Assad Hashmi
Assad Hashmi
User issue raised when running on A64FX https://groups.google.com/g/dynamorio-users/c/_7H9NZXh3wc
The following tests fail on the new Jenkins CI host, an Ampere Altra: code_api|tool.drcachesim.phys #4922 code_api|tool.drcacheoff.rseq #4924 code_api|api.rseq #4923 code_api|tool.drcachesim.threads #4928 code_api|tool.drcachesim.TLB-threads #4928
run arm tests
This patch continues the work started in https://github.com/DynamoRIO/dynamorio/pull/5235. I think I've addressed all of @derekbruening's bullet points at https://github.com/DynamoRIO/dynamorio/pull/5235/files#r761331940 except the last two: > Adding support for the new flag...
> @AssadHashmi is there any ongoing work looking at AArch64 overhead? There seem to be several cases of significant overhead for DR on AArch64 compared to DR on x86: this...
> heavyweight. @AssadHashmi -- could this be skipped for brand new code in a fresh mmap? Xref [ARM machine_cache_sync is not thread-safe #1911](https://github.com/DynamoRIO/dynamorio/issues/1911). Yes AFAICT but I don't have much...
> I didn't look up what this hint does: does DR need to take any action there or this is just a missing innocuous opcode? Looks like this `HINT` became...
> Would this trap show up as a signal to user mode that we would see? Yes. According to the AArch64 spec, h/w will raise a Branch Target exception when...
> Some clarifications/questions: > > * These HINT warnings are what _I_ observed running java on the Jenkins machine. I don't think that has ARMv8.5? It doesn't support `FEAT_BTI`. So...