mirror/sointu
1
0
Fork 0
mirror of https://github.com/vsariola/sointu.git synced 2025-05-28 03:10:24 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(vm): x87 native filter unit was denormalizing and eating up CPU

Browse Source 
When voice was silent, the exponential decays in the filter unit
were causing the high pass component to eventually denormalize,
causing high CPU loads. The solution is the same as in the delay
unit: add and subtract a small number from the value, causing
essentially a flush to zero.
https://en.wikipedia.org/wiki/Subnormal_number

Fixes #68.
This commit is contained in:
5684185+vsariola@users.noreply.github.com 2024-06-19 18:58:20 +03:00
parent a14e21dff6
commit db2d9cac9d
2 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -29,6 +29,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
x87 stack.
### Fixed
- The x87 native filter unit was denormalizing and eating up a lot of CPU ([#68][i68])
- Modulating delaytime in wasm could crash, because delay time was converted to
int with i32.trunc_f32_u. Using i32.trunc_f32_s fixed this.
- When recording notes from VSTI, no track was created for instruments that had
@ -153,6 +154,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
[0.2.0]: https://github.com/vsariola/sointu/compare/v0.1.0...v0.2.0
[0.1.0]: https://github.com/vsariola/sointu/compare/4klang-3.11...v0.1.0
[i65]: https://github.com/vsariola/sointu/issues/65
[i68]: https://github.com/vsariola/sointu/issues/68
[i112]: https://github.com/vsariola/sointu/issues/112
[i116]: https://github.com/vsariola/sointu/issues/116
[i120]: https://github.com/vsariola/sointu/issues/120

3
vm/compiler/templates/amd64-386/effects.asm
View File

@ -156,6 +156,9 @@ su_op_dbgain_mono:
fsubp st2, st0 ; r x-l'
fmul dword [{{.WRK}}+8] ; r*b x-l'
fsubp st1, st0 ; x-l'-r*b
{{- .Float 0.5 | .Prepare | indent 4}}
fadd dword [{{.Float 0.5 | .Use}}] ; add and sub small offset to prevent denormalization
fsub dword [{{.Float 0.5 | .Use}}] ; See for example: https://stackoverflow.com/questions/36781881/why-denormalized-floats-are-so-much-slower-than-other-floats-from-hardware-arch
fst dword [{{.WRK}}+4] ; h'=x-l'-r*b
fmul dword [{{.WRK}}+12] ; f2*h'
fadd dword [{{.WRK}}+8] ; f2*h'+b