[PATCH] D20468: [X86][AVX] Ensure zero-extension of _mm256_extract_epi8 and _mm256_extract_epi16

[Simon Pilgrim via cfe-commits]

RKSimon created this revision.
RKSimon added reviewers: mkuper, craig.topper, kromanova, spatel.
RKSimon added a subscriber: cfe-commits.
RKSimon set the repository for this revision to rL LLVM.

Ensure _mm256_extract_epi8 and _mm256_extract_epi16 zero extend their i8/i16 result to i32. This matches _mm_extract_epi8 and _mm_extract_epi16.

Fix for PR27594 

Katya - I've updated the doxygen comments for _mm256_extract_epi8 and _mm256_extract_epi16, I guess this will need to be updated in Sony's intrinsics document for the next regeneration?

Repository:
  rL LLVM

http://reviews.llvm.org/D20468

Files:
  lib/Headers/avxintrin.h
  test/CodeGen/avx-builtins.c

Index: test/CodeGen/avx-builtins.c
===================================================================
--- test/CodeGen/avx-builtins.c
+++ test/CodeGen/avx-builtins.c
@@ -314,21 +314,19 @@
   return _mm256_dp_ps(A, B, 7);
 }
 
-// FIXME: ZEXT instead of SEXT
 int test_mm256_extract_epi8(__m256i A) {
   // CHECK-LABEL: test_mm256_extract_epi8
   // CHECK: and i32 %{{.*}}, 31
   // CHECK: extractelement <32 x i8> %{{.*}}, i32 %{{.*}}
-  // CHECK: ext i8 %{{.*}} to i32
+  // CHECK: zext i8 %{{.*}} to i32
   return _mm256_extract_epi8(A, 32);
 }
 
-// FIXME: ZEXT instead of SEXT
 int test_mm256_extract_epi16(__m256i A) {
   // CHECK-LABEL: test_mm256_extract_epi16
   // CHECK: and i32 %{{.*}}, 15
   // CHECK: extractelement <16 x i16> %{{.*}}, i32 %{{.*}}
-  // CHECK: ext i16 %{{.*}} to i32
+  // CHECK: zext i16 %{{.*}} to i32
   return _mm256_extract_epi16(A, 16);
 }
 
Index: lib/Headers/avxintrin.h
===================================================================
--- lib/Headers/avxintrin.h
+++ lib/Headers/avxintrin.h
@@ -1875,13 +1875,13 @@
 /// \param __imm
 ///    An immediate integer operand with bits [3:0] determining which vector
 ///    element is extracted and returned.
-/// \returns A 32-bit integer containing the extracted 16 bits of extended
+/// \returns A 32-bit integer containing the extracted 16 bits of zero extended
 ///    packed data.
 static __inline int __DEFAULT_FN_ATTRS
 _mm256_extract_epi16(__m256i __a, const int __imm)
 {
   __v16hi __b = (__v16hi)__a;
-  return __b[__imm & 15];
+  return (unsigned short)__b[__imm & 15];
 }
 
 /// \brief Takes a [32 x i8] vector and returns the vector element value
@@ -1897,13 +1897,13 @@
 /// \param __imm
 ///    An immediate integer operand with bits [4:0] determining which vector
 ///    element is extracted and returned.
-/// \returns A 32-bit integer containing the extracted 8 bits of extended packed
-///    data.
+/// \returns A 32-bit integer containing the extracted 8 bits of zero extended
+///    packed data.
 static __inline int __DEFAULT_FN_ATTRS
 _mm256_extract_epi8(__m256i __a, const int __imm)
 {
   __v32qi __b = (__v32qi)__a;
-  return __b[__imm & 31];
+  return (unsigned char)__b[__imm & 31];
 }
 
 #ifdef __x86_64__


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D20468.57927.patch
Type: text/x-patch
Size: 2282 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20160520/1faff408/attachment.bin>