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.

Reply via email to