| commit | f6dd32fd3584380730a09b042cfbac852f36eb00 | |
| author | Kerry McLaughlin <kerry.mclaughlin@arm.com> | |
| Mon, 7 Dec 2020 10:39:04 +0000 (7 10:39 +0000) | ||
| committer | Kerry McLaughlin <kerry.mclaughlin@arm.com> | |
| Mon, 7 Dec 2020 12:20:41 +0000 (7 12:20 +0000) | ||
| tree | c71118b60c305c92d94e92e8e5a7ee157d9cccd7 | treesnapshot (tar.gz zip) |
| parent | 980618145bf00a8e212cf3c6db46fb0a83081d69 | commitdiff |
[SVE][CodeGen] Lower scalable masked gathers
Lowers the llvm.masked.gather intrinsics (scalar plus vector addressing mode only)
Changes in this patch:
- Add custom lowering for MGATHER, using getGatherVecOpcode() to choose the appropriate
gather load opcode to use.
- Improve codegen with refineIndexType/refineUniformBase, added in D90942
- Tests added for gather loads with 32 & 64-bit scaled & unscaled offsets.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D91092
Lowers the llvm.masked.gather intrinsics (scalar plus vector addressing mode only)
Changes in this patch:
- Add custom lowering for MGATHER, using getGatherVecOpcode() to choose the appropriate
gather load opcode to use.
- Improve codegen with refineIndexType/refineUniformBase, added in D90942
- Tests added for gather loads with 32 & 64-bit scaled & unscaled offsets.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D91092
12 files changed: