dcode
cdec865bef
Update Binaryen to latest nightly
2019-03-08 16:19:46 +01:00
Daniel Wirtz
4e1bba3a24
Use Binaryen's function signature naming scheme ( #522 )
2019-03-01 00:01:23 +01:00
Max Graey
6b495f71d0
Ensure Math.clz32/imul compatibility with JS ( #474 )
2019-02-21 00:32:58 +01:00
Daniel Wirtz
2f1a6c44ce
Add SIMD prerequisites ( #469 )
2019-02-07 15:26:26 +01:00
dcode
cd1cfe6957
Update Binaryen to latest and rebuild dist files
2019-02-05 17:12:10 +01:00
Max Graey
c7441066dc
Minor math tweaks + ipow32f/ipow64f ( #428 )
2019-01-24 23:17:44 +01:00
Max Graey
d3715688fc
Fix Math.imul and add tests ( #432 )
2019-01-24 01:23:53 +01:00
dcode
20f4092eb2
Update Binaryen and other dependencies; Update dist files
2019-01-09 13:02:47 +01:00
dcodeIO
a661ff7d89
Update Binaryen to latest
2018-12-01 03:09:43 +01:00
Daniel Wirtz
c30c62e383
Cast to bool by comparing to zero ( #343 )
2018-11-23 15:20:52 +01:00
Max Graey
410036e445
Use mixed Horner scheme in Math.exp/expm1 to improve instruction parallelization ( #311 )
2018-11-09 17:56:42 +01:00
dcodeIO
4f95dce6e2
Do not emit debug info by default
...
This basically flips the --noDebug flag to become a --debug flag, so some optimizations, like inlining, aren't skipped by default, which might be unexpected.
2018-11-09 12:28:10 +01:00
Daniel Wirtz
2bdc2a72f1
Use stack IR when emitting text format ( #312 )
2018-11-08 08:04:24 +01:00
Max Graey
376afd45fc
Improve Math routines; Add Mathf-specific prng ( #297 )
2018-10-26 00:10:17 +02:00
Daniel Wirtz
f7c734789e
Update Binaryen to latest; Various fixes
2018-10-11 08:49:08 +02:00
dcodeIO
16d1a833dd
Always add a null function at table index zero
...
This allows function references (a table index internally) to be nullable
2018-09-17 01:48:35 +02:00
dcodeIO
d90cd085e5
Update Binaryen
2018-09-13 23:10:49 +02:00
dcodeIO
6949cf9f9e
Switch signed/unsigned instructions when upcasting 32- to 64-bit integers, fixes #247
...
Matches C semantics now. Turns around some instructions in tests, especially libm, but doesn't break anything.
2018-09-10 14:25:33 +02:00
Daniel Wirtz
dc0f271fc2
Initial GC integration ( #196 )
2018-08-02 18:23:02 +02:00
dcodeIO
26e46f6f86
Reintroduce builtin decorator so these can appear anywhere in stdlib again
...
Avoids wrapping an undocumented function within 'memory.size' for example.
2018-07-19 02:10:04 +02:00
dcodeIO
a1b75b69b7
Rename memory instructions; Rework constant handling
2018-07-18 23:49:32 +02:00
dcodeIO
9c16363796
Initial external decorator for annotating explicit import names; Use file name as default module name in imports; Emit empty memory if there are no static segments; Update TLSF and examples accordingly
2018-06-28 01:44:32 +02:00
dcodeIO
7a8995b18b
Properly inline getters; Simplify blocks when last statement returns
2018-06-22 15:26:59 +02:00
dcodeIO
c6ec5e2832
Utilize Binaryen's -O4
...
When specifying -O3 or -Oz, asc now automatically increases the optimize level to 4, then including costly non-LLVM optimizations for blocky code, in turn achieving similar results as an LLVM-based generator.
2018-06-09 14:05:33 +02:00
dcodeIO
6c0a5c47d9
Update Binaryen and take care of WebAssembly/binaryen#1547
2018-05-14 16:55:55 +02:00
Daniel Wirtz
50f6c1c460
Update internal ABI to zero/sign-extend where necessary only ( #87 )
2018-05-06 00:00:54 +02:00
Max Graey
8997561670
Update dependencies ( #93 )
2018-05-03 18:25:32 +02:00
dcodeIO
6d6d1dddcf
Improve inlining where locals can be aliased; Add a crude mechanism for explicit unchecked array accesses
...
The `unchecked` builtin should be handled with ultimate care and it would be a lot better if there'd be a mechanism doing this automatically.
2018-04-25 05:04:35 +02:00
Max Graey
a15457d8b9
Simplify isFinite & isNaN ( #78 )
2018-04-18 15:14:24 +02:00
dcodeIO
4929fca363
Move some numeric builtins to stdlib; Minor refactoring
2018-04-17 02:50:38 +02:00
dcodeIO
78a679759a
Update dependencies
2018-04-13 15:31:23 +02:00
dcodeIO
748e811137
Proper isNaN/isFinite without a temp. local
2018-04-12 20:40:00 +02:00
Max Graey
1cea3c6f08
Improve Math#sign ( #72 )
2018-04-12 19:26:50 +02:00
Max Graey
2002e32c9c
Inline small stdlib functions ( #71 )
2018-04-12 14:17:29 +02:00
dcodeIO
06198a3723
Rename lib prefix to '~lib' (parens aren't valid); Add built-in alignof<T>; Prepare for ArrayBufferView
2018-04-02 19:05:26 +02:00
dcodeIO
59a22c1842
A little 'asinit' CLI tool for quickly setting up a project; Minor refactoring
2018-04-01 23:46:41 +02:00
Daniel Wirtz
164f134053
Even more math ( #56 )
...
Remaining implementations of JavaScript's Math functions (except sin/cos/tan), both double (Math) and single (Mathf) precision, ported from musl incl. tests from libc-test, plus some changes to match JS semantics. Also binds fmod to `%` and pow to `**`.
2018-03-30 17:25:54 +02:00
