# The State of JavaScript on Android in 2015 is... poor
**URL:** https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889
**Category:** General
**Created:** [9월 29, 2015, 11:25오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889 "2015-09-29T23:25:14Z")
**Posts on this page:** 20
**Page:** 13
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [9월 22, 2017, 9:33오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/249 "2017-09-22T09:33:50Z")
Impressively, I just tested @zogstrip’s Nexus 6p on [emberperf.eviltrout.com](http://emberperf.eviltrout.com), render complex list, 2.11 and I got ~150ms. That’s quite good.
| | |
| --- | --- |
| Chrome 55 | 212 ms |
| Chrome 58 | 175 ms |
| Chrome 61 | 150ms |
That puts it in iPhone 6 territory, which is about where it should be based on the CPU, and I would rate it as solidly “good”. The Nexus 6p is not exactly a new device.. we’ll see where Snapdragon 845 takes us. Current rumors say:
> The Snapdragon 845 scores 2600+ in GeekBench 4, for single core results.
That’s about 10% faster than iPhone 6s.
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 10, 2017, 4:34오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/250 "2017-10-10T16:34:42Z")
For those that are not familiar with why Apple devices show higher performance and why Android device manufacturers appear to be playing catch-up here is a nice video with a little bit of history:
[ ](https://www.youtube.com/watch?v=TiVF_ZzzLM0)
* * *
For point of reference I ran some of the benchmarks on my OnePlus 2 (ONE A2003) an August 2015 Qualcomm Snapdragon 810 phone - the same processor as the [Nexus 6P mentioned above](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/249).
This was a new phone when this thread was started back in 2015, now updated the phone running on a custom Lineage OS build (Android 7.1.2). In a months time a replacement phone will come and I’ll reset the device to whatever the latest manufacturer OS is and run these numbers again.
| Browser version | [“render complex list”, 2.11](http://emberperf.eviltrout.com/) | [Speedometer](http://browserbench.org/Speedometer/) |
| --- | --- | --- |
| Chrome 61 (Stable) | 152.27ms | 27.2 (±2.4) |
| Chrome 62 (Beta) | 179.04ms | 25.4 (±1.4) |
| Chrome 63 (Canary) | 190.00ms | 23.7 (±1.7) |
Allowing the phone to “cool” between benchmark runs - these are pretty repeatable numbers.
Hopefully this doesn’t indicate that Chrome is slipping backwards any when Chrome 63 finally reaches the general public.
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [10월 10, 2017, 10:48오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/251 "2017-10-10T22:48:08Z")
Canary isn’t a good test candidate. Try beta. Canary is too variable. Also you don’t need both runs, the HTML and regular are pretty much the same these days.
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 10, 2017, 11:31오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/252 "2017-10-10T23:31:55Z")
> [@codinghorror](#):
>
> Canary isn’t a good test candidate. Try beta. Canary is too variable.
I’ve updated the post above to include the Chrome Beta numbers too.
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [10월 10, 2017, 11:49오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/253 "2017-10-10T23:49:20Z")
Well that is concerning. I am not on Twitter any more but you might try pinging Benedikt with a link to your post [https://twitter.com/bmeurer](https://twitter.com/bmeurer)
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 11, 2017, 12:10오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/254 "2017-10-11T00:10:16Z")
> [@codinghorror](#):
>
> you might try pinging Benedikt with a link to your post
Done:
[https://twitter.com/DeanMarkTaylor/status/917904963438866432](https://twitter.com/DeanMarkTaylor/status/917904963438866432)
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 11, 2017, 1:21오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/255 "2017-10-11T01:21:06Z")
I wanted to check if this repeatable cross another device…
Trying it on a slightly older (from the factory, OEM updates only) “OnePlus One” (A0001) - Qualcomm Snapdragon 801 - Cyanogen OS 13.1.2 - Android 6.0.1 phone - released April 2014.
| Browser version | [“render complex list”, 2.11](http://emberperf.eviltrout.com/) | [Speedometer](http://browserbench.org/Speedometer/) |
| --- | --- | --- |
| Chrome 61 (Stable) | 329.27ms | 15.70 |
| Chrome 62 (Beta) | 435.83ms | 14.59 |
| Chrome 63 (Canary) | 451.24ms | 15.10 |
Again allowing it to “cool” between runs.
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 11, 2017, 4:17오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/256 "2017-10-11T04:17:04Z")
Just had this reply:
>
EDIT: Additional update:
>
EDIT #2: Additional update:
>
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 25, 2017, 11:45오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/257 "2017-10-25T23:45:38Z")
I re-ran all the benchmarks…
## OnePlus 2 (ONE A2003):
| Browser version | [“render complex list”, 2.11](http://emberperf.eviltrout.com/) | [Speedometer](http://browserbench.org/Speedometer/) |
| --- | --- | --- |
| Chrome 61 (Stable) | 147.74ms | 26.10 (± 2.50) |
| Chrome 62 (Beta) | 165.26ms | 24.80 (± 2.00) |
| Chrome 64 (Canary) | 118.85ms | 27.90 (± 0.48) |
## OnePlus One (A2001):
| Browser version | [“render complex list”, 2.11](http://emberperf.eviltrout.com/) | [Speedometer](http://browserbench.org/Speedometer/) |
| --- | --- | --- |
| Chrome 61 (Stable) | 333.12ms | 15.82 (± 0.086) |
| Chrome 62 (Beta) | 421.10ms | 14.59 (± 0.060) |
| Chrome 64 (Canary) | 285.00ms | 16.00 (± 0.084) |
Note the following for the latest Chrome 64 (Canary):
- “render complex list” times going down - yay! :allthethings:
- “Speedometer” numbers going up - yay! :allthethings:
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [10월 26, 2017, 12:07오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/258 "2017-10-26T00:07:50Z")
Very nice results!! All kudos to Benedikt. Be sure to link him to your results via Twitter; I can’t as I am no longer on Twitter.
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [10월 26, 2017, 12:25오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/259 "2017-10-26T00:25:56Z")
> [@codinghorror](#):
>
> All kudos to Benedikt. Be sure to link him to your results via Twitter
>
UPDATE: Reply from Benedikt
>
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [6월 16, 2018, 6:16오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/260 "2018-06-16T06:16:53Z")
Good news! In the last year things have gotten a _lot_ better!
Snapdragon 835, Android / Chrome circa June 2017
Snapdragon 845, Android / Chrome circa June 2018
Note this is Speedometer 1.0 to keep the comparison apples to apples. Between the respectable hardware bump (finally) and major Chrome/Android JS improvements, we’re looking at 2x improvement. Vastly overdue.. but I’ll take it!
This is finally iPhone 6s territory which I’d call certainly fast enough for native Discourse performance.
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [9월 29, 2019, 8:47오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/261 "2019-09-29T08:47:02Z")
여기서는 더 정확하지만(수치가 더 낮은) Speedometer 2.0 기준 수치를 사용했습니다:
OnePlus 5 — Snapdragon 835 — 33.1
OnePlus 6 — Snapdragon 845 — 49.4
Xiaomi 9 — Snapdragon 855 — 68.5
물론 이 수치들은 iOS 하드웨어 수치와는 꽤 차이가 있으며, 대략 iPhone 7 수준입니다. 비교를 위해 이 iPad Pro는 137.5를 기록했고, iPhone 11은 약 150을 기록했습니다.
---
### Author:  [@DeanMarkTaylor](https://meta.discourse.org/u/DeanMarkTaylor)
#### Post date: [9월 29, 2019, 3:05오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/262 "2019-09-29T15:05:09Z")
모든 스냅드래곤 835가 동일한 것은 아님을 보여주는 비교 자료입니다:
Google Pixel 2 XL — Snapdragon 835 — 24.6
Android 10으로 업데이트하고, 완전히 충전한 후, 깨끗하게 재시작하여 전원 어댑터에 연결한 상태로 5분간 대기했습니다(휴대폰이 부팅으로 바쁜 상태가 아니도록 하기 위함).
해당 휴대폰은 처음 출시된 지 23개월(2017년 10월)이 지났으며, 불과 6개월도 안 된 시점(2019년 4월)에 단종되었습니다.
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [9월 29, 2019, 3:06오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/263 "2019-09-29T15:06:42Z")
제 기기는 하드웨어가 처음 출시된 시기에 가까운 몇 달 전에 테스트했습니다. 다른 모델도 마찬가지입니다. 샤오미 제품은 어제 테스트했죠 😉
---
### Author:  [@Remah](https://meta.discourse.org/u/Remah)
#### Post date: [9월 29, 2019, 8:08오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/264 "2019-09-29T20:08:50Z")
> [@codinghorror](#):
>
> OnePlus 6 — Snapdragon 845 — 49.4
LG ThinQ G7 — Snapdragon 845 — 52.6
Chrome 77.0 Android 9, Speedometer 2
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [4월 16, 2020, 5:55오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/265 "2020-04-16T05:55:27Z")
대박으로 마무리할게요
> **[New iPhone SE](https://news.ycombinator.com/item?id=22878515)**
>
> 1539 points —
> 1459 comments —
> CoachRufus87 —
> 3:03 PM - 15 Apr 2020
[quote=“codinghorror, post:261, topic:33889”]
OnePlus 5 — Snapdragon 835 — 33.1
OnePlus 6 — Snapdragon 845 — 49.4
Xiaomi 9 — Snapdragon 855 — 68.5
[/quote]여기서 Snapdragon 865는 [80~85 정도](https://hothardware.com/reviews/qualcomm-snapdragon-865-performance-preview)를 기록하는데, 비교 대상은..
>
---
### Author:  [@henkpoley](https://meta.discourse.org/u/henkpoley)
#### Post date: [4월 17, 2020, 6:42오전 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/266 "2020-04-17T06:42:03Z")
다만 데스크톱 Edge Canary에서는 눈에 띄는 성능 향상이 관찰되었습니다. 안정판 Chrome v80에서 75~85에 그치던 i5-8265U가 이제 110을 기록하고 있습니다(30% 향상, v84 기준).
주요 원인은 처리량이 줄어든 것 같습니다. Intel Power Gadget에서 ‘CPU Util%’(실행 유닛이 처리할 수 있는 명령어 수를 추정하는 지표)에 큰 차이는 보이지 않으므로, 실제로는 더 적은 작업을 수행하는 것으로 보입니다.
ARM 환경에서는 어떻게 나타날지 확실하지 않습니다. 좋은 결과가 나오기를 기대합니다.
---
### Author:  [@codinghorror](https://meta.discourse.org/u/codinghorror)
#### Post date: [4월 17, 2020, 3:43오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/267 "2020-04-17T15:43:39Z")
데스크톱은 사실 큰 문제가 아닙니다. 성능이 매우 뛰어나니까요. 하지만 퀄컴 SoC의 약점 때문에 안드로이드에 대한 성능 개선은 엄청납니다! 안드로이드에서 카나리(사전 배포 버전) 개선 효과를 보고 계신가요? 🤔
솔직히 안드로이드 쪽에서 iPhone 7 (855)과 iPhone 8 / X (865)의 성능은 나쁘지 않습니다. 디스커스(Discourse) 관점에서는 분명히 "충분"합니다. 숨이 막힐 정도는 아니지만, 완전히 쓸 만한 수준입니다.
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [7월 3, 2020, 4:31오후 UTC](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889/268 "2020-07-03T16:31:50Z")
[https://www.androidpolice.com/2020/07/03/chrome-for-android-is-finally-going-64-bit/](https://www.androidpolice.com/2020/07/03/chrome-for-android-is-finally-going-64-bit/)
제 메타 PWA는 이미 64비트로 실행 중입니다 🎉
[이전 페이지](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889.md?page=12)
[다음 페이지](https://meta.discourse.org/t/the-state-of-javascript-on-android-in-2015-is-poor/33889.md?page=14)