[clang][AVX512][Builtin] adding missing intrinsics for vpmultishiftqb{128|256|512...

Differential Revision: http://reviews.llvm.org/D20521

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@270441 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Basic/BuiltinsX86.def b/include/clang/Basic/BuiltinsX86.def
index 723df2ff8fce2b52467e6380c6c71a219a5e13d6..59c7623e913451ba7137497af38cde757699af76 100644 (file)
--- a/include/clang/Basic/BuiltinsX86.def
+++ b/include/clang/Basic/BuiltinsX86.def
@@ -2276,6 +2276,9 @@ TARGET_BUILTIN(__builtin_ia32_cvtusi2sd32, "V2dV2dUi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2sd64, "V2dV2dULLiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2ss32, "V4fV4fUiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2ss64, "V4fV4fULLiIi","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb512_mask, "V64cV64cV64cV64cULLi","","avx512vbmi")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb128_mask, "V16cV16cV16cV16cUs","","avx512vbmi,avx512vl")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb256_mask, "V32cV32cV32cV32cUi","","avx512vbmi,avx512vl")
 
 // MONITORX/MWAITX
 TARGET_BUILTIN(__builtin_ia32_monitorx, "vv*UiUi", "", "mwaitx")

diff --git a/lib/Headers/avx512vbmiintrin.h b/lib/Headers/avx512vbmiintrin.h
index a2c3b8f2bf92b83a0fa2c955d4fe7ae59a69463f..6340bebd2a1136f5394b891533ce7d6da80bd9d9 100644 (file)
--- a/lib/Headers/avx512vbmiintrin.h
+++ b/lib/Headers/avx512vbmiintrin.h
@@ -108,6 +108,36 @@ _mm512_mask_permutexvar_epi8 (__m512i __W, __mmask64 __M, __m512i __A,
                  (__mmask64) __M);
 }
 
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_mask_multishift_epi64_epi8 (__m512i __W, __mmask64 __M, __m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi) __W,
+                (__mmask64) __M);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_maskz_multishift_epi64_epi8 (__mmask64 __M, __m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi)
+                _mm512_setzero_si512 (),
+                (__mmask64) __M);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_multishift_epi64_epi8 (__m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi)
+                _mm512_undefined_epi32 (),
+                (__mmask64) -1);
+}
+
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif

diff --git a/lib/Headers/avx512vbmivlintrin.h b/lib/Headers/avx512vbmivlintrin.h
index 57989699a86ff9f896c002ff418c878b99c11eb9..105c6d142fa6f4340f3bd52afb639064b910396b 100644 (file)
--- a/lib/Headers/avx512vbmivlintrin.h
+++ b/lib/Headers/avx512vbmivlintrin.h
@@ -29,7 +29,7 @@
 #define __VBMIVLINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__(( __nodebug__, __target__("avx512vbmi,avx512vl")))
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("avx512vbmi,avx512vl")))
 
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -183,6 +183,65 @@ _mm256_mask_permutexvar_epi8 (__m256i __W, __mmask32 __M, __m256i __A,
                  (__mmask32) __M);
 }
 
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_mask_multishift_epi64_epi8 (__m128i __W, __mmask16 __M, __m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi) __W,
+                (__mmask16) __M);
+}
+
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_maskz_multishift_epi64_epi8 (__mmask16 __M, __m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi)
+                _mm_setzero_si128 (),
+                (__mmask16) __M);
+}
+
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_multishift_epi64_epi8 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi)
+                _mm_undefined_si128 (),
+                (__mmask16) -1);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_mask_multishift_epi64_epi8 (__m256i __W, __mmask32 __M, __m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi) __W,
+                (__mmask32) __M);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_maskz_multishift_epi64_epi8 (__mmask32 __M, __m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi)
+                _mm256_setzero_si256 (),
+                (__mmask32) __M);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_multishift_epi64_epi8 (__m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi)
+                _mm256_undefined_si256 (),
+                (__mmask32) -1);
+}
+
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif

diff --git a/test/CodeGen/avx512vbmi-builtins.c b/test/CodeGen/avx512vbmi-builtins.c
index c1aa04cc191150be0459b8b45ed38b2f98a98686..3fe97fd536b9da7aee88ae8212c116a37e4342e2 100644 (file)
--- a/test/CodeGen/avx512vbmi-builtins.c
+++ b/test/CodeGen/avx512vbmi-builtins.c
@@ -46,3 +46,21 @@ __m512i test_mm512_mask_permutexvar_epi8(__m512i __W, __mmask64 __M, __m512i __A
   // CHECK: @llvm.x86.avx512.mask.permvar.qi.512
   return _mm512_mask_permutexvar_epi8(__W, __M, __A, __B); 
 }
+
+__m512i test_mm512_mask_multishift_epi64_epi8(__m512i __W, __mmask64 __M, __m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m512i test_mm512_maskz_multishift_epi64_epi8(__mmask64 __M, __m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m512i test_mm512_multishift_epi64_epi8(__m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_multishift_epi64_epi8(__X, __Y); 
+}

diff --git a/test/CodeGen/avx512vbmivl-builtin.c b/test/CodeGen/avx512vbmivl-builtin.c
index 29864eccdf257ec3e5f0f91dad1ea248df453ed7..549c9656c0de42b9c5d02779fc821e7e936da81e 100644 (file)
--- a/test/CodeGen/avx512vbmivl-builtin.c
+++ b/test/CodeGen/avx512vbmivl-builtin.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -target-feature avx512vbmi -target-feature avx512vl -target-feature avx2 -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -target-feature +avx512vbmi -target-feature +avx512vl -target-feature +avx512bw -emit-llvm -o - -Werror | FileCheck %s
 
 // Don't include mm_malloc.h, it's system specific.
 #define __MM_MALLOC_H
@@ -85,6 +85,43 @@ __m256i test_mm256_mask_permutex2var_epi8(__m256i __A, __mmask32 __U, __m256i __
 
 __m256i test_mm256_maskz_permutex2var_epi8(__mmask32 __U, __m256i __A, __m256i __I, __m256i __B) {
   // CHECK-LABEL: @test_mm256_maskz_permutex2var_epi8
-  // CHECK: @llvm.x86.avx512.mask.vpermt2var.qi.256
+  // CHECK: @llvm.x86.avx512.maskz.vpermt2var.qi.256
   return _mm256_maskz_permutex2var_epi8(__U, __A, __I, __B); 
-}
\ No newline at end of file
+}
+
+__m128i test_mm_mask_multishift_epi64_epi8(__m128i __W, __mmask16 __M, __m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m128i test_mm_maskz_multishift_epi64_epi8(__mmask16 __M, __m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m128i test_mm_multishift_epi64_epi8(__m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_multishift_epi64_epi8(__X, __Y); 
+}
+
+__m256i test_mm256_mask_multishift_epi64_epi8(__m256i __W, __mmask32 __M, __m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m256i test_mm256_maskz_multishift_epi64_epi8(__mmask32 __M, __m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m256i test_mm256_multishift_epi64_epi8(__m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_multishift_epi64_epi8(__X, __Y); 
+}
+