fluencelabs/assemblyscript
1
0
Fork 0
mirror of https://github.com/fluencelabs/assemblyscript synced 2025-04-25 15:12:12 +00:00
Code Issues Projects Releases Wiki Activity
620 Commits 10 Branches 1 Tag
Commit Graph

59 Commits

Author SHA1 Message Date
Max Graey
208dc2f1de Implement Mathf.sin/cos/tan (#491) 2019-03-05 19:36:22 +01:00
Daniel Wirtz
4e1bba3a24
Use Binaryen's function signature naming scheme (#522) 2019-03-01 00:01:23 +01:00
dcode
7184db6dde Update Binaryen to latest and regenerate dist files 2019-02-28 18:26:04 +01:00
Max Graey
6b495f71d0 Ensure Math.clz32/imul compatibility with JS (#474) 2019-02-21 00:32:58 +01:00
Daniel Wirtz
0c64f21250
Rework resolver (#489) 
* Rework IR and resolver to use nested lookup tables
* Integrate types into IR
* Make components prefer IR, slimmed down AST
* Implement `export *`
* Add `@lazy` annotation and remove `--noTreeShaking`
* Add `@start` annotation and remove magic `main`
* Related refactoring, cleanup and docs
 2019-02-21 00:11:22 +01:00
Daniel Wirtz
2f1a6c44ce
Add SIMD prerequisites (#469) 2019-02-07 15:26:26 +01:00
Daniel Wirtz
831054dfd3
Rework inlining logic (#463) 2019-02-06 23:42:43 +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
4944280cdc Add Math.signbit (#333) 2018-11-18 11:46:48 +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
d864bef1eb Improve per-bit divmod loop for mod & rem (#307) 2018-10-30 15:10:50 +01:00
Max Graey
e58582e9e9 Minor remquof improvemnts (#306) 2018-10-27 18:27:54 +02:00
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
Max Graey
c27b6e8951 Add integer power functions (#212) 2018-09-09 04:07:27 +02:00
dcodeIO
631478c7c9 Rework static memory segment creation; Fix stdlib gc hooks not marking own fields; Align everything to 8 bytes that might be touched by GC 2018-08-04 00:36:59 +02:00
Daniel Wirtz
dc0f271fc2
Initial GC integration (#196) 2018-08-02 18:23:02 +02:00
dcodeIO
34839353fd Inline isNaN and isFinite 
Looking at our existing tests it seems that inlining these can be performed by reusing locals most of the time, and sometimes enables erasing quite a bit of unnecessary code when optimizing.
 2018-07-19 04:12:40 +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
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
7ad13f9d65 Add a 'call_indirect' builtin to emit arbitrary calls (might trap at runtime); Optimize 'for' loop compilation a bit 2018-05-25 15:59:17 +02:00
dcodeIO
829af2285c Fix continue labels in 'for' loops skipping the incrementor 2018-05-23 11:32:12 +02:00
dcodeIO
73417a9a06 Move 'abort' out of builtins and make it overridable 
Now defaults to 'env.abort' as imported in lib/env.ts, but can be overridden through '--use abort=someThingElseOrNothingAtAll'
 2018-05-21 18:48:29 +02:00
dcodeIO
6c0a5c47d9 Update Binaryen and take care of WebAssembly/binaryen#1547 2018-05-14 16:55:55 +02:00
dcodeIO
e415377cda Avoid trampolines where optional arguments are constant literals, see #102; Fix temporary local flags not being cleared; Fix inlined temporary locals not being free'd; Fix inlined flows not breaking after returns; Allow changetype of u32s, i.e. function pointers 2018-05-11 16:31:56 +02:00
dcodeIO
ef9b43740d Eliminate leftover temporary function types using latest Binaryen 2018-05-09 16:33:42 +02:00
dcodeIO
25a1f6230a Suppress some unnecessary blocks and nops; Fix compilation of always 'break'ing 'do's 2018-05-06 05:46:35 +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
Daniel Wirtz
623597c23a
Make the transition to ArrayBuffer backed Arrays (#70) 
* Traverse base classes when resolving overloads
* Implement preliminary TypedArray accessors
* Extract decorator flags from common flags to make space
* Add '**' overload
* Implement basic explicit inlining
* Support inlining of instance methods
* Reduce number of required locals when inlining
* Implement inlining of operator overloads
* Fix issues when inlining generic functions
 2018-04-11 23:35:19 +02:00
dcodeIO
acfef646ef Update dist files; Also parse name and source mapping sections in lib/parse 2018-04-04 03:41:04 +02:00