[Clang][AVX512][BUILTIN]Adding intrinsics for range_round_{sd|ss}

Differential Revision: http://reviews.llvm.org/D21002

llvm-svn: 272123

3 files changed, 80 insertions, 0 deletions

diff --git a/clang/include/clang/Basic/BuiltinsX86.def b/clang/include/clang/Basic/BuiltinsX86.def
index 68f68e26efe..10a3103c32b 100644
--- a/clang/include/clang/Basic/BuiltinsX86.def
+++ b/clang/include/clang/Basic/BuiltinsX86.def
@@ -1527,6 +1527,8 @@ TARGET_BUILTIN(__builtin_ia32_rangepd128_mask, "V2dV2dV2dIiV2dUc", "", "avx512vl
 TARGET_BUILTIN(__builtin_ia32_rangepd256_mask, "V4dV4dV4dIiV4dUc", "", "avx512vl,avx512dq")
 TARGET_BUILTIN(__builtin_ia32_rangeps128_mask, "V4fV4fV4fIiV4fUc", "", "avx512vl,avx512dq")
 TARGET_BUILTIN(__builtin_ia32_rangeps256_mask, "V8fV8fV8fIiV8fUc", "", "avx512vl,avx512dq")
+TARGET_BUILTIN(__builtin_ia32_rangesd128_round_mask, "V2dV2dV2dV2dUcIiIi", "", "avx512dq")
+TARGET_BUILTIN(__builtin_ia32_rangess128_round_mask, "V4fV4fV4fV4fUcIiIi", "", "avx512dq")
 TARGET_BUILTIN(__builtin_ia32_reducepd128_mask, "V2dV2dIiV2dUc", "", "avx512vl,avx512dq")
 TARGET_BUILTIN(__builtin_ia32_reducepd256_mask, "V4dV4dIiV4dUc", "", "avx512vl,avx512dq")
 TARGET_BUILTIN(__builtin_ia32_reduceps128_mask, "V4fV4fIiV4fUc", "", "avx512vl,avx512dq")
diff --git a/clang/lib/Headers/avx512dqintrin.h b/clang/lib/Headers/avx512dqintrin.h
index 6180b40546a..19514cf489a 100644
--- a/clang/lib/Headers/avx512dqintrin.h
+++ b/clang/lib/Headers/avx512dqintrin.h
@@ -785,6 +785,48 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
                                          (__v16sf)_mm512_setzero_ps(), \
                                          (__mmask16)(U), (int)(R)); })
 
+#define _mm_range_round_ss(A, B, C, R) __extension__ ({           \
+  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                               (__v4sf)(__m128)(B), \
+                                               (__v4sf)_mm_setzero_ps(), \
+                                               (__mmask8) -1, (int)(C),\
+                                               (int)(R)); })
+
+#define _mm_mask_range_round_ss(W, U, A, B, C, R) __extension__ ({ \
+  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                               (__v4sf)(__m128)(B), \
+                                               (__v4sf)(__m128)(W),\
+                                               (__mmask8)(U), (int)(C),\
+                                               (int)(R)); })
+
+#define _mm_maskz_range_round_ss(U, A, B, C, R) __extension__ ({ \
+  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                               (__v4sf)(__m128)(B), \
+                                               (__v4sf)_mm_setzero_ps(), \
+                                               (__mmask8)(U), (int)(C),\
+                                               (int)(R)); })
+
+#define _mm_range_round_sd(A, B, C, R) __extension__ ({           \
+  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                (__v2df)(__m128d)(B), \
+                                                (__v2df)_mm_setzero_pd(), \
+                                                (__mmask8) -1, (int)(C),\
+                                                (int)(R)); })
+
+#define _mm_mask_range_round_sd(W, U, A, B, C, R) __extension__ ({ \
+  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                (__v2df)(__m128d)(B), \
+                                                (__v2df)(__m128d)(W),\
+                                                (__mmask8)(U), (int)(C),\
+                                                (int)(R)); })
+
+#define _mm_maskz_range_round_sd(U, A, B, C, R) __extension__ ({ \
+  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                (__v2df)(__m128d)(B), \
+                                                (__v2df)_mm_setzero_pd(), \
+                                                (__mmask8)(U), (int)(C),\
+                                                (int)(R)); })
+
 #define _mm512_reduce_pd(A, B) __extension__ ({             \
   (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
                                            (__v8df)_mm512_setzero_pd(), \
diff --git a/clang/test/CodeGen/avx512dq-builtins.c b/clang/test/CodeGen/avx512dq-builtins.c
index c1dea8c69a3..fe54e391577 100644
--- a/clang/test/CodeGen/avx512dq-builtins.c
+++ b/clang/test/CodeGen/avx512dq-builtins.c
@@ -635,6 +635,42 @@ __m512d test_mm512_maskz_range_round_pd(__mmask8 __U, __m512d __A, __m512d __B)
   return _mm512_maskz_range_round_pd(__U, __A, __B, 4, 8); 
 }
 
+__m128d test_mm512_range_round_sd(__m128d __A, __m128d __B) {
+  // CHECK-LABEL: @test_mm512_range_round_sd
+  // CHECK: @llvm.x86.avx512.mask.range.sd
+  return _mm_range_round_sd(__A, __B, 4, 8); 
+}
+
+__m128d test_mm512_mask_range_round_sd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
+  // CHECK-LABEL: test_mm512_mask_range_round_sd
+  // CHECK: @llvm.x86.avx512.mask.range.sd
+  return _mm_mask_range_round_sd(__W, __U, __A, __B, 4, 8); 
+}
+
+__m128d test_mm512_maskz_range_round_sd(__mmask8 __U, __m128d __A, __m128d __B) {
+  // CHECK-LABEL: @test_mm512_maskz_range_round_sd
+  // CHECK: @llvm.x86.avx512.mask.range.sd
+  return _mm_maskz_range_round_sd(__U, __A, __B, 4, 8); 
+}
+
+__m128d test_mm512_range_round_ss(__m128d __A, __m128d __B) {
+  // CHECK-LABEL: @test_mm512_range_round_ss
+  // CHECK: @llvm.x86.avx512.mask.range.ss
+  return _mm_range_round_ss(__A, __B, 4, 8); 
+}
+
+__m128d test_mm512_mask_range_round_ss(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
+  // CHECK-LABEL: @test_mm512_mask_range_round_ss
+  // CHECK: @llvm.x86.avx512.mask.range.ss
+  return _mm_mask_range_round_ss(__W, __U, __A, __B, 4, 8); 
+}
+
+__m128 test_mm512_maskz_range_round_ss(__mmask8 __U, __m128 __A, __m128 __B) {
+  // CHECK-LABEL: @test_mm512_maskz_range_round_ss
+  // CHECK: @llvm.x86.avx512.mask.range.ss
+  return _mm_maskz_range_round_ss(__U, __A, __B, 4, 8); 
+}
+
 __m512 test_mm512_range_ps(__m512 __A, __m512 __B) {
   // CHECK-LABEL: @test_mm512_range_ps
   // CHECK: @llvm.x86.avx512.mask.range.ps.512