The current code for generating nontemporal load outputs the wrong assembly for big endian architecture
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp | ||
---|---|---|
20598 | It looks like this line is too long. Could you run clang-format on the diff? Also, can you extend the comment to say that this applies to little-endian only? |
Comment Actions
LGTM, thanks!
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp | ||
---|---|---|
20598 | I'll reword this to Handle lowering 256 bit non temporal loads into LDNP for little-endian targets. when committing. |
It looks like this line is too long. Could you run clang-format on the diff? Also, can you extend the comment to say that this applies to little-endian only?