This patch implements d16 support for image load, image store and image sample intrinsics.
It depends on the following patch that is pending reviews:
https://reviews.llvm.org/D38906
The LIT tests are still under development and will be ready soon.
Differential D39912
AMDGPU/SI: Implement d16 support for image intrinsics cfang on Nov 10 2017, 11:13 AM. Authored by
Details This patch implements d16 support for image load, image store and image sample intrinsics. The LIT tests are still under development and will be ready soon.
Diff Detail Event TimelineComment Actions Pardon my ignorance, but why isn't include/llvm/IR/IntrinsicsAMDGCN.td being updated? Comment Actions We did not add new intrinsics. We just add support for new data types. In IntrinsicsAMDGCN.td, we have already defined In other wordm llvm.amdgcn.image.load.v4f16 (for example) has already been declared in IntrinsicsAMDGCN.td. And this patch just needs to actually define (implement) it.
Comment Actions
NOTE: We may define more instructions than necessary for the "PACKED", but I would appreciate suggestions to get rid of them.
Comment Actions
Comment Actions Don't know why I didn't received a message after I updated the patch. So ping here with the updating message:
Comment Actions Patched updated! Request for reviewer's check. Thanks. Comment Actions Patch committed to trunk: |