[PATCH] D15675: AVX512: Fix TRUNCATE lowering vector to vector i1.

[Igor Breger via llvm-commits]

igorb added inline comments.

================
Comment at: lib/Target/X86/X86ISelLowering.cpp:13226
@@ +13225,3 @@
+    // Use AND with 1 ( memory access) and TESTM.
+    if (InVT == MVT::v64i8) {
+      SDValue OneV = DAG.getBitcast(MVT::v16i32, DAG.getConstant(1, DL, InVT));
----------------
delena wrote:
> 32i8?
32i8/16i8 can be implememnted by extending to 32i16/32i32 to avoid memory access


Repository:
  rL LLVM

http://reviews.llvm.org/D15675