[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #19 from George Pee --- Thank you for all of your thoughts and details, it has been tremendously helpful!

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #17 from George Pee --- Any idea on why the issue is intermittent?

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #15 from George Pee --- Funny that you mention that... https://lore.kernel.org/linux-arm-kernel/20220901141307.2361752-1-george...@gmail.com/T/#u

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #12 from George Pee --- SMP is enabled. The opcode thing was an experiment only. Your suggestion seems to work great, but is it safe to make the change across all ARM cpus ?

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #9 from George Pee --- Thank you for following up even after I closed the ticket. Unfortunately, I'm unable to switch to a 64-bit kernel at the moment. Using this works around the issue by treating it via a neon path and enabling t

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 George Pee changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED Resolution|---

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #6 from George Pee --- That explanation makes a lot of sense. Thank you!

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #4 from George Pee --- Yes, it's possible that this isn't a compiler bug. I thought that it might be because the problem started showing up after upgrading the toolchain. I wasn't sure if the compiler was failing to emit some kind

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #2 from George Pee --- Forgot to mention that I'm building 32-bit.

[Bug target/106763] Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 --- Comment #1 from George Pee --- I was using gcc-12, but I was also able to reproduce this issue using the sample program above and gcc-10.

[Bug target/106763] New: Armv8.2 vmov.f16 instruction sometimes causes SIGILL

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106763 Bug ID: 106763 Summary: Armv8.2 vmov.f16 instruction sometimes causes SIGILL Product: gcc Version: unknown Status: UNCONFIRMED Severity: normal Priority: P3 Com