After Brian's perf fixes last week, TI+JM is only 2-3% slower on Kraken and V8 (compared to JM from the tracemonkey branch). On some tests TI+JM is already much faster than JM. It would be nice if we could use AWFY to track regressions and see how TI+JM compares to V8 and TM/JM.
It now appears as a light blue line on the x86 regress and breakdown pages. Let me know when to add it to more.
Assignee: general → dvander
Status: NEW → RESOLVED
Last Resolved: 8 years ago
Resolution: --- → FIXED
You need to log in before you can comment on or make changes to this bug.