[PATCH] D11564: [X86][AVX512bw] add convert i16 to i8 and unpack intrinsics

Michael Kuperstein michael.m.kuperstein at intel.com
Wed Jul 29 00:44:47 PDT 2015


mkuper added inline comments.

================
Comment at: lib/Headers/avx512bwintrin.h:1403
@@ +1402,3 @@
+  return (__m256i) __builtin_ia32_pmovwb512_mask ((__v32hi) __A,
+              (__v32qi) __O, __M);
+}
----------------
Sorry for the nitpicking, but, for consistency, line-break before the __M?

================
Comment at: lib/Headers/avx512bwintrin.h:1484
@@ +1483,3 @@
+                 (__v64qi) __B,
+               (__v64qi) _mm512_setzero_qi(),
+                 (__mmask64) __U);
----------------
Have a tab here, perhaps?


http://reviews.llvm.org/D11564







More information about the llvm-commits mailing list