Hacker News Reader

Comment by wmf | Hacker News Reader

Agreed, but I think the purpose of these kind of criticisms is to "fix" RISC-V before it becomes yet another worse-is-better design locked in for 50 years.

View on HN

I think you are really missing the point here. Of course RISC-V has negatives but most of those negatives exist for good reasons. It is a question of tradeoffs.

One of the most important goals of RISC-V is to make an architecture which can stand the test of time. In this space adding the wrong kind of instructions is a bigger problem than not adding particular instructions.

Whether you look at x86, HTML or just about anything the problem is nearly always about having to support old junk which no longer makes sense to support, or lacking the ability to grow. Remember 640K is enough for everyone? RISC-V has a lot of room to grow.

If you want an architecture for the future you would want a minimalist one with room to grow a lot. By keeping the instruction count very low and building in a system for extensions they have made a future proof ISA. Okay we cannot know the future, but it is more likely to survive for decades than something like x86 or maybe even ARM.

Most of the complaints about RISC-V are extremely basic things like array indexing and conditional execution. These will never not be needed.

The problem is that those criticisms are almost always wrong. For instance the ARM proponents criticise RISC-V for having long instruction encodings and then they quote a few carefully cherry picked examples. But if you look at actual compiled programs RISC-V is nearly always 10-15% smaller than ARM.

I’m sure that’s what the team that invented segment registers said too.

The question is does it make sense to add these to the ISA long term? In the short term, given die density and how memory works today, it has advantages. But die density increases, making OoO cores cheaper, and memory technology changes. It’s not obvious that these are long term improvements.

It's not that the examples given are not correct, in isolation, it's that they are not common enough in real code to matter.

IANAE, but the article addresses why the arguments that assume these instructions need to be combined are usually not based on looking at the whole picture.

The only part of RISC-V that is "locked in" to any extent is the minimal set of basic integer instructions. Everything else is defined as part of standardized extensions, and can be superseded simply by defining new custom extensions. Actually even the minimal instruction set admits of some variation, such as the 'E' architectures that dispense with registers R16 to R31, thus saving area in the smallest implementations and potentially freeing up some bits in the encoding.

Things get locked in not by standards, but by usage. If your software depends on particular instructions being present you’re not going to buy a processor that has superseded those instructions, even if the new instructions conform to a theoretically cleaner design.

Everything being an extension (and thus removable) is a strength in some specific circumstances, but is a weakness in most.

That doesn't make any sense. Because RISC-V has kept instructions to such a bare minimum, there will be very little you will be dependent on and which new designs have to take into account. What you describe is a problem for x86 and ARM not for RISC-V. You got it all in reverse.

General-purpose CPUs for desktop computers and such will not be willy nilly adding extensions. They will standardize on something like RV64GC. However for specialized hardware which you only ever deal with through drivers, nobody will care whether extensions come and go. Are you worried that the processor in your keyboard or mouse isn't backwards compatible with the processor you used in your previous mouse or keyboard?

Anyway code today can already check what extensions you have and generate different code paths. You can ship operating systems which have fallback code for most extensions so they can be be removed in the future. You also got traps so RISC-V can jump to a software implementation of unsupported instructions.

> Are you worried that the processor in your keyboard or mouse isn't backwards compatible with the processor you used in your previous mouse or keyboard?

No, but the keyboard manufacturer might be, as might the people who are writing and optimising compilers targetting that CPU.

Reply on news.ycombinator.com