[X86, AVX2] Replace inserti128 and extracti128 intrinsics with generic shuffles

This is nearly identical to the v*f128_si256 parts of r231792 and r232052.

AVX2 introduced proper integer variants of the hacked integer insert/extract
C intrinsics that were created for this same functionality with AVX1.

This should complete the front end fixes for insert/extract128 intrinsics. 
Corresponding LLVM patch to follow.

llvm-svn: 232109

2 files changed, 15 insertions, 10 deletions

diff --git a/clang/lib/Headers/avx2intrin.h b/clang/lib/Headers/avx2intrin.h
index af43bec0efd..7485bddb41b 100644
--- a/clang/lib/Headers/avx2intrin.h
+++ b/clang/lib/Headers/avx2intrin.h
@@ -874,14 +874,21 @@ _mm256_permutevar8x32_ps(__m256 __a, __m256 __b)
   __m256i __V2 = (V2); \
   (__m256i)__builtin_ia32_permti256(__V1, __V2, (M)); })
 
-#define _mm256_extracti128_si256(A, O) __extension__ ({ \
-  __m256i __A = (A); \
-  (__m128i)__builtin_ia32_extract128i256(__A, (O)); })
-
-#define _mm256_inserti128_si256(V1, V2, O) __extension__ ({ \
-  __m256i __V1 = (V1); \
-  __m128i __V2 = (V2); \
-  (__m256i)__builtin_ia32_insert128i256(__V1, __V2, (O)); })
+#define _mm256_extracti128_si256(V, M) __extension__ ({ \
+  (__m128i)__builtin_shufflevector( \
+    (__v4di)(V), \
+    (__v4di)(_mm256_setzero_si256()), \
+    (((M) & 1) ? 2 : 0), \
+    (((M) & 1) ? 3 : 1) );})
+
+#define _mm256_inserti128_si256(V1, V2, M) __extension__ ({ \
+  (__m256i)__builtin_shufflevector( \
+    (__v4di)(V1), \
+    (__v4di)_mm256_castsi128_si256((__m128i)(V2)), \
+    (((M) & 1) ? 0 : 4), \
+    (((M) & 1) ? 1 : 5), \
+    (((M) & 1) ? 4 : 2), \
+    (((M) & 1) ? 5 : 3) );})
 
 static __inline__ __m256i __attribute__((__always_inline__, __nodebug__))
 _mm256_maskload_epi32(int const *__X, __m256i __M)
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 7a4a370adc2..60382e8b616 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -882,8 +882,6 @@ bool Sema::CheckX86BuiltinFunctionCall(unsigned BuiltinID, CallExpr *TheCall) {
   switch (BuiltinID) {
   default: return false;
   case X86::BI_mm_prefetch: i = 1; l = 0; u = 3; break;
-  case X86::BI__builtin_ia32_extract128i256: i = 1, l = 0, u = 1; break;
-  case X86::BI__builtin_ia32_insert128i256: i = 2, l = 0; u = 1; break;
   case X86::BI__builtin_ia32_sha1rnds4: i = 2, l = 0; u = 3; break;
   case X86::BI__builtin_ia32_vpermil2pd:
   case X86::BI__builtin_ia32_vpermil2pd256: