shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
575,643 Commits 1,713 Branches 298 Tags
Commit Graph

4 Commits

Author SHA1 Message Date
Maksim Levental
47f9e0ab2a
[mlir][math] Add vector support for math-to-apfloat (#172715) 
This PR adds vector type support to `math-to-apfloat`.
 2026-01-16 10:14:00 -08:00
Maksim Levental
54eee1e947
Reapply "[mlir][math] Add FP software implementation lowering pass: math-to-apfloat" (#172714) (#172716) 
Reapply https://github.com/llvm/llvm-project/pull/171221 - Fix builder
by linking `MLIRTransformUtils`. Also move headers to
`mlir/Conversion/ArithAndMathToAPFloat`.
 2025-12-17 17:26:37 -08:00
Maksim Levental
621fe03eaa
Revert "[mlir][math] Add FP software implementation lowering pass: math-to-apfloat" (#172714) 
Reverts llvm/llvm-project#171221

Broken builder https://lab.llvm.org/buildbot/#/builders/138/builds/23270
 2025-12-17 10:52:43 -08:00
Maksim Levental
7f1a30ebd2
[mlir][math] Add FP software implementation lowering pass: math-to-apfloat (#171221) 
Add APFloat software implementation for `math.fma`, `math.abs`,
`math.isnan`, `math.isfinite`, `math.isinf`, `math.isnormal` for reduced
precision (`fp4*`, `fp6*`, `fp8*`).
 2025-12-17 18:37:13 +00:00