alt Hacker NewsIs there a simple explanation why RISC-V software has to be built on a RISC-V system? Why is it so hard for compilers to compile for a different architecture? The general structure of the target architecture lives inside the compiler code and isn’t generated by introspecting the current system, right?
Replies
Under specified build dependencies that use libraries/config on your host OS rather than the target system
You can solve this on a per language basis, but the C/C++ ecosystem is messy. So people use VMs or real hardware of the target arch to not have to think about it
Old compilers tended to make it a compile-time switch which backends were included, probably because backends were "huge", so they were left out. (The insn lookup table in GCC took ages to generate and compile.) And of course all development environments running on Windows assumed x86 was the only architecture.
With LLVM existing, cross-compiling is not a problem anymore, but it means you can't run tests without an emulator. So it might just be easier to do it all on the target machine.
The cross-compiler part itself is easy, but getting all the build scripting of tens of thousands of Fedora packages to work perfectly for cross-compiling would be a lot of work.
There are lots of small issues (libraries or headers not being found, wrong libraries or headers being found, build scripts trying to run the binaries they just built, wrong compiler being used, wrong flags being used, etc.) when trying to cross-compile arbitrary software.
All fixable (cross-compiling entire distributions is a thing), but a lot of work and an extra maintenance burden.
Cross building of possible, but it's rather useful to be able to test the software you just built... And often enough, tests take more resources than the build.
Native builds are always a safer/more reliable path to take than cross-compiling, which usually requires solid native builds to be operational before the cross environment can be reliably trusted.
Its a bootstrapping chain of priority. Once a native build regime is set in stone, cross compiling harnesses can be built to exploit the beachhead.
I have saved many a failing projects budget and deadline by just putting the compiler onboard and obviating the hacky scaffolding usually required for reliable cross compiling at the beginning stages of a new architecture project, and I suspect this is the case here too ..
Cross compilation of entire distributions requires such distributions to be prepated for it. Which is not a case when you use OpenEmbedded/Yocto or Buildroot to build it. But it gets complicated with distributions which are built natively.
Fedora does not have a way to cross compile packages. The only cross compiler available in repositories is bare-metal one. You can use it to build firmware (EDK2, U-Boot) or Linux kernel. But nothing more.
Then there is the other problem: testing. What is a point of successful build if it does not work on target systems? Part of each Fedora build is running testsuite (if packaged software has any). You should not run it in QEMU so each cross-build would need to connect to target system, upload build artifacts and run tests. Overcomplicated.
Native builds allows to test is distribution ready for any kind of use. I use AArch64 desktop daily for almost a year now. But it is not "4core/16GB ram SBC" but rather "server-as-a-desktop" kind (80 cores, 128 GB ram, plenty of PCI-Express lanes). And I build software on, write blog posts, watch movies etc. And can emulate other Fedora architectures to do test builds.
Hardware architecture slow today, can be fast in the future. In 2013 building Qt4 for Fedora/AArch64 took days (we used software emulators). Now it takes 18 minutes.