Brendan Eich

ND is the enemy; this isn't the last time double sprinting ND will bite, I bet (based on decades of bitter experience). I know dtoa.c is ugly old code, and...

@lukewagner Yes! See http://www.ecma-international.org/ecma-262/6.0/#sec-tostring-applied-to-the-number-type. /be P.S. Recall we had Guy Steele on Ecma TC39 TG1 in 1996-7 courtesy Sun, and he and David M. Gay co-authored the dtoa.c paper.

I want to repeat something from Slack: we should be big in our thinking for competitive reasons and to avoid building up too many dropped-shield exceptions. * Block Scripts sometimes...

@juj - thanks for writing that up. If one believes (as I do) in the [extensible web manifesto](http://extensiblewebmanifesto.org), then there is a tension between exposing native, hardware-specific capabilities on the...

@kripken: the problem with 2 is that object detection, even without fallback, is better than a perf cliff. The app that doesn't also code for NEON will just fail to...

@kripken: It would help if I defined "perf cliff": I mean the code works everywhere, but terribly slowly on some platforms, untenable slowness (4x slowdown counts? I think so). The...

@kripken: it's true, unless a particular instruction available only in one arch were on a super-critical path, the cliff might be much less than 4x for the macro-benchmark. Hard to...

I contend that portable but 2x or slower is a non-starter. SIMD-based C/C++ code can't tolerate it when cross-compiled if the resulting JS is to compete with native and provided...

Can we (Bob's team, anyone on B2G with chops) automate a perf regression test? /be Chris Jones wrote: > On maguro. Several possible culprits here. > > --- > >...

Someone update the README?