bfloat16 is stored internally as a double, so we can't direct use Type::getIntOrFloatBitWidth.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Paths
| Differential D75133
[mlir][DenseElementsAttr] Fix storage size for bfloat16 when parsing from hex. ClosedPublic Authored by rriddle on Feb 25 2020, 12:05 PM.
Details Summary bfloat16 is stored internally as a double, so we can't direct use Type::getIntOrFloatBitWidth.
Diff Detail
Event TimelineThis revision is now accepted and ready to land.Feb 25 2020, 12:18 PM Closed by commit rGb3e6487f02ac: [mlir][DenseElementsAttr] Fix storage size for bfloat16 when parsing from hex. (authored by rriddle). · Explain WhyFeb 25 2020, 3:05 PM This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 246584 mlir/lib/Parser/Parser.cpp
mlir/test/IR/dense-elements-hex.mlir
|