Commit Graph

5 Commits

Author SHA1 Message Date
Alex Crichton
92394566fc x64: Migrate fabs and bnot vector operations to ISLE
This was my first attempt at transitioning code to ISLE to originally
fix #3327 but that fix has since landed on `main`, so this is instead
now just porting a few operations to ISLE.

Closes #3336
2021-11-16 07:36:49 -08:00
Johnnie Birch
5d5629de60 Fix for issue 3327. Updates Bnot to handle case for NaN float 2021-11-15 18:47:23 -08:00
Johnnie Birch
e3aae9e498 Refactor to avoid too strict assertion. Fix for 3160 and 3161.
Assertion was intended for SIMD lowering of F64x2ConvertLowI32x4U
2021-08-24 19:39:47 -07:00
Alex Crichton
c6b095f9a3 cranelift: Implement nan canonicalization for vectors (#3146)
This fixes some fuzz bugs that came about enabling simd where nan
canonicalization is performed on the fuzzers but cranelift would panic
on these ops for vectors. This adds some custom codegen with `bitselect`
to ensure any nan lanes are canonical-nan lanes in the canonicalized
operations.
2021-08-05 13:44:16 -05:00
Andrew Brown
961c9ea909 test: check unaligned load-coalescing with SIMD operations 2021-07-26 13:39:16 -07:00