 but that’s optional. ARM’s versioning is more numerous than x86-64 (which also has v2, v3, etc) but that doesn’t mean it’s not well defined.
Not really. Unlike x86, an ARM implementation doesn’t have to be compatible to any of the existing CPUs. That’s because of its nature being RISC it can be adapted and changed. There is no core ARM set that has to be implemented by every ARM CPU like x86 does, so that base compatibility is guaranteed. Just because a few CPUs in the family were compatible, doesn’t make the entire architecture design well defined… it cannot be by nature being a RISC implementation.
This statement is just fundamentally wrong. And it looks like someone else explained this better than I did.
But there is. There is a base ISA. It looks like you have several fundamental misunderstandings…
ARM has multiple revisions that are incompatible with each other, such as ARMv7 being incompatible with AARCH64, but each ARMv7 implementation is compatible with other ARMv7 implementations, and each AARCH64 implementation is comaptible with other ARCH64 implementations, otherwise something like Android APKs or Linux binaries built for AARCH64 would only be able to be run on SoCs from a single company instead of being able to run on SoCs from Qualcomm, Samsung, Nvidia, and Mediatek just the same like they are.
Just because ARM does not maintain backwards compatability does not invalidate my point.
It does. ARM is basically a set of RISC processors that each of them are different. There is no single ARM well defined instruction set, because every ARM CPU is incompatible and an implementation of the RISC idea. You cannot say ARM is well defined. But you can say x86 is well defined.
I mean 80s computers had ARM CPUs, that has nothing todo with todays ARM anymore. This is not what I would call “well-defined”.
If backwards compatibility bothers you, then replace it with “a series of well defined ISAs”, which still does not define the RISC philosophy as a whole, which is the entire point I’m trying to make.
This is exactly what I’m saying, its not well defined architecture. You never know if the next ARM CPU will be compatible or not to any existing variants.
What do you mean? ARM is a RISC CPU. The entire philosophy of RISC is that anyone can implement this RISC system, and no guarantees are made to be compatible with any prior CPU. We have RISC CPUs since the beginning of 80s.
RISC literally just means reduced instruction set architecture. Any CPU that has a small amount of instructions (defined somewhat arbitrarilly) is considered to be a RISC CPU as opposed to a CISC (complex instruction set architecture) CPU. The idea behind RISC is to improve performance by reducing bloat, but the tradeoff is that performing more complex tasks takes more instructions to do.