Is there any remotely modern x86 that can be fully de-backdoored? (SMM, ME, etc. not present or able to be disabled)
@piecritic I like the ISA but we're a long ways away from having tolerable codegen in compilers. It's like 2x larger, slower than should be.
-
-
@piecritic It would help if someone were actually upstreaming@risc_v support in GCC & binutils.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@RichFelker isn’t that story true for any emerging architecture though? -
@piecritic Yes. But it's a major obstacle to making the arch (or any new arch) practical and nobody seems to be taking it seriously. -
@RichFelker well yes, not _yet_ though. I think it hasn’t in the minds of many people crossed from “excellent engineering experiment” yet. -
@piecritic I understand the reasoning but I think it's a mistake. It *can't* cross from "experiment" unless users can see it's viable. -
@piecritic And that means ability to produce binaries which perform competitively with x86 ones. -
@RichFelker it will also help once there’s actually hardware boards that people can play with. Makes it “real”. -
@piecritic Are there any FPGA boards you can get a practical system with right now? (practical = fast, necessary add'l devices etc.) -
@RichFelker afaik none whatsoever. - 4 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.