A couple of new entries.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27993 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt
index 4016e4ee7a28ecb9ddc3b345cfcb4b9ae7e0988a..4dd7238b6f5b3bfb479f3d5c89251c667121630c 100644 (file)
--- a/lib/Target/X86/README.txt
+++ b/lib/Target/X86/README.txt
@@ -1107,3 +1107,40 @@ icc generates:
 
 So icc is smart enough to know that B is in memory so it doesn't load it and
 store it back to stack.
+
+//===---------------------------------------------------------------------===//
+
+__m128d test1( __m128d A, __m128d B) {
+  return _mm_shuffle_pd(A, B, 0x3);
+}
+
+compiles to
+
+shufpd $3, %xmm1, %xmm0
+
+Perhaps it's better to use unpckhpd instead?
+
+unpckhpd %xmm1, %xmm0
+
+Don't know if unpckhpd is faster. But it is shorter.
+
+//===---------------------------------------------------------------------===//
+
+typedef short  v8i16 __attribute__ ((__vector_size__ (16)));
+v8i16 test(v8i16 x, v8i16 y) {
+  return x + y;
+}
+
+compiles to
+
+_test:
+       paddw %xmm0, %xmm1
+       movaps %xmm1, %xmm0
+       ret
+
+It should be
+
+       paddw %xmm1, %xmm0
+       ret
+
+since paddw is commutative.