[PATCH] D68374: [X86] Add v32i8 shuffle lowering strategy to recognize two v4i64 vectors truncated to v4i8 and concatenated into the lower 8 bytes with undef/zero upper bytes.
Simon Pilgrim via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 3 04:02:27 PDT 2019
RKSimon added inline comments.
================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:15539
+ return SDValue();
+ }
+
----------------
isSequentialOrUndefInRange(Mask, 0, 8, 0, 8) ?
================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:15542
+ // Upper bits need to be zeroable.
+ for (int i = 8; i != 24; ++i)
+ if (!Zeroable[i])
----------------
Zeroable.extractBits(16, 8).isAllOnesValue() ?
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D68374/new/
https://reviews.llvm.org/D68374
More information about the llvm-commits
mailing list