An Attempt to Catch Up with JIT Compilers

Re:An Attempt to Catch Up with JIT Compilers by tsunego on Monday March 03, 2025 @11:31AM (#43243446)

chasing inline cache micro-optimizations with dynamic binary modification is a dead end. modern CPUs are laughing at our outdated compiler tricks. maybe it's time to accept that clever hacks won’t outrun silicon.

[ Parent | on HN ]

Re:An Attempt to Catch Up with JIT Compilers by andrekandre on Monday March 03, 2025 @07:24PM (#43248574)

what is the better approach?

[ Parent | on HN ]

Re:An Attempt to Catch Up with JIT Compilers by Sparkyte on Monday March 03, 2025 @08:25PM (#43249049)

You don't, there are equal trade offs. JIT might use more memory because of what it does at the runtime, but it is also the exact reason it is faster to start. A good trade off is just using the type of languages best suited for the workload.

[ Parent | on HN ]

Re:An Attempt to Catch Up with JIT Compilers by saagarjha on Tuesday March 04, 2025 @04:26AM (#43252369)

JITs typically are too broken for compiler tricks so I don't think it's time to accept that just yet.

[ Parent | on HN ]