Hi all, I am trying to investigate the performance of WASM atomics with lower atomic guarantees. Specifically I am targeting the x86_64 architecture. i32.atomic.rmw.add currently compiles to LOCK XADDL, I want it to compile only to XADDL. I am changing "void LiftoffAssembler::AtomicAdd" in "src/wasm/baseline/x64/liftoff-assembler-x64-inl.h" by commenting out the lock() function on line 713. However, this does not seem to work. Neither does commenting out "emit(0xF0)" in "void Assembler:lock()" in assembler-x64.cc. I am running d8 with the -print-wasm-code, --liftoff and --no-wasm-tier-up flags.
Could someone point me in the right direction on how I would do this? -- -- v8-dev mailing list [email protected] http://groups.google.com/group/v8-dev --- You received this message because you are subscribed to the Google Groups "v8-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/v8-dev/838d2d34-3a8c-46da-8cf8-524e32f1a57cn%40googlegroups.com.
