[PATCH] D11327: [X86][SSE] Keep 32-bit target i64 vector shifts on SSE unit.
Quentin Colombet
qcolombet at apple.com
Tue Jul 28 14:11:37 PDT 2015
qcolombet added inline comments.
================
Comment at: lib/Target/X86/X86ISelLowering.cpp:17157
@@ +17156,3 @@
+ SplatIndex = SVN->getSplatIndex();
+ Amt = Amt.getOperand(0);
+ }
----------------
We should check that the SplatIndex is covered by the first operand of Amt, otherwise the following code is wrong.
Repository:
rL LLVM
http://reviews.llvm.org/D11327
More information about the llvm-commits
mailing list