diff options
Diffstat (limited to 'results/scraper/box64/520')
| -rw-r--r-- | results/scraper/box64/520 | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/results/scraper/box64/520 b/results/scraper/box64/520 new file mode 100644 index 000000000..daeb7a12a --- /dev/null +++ b/results/scraper/box64/520 @@ -0,0 +1,14 @@ +80-bit floating-point math on ppc64le +From [this comment](https://github.com/ptitSeb/box64/issues/242#issuecomment-1052656727) by @ptitSeb : + +> SSE/SSE2 instruction are converted t the underling SIMD instruction. Same for x87 that are converted to Float and Double operation (ignoring 80bits operation for most part). + +[According to](https://github.com/FEX-Emu/FEX/issues/2409#issuecomment-1432585400) @awilfox : + +> There is quad-float support in hardware with ISA 3.0 (Power9). + +It might be interesting to support 80-bit x87 math on POWER9 via quad-precision floating-point math, for a speed-up when the default [BOX64_X87_NO80BITS=0](https://github.com/ptitSeb/box64/blob/main/docs/USAGE.md#box64_x87_no80bits-) is used. + +My understanding is that quad float is only hardware-accelerated in POWER9 and higher (so POWER8LE users would need to disable it), and is only aliased to `long double` on a subset of distros (e.g. recent Fedora, grep [Talospace](https://talospace.com/) for articles that mention "long double"). + +It looks to me like the GCC options you want are `-mfloat128 -mfloat128-hardware`, and then use the `__float128` data type instead of `long double` so that it works as expected on older distros. \ No newline at end of file |