Add missing mask[z]_roundscale_[round]_s[d,s] intrinsics

gcc/
	* config/i386/avx512fintrin.h (_mm_mask_roundscale_ss,
	_mm_maskz_roundscale_ss, _mm_maskz_roundscale_round_ss,
	_mm_maskz_roundscale_round_ss, _mm_mask_roundscale_sd,
	_mm_maskz_roundscale_sd, _mm_mask_roundscale_round_sd,
	_mm_maskz_roundscale_round_sd): New intrinsics.
	(_mm_roundscale_ss, _mm_roundscale_round_ss): Use
	__builtin_ia32_rndscales?_mask_round builtins instead of
	__builtin_ia32_rndscales?_round.
	* config/i386/i386-builtin.def (__builtin_ia32_rndscaless_round,
	__builtin_ia32_rndscalesd_round): Remove.
	(__builtin_ia32_rndscaless_mask_round,
	__builtin_ia32_rndscalesd_mask_round): New intrinsics.
	* config/i386/sse.md
	(avx512f_rndscale<mode><round_saeonly_name>): Renamed to ...
	(avx512f_rndscale<mode><mask_scalar_name><round_saeonly_scalar_name>):
	 ... this, adjust and add subst atrributes to make it maskable.

gcc/testsuite/
	* gcc.target/i386/avx512f-vrndscaless-1.c: Add scan-assembler-times
	directives for newly expected instructions.
	* gcc.target/i386/avx512f-vrndscalesd-1.c: Likewise.
	* gcc.target/i386/avx512f-vrndscaless-2.c
	(avx512f_test): Add tests for new intrinsics.
	* gcc.target/i386/avx512f-vrndscalesd-2.c: Likewise.
	* gcc.target/i386/avx-1.c (__builtin_ia32_rndscalefss_round,
	__builtin_ia32_rndscalefsd_round): Remove.
	(__builtin_ia32_rndscalefss_mask_round,
	__builtin_ia32_rndscalefsd_mask_round): Define.
	* gcc.target/i386/sse-13.c: Ditto.
	* gcc.target/i386/sse-23.c: Ditto.

From-SVN: r276986

3 files changed, 241 insertions, 30 deletions

diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
index c2ca4e1..1d08f01 100644
--- a/gcc/config/i386/avx512fintrin.h
+++ b/gcc/config/i386/avx512fintrin.h
@@ -9169,10 +9169,43 @@ _mm512_maskz_roundscale_round_pd (__mmask8 __A, __m512d __B,
 
 extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm, const int __R)
+_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm,
+			 const int __R)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+					  (__v4sf) __B, __imm,
+					  (__v4sf)
+					  _mm_setzero_ps (),
+					  (__mmask8) -1,
+					  __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_ss (__m128 __A, __mmask8 __B, __m128 __C,
+			      __m128 __D, const int __imm, const int __R)
 {
-  return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
-						   (__v4sf) __B, __imm, __R);
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+					  (__v4sf) __D, __imm,
+					  (__v4sf) __A,
+					  (__mmask8) __B,
+					  __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_ss (__mmask8 __A, __m128 __B, __m128 __C,
+			       const int __imm, const int __R)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+					  (__v4sf) __C, __imm,
+					  (__v4sf)
+					  _mm_setzero_ps (),
+					  (__mmask8) __A,
+					  __R);
 }
 
 extern __inline __m128d
@@ -9180,8 +9213,40 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_round_sd (__m128d __A, __m128d __B, const int __imm,
 			 const int __R)
 {
-  return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
-						    (__v2df) __B, __imm, __R);
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+					  (__v2df) __B, __imm,
+					  (__v2df)
+					  _mm_setzero_pd (),
+					  (__mmask8) -1,
+					  __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_sd (__m128d __A, __mmask8 __B, __m128d __C,
+			      __m128d __D, const int __imm, const int __R)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+					  (__v2df) __D, __imm,
+					  (__v2df) __A,
+					  (__mmask8) __B,
+					  __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_sd (__mmask8 __A, __m128d __B, __m128d __C,
+			       const int __imm, const int __R)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+					  (__v2df) __C, __imm,
+					  (__v2df)
+					  _mm_setzero_pd (),
+					  (__mmask8) __A,
+					  __R);
 }
 
 #else
@@ -9211,12 +9276,54 @@ _mm_roundscale_round_sd (__m128d __A, __m128d __B, const int __imm,
 					     (int)(C),			\
 					     (__v8df)_mm512_setzero_pd(),\
 					     (__mmask8)(A), R))
-#define _mm_roundscale_round_ss(A, B, C, R)					\
-  ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A),	\
-    (__v4sf)(__m128)(B), (int)(C), R))
-#define _mm_roundscale_round_sd(A, B, C, R)					\
-  ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A),	\
-    (__v2df)(__m128d)(B), (int)(C), R))
+#define _mm_roundscale_round_ss(A, B, I, R)				\
+  ((__m128)								\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),		\
+					 (__v4sf) (__m128) (B),		\
+					 (int) (I),			\
+					 (__v4sf) _mm_setzero_ps (),	\
+					 (__mmask8) (-1),		\
+					 (int) (R)))
+#define _mm_mask_roundscale_round_ss(A, U, B, C, I, R)		\
+  ((__m128)							\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B),	\
+					 (__v4sf) (__m128) (C),	\
+					 (int) (I),		\
+					 (__v4sf) (__m128) (A),	\
+					 (__mmask8) (U),	\
+					 (int) (R)))
+#define _mm_maskz_roundscale_round_ss(U, A, B, I, R)			\
+  ((__m128)								\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),		\
+					 (__v4sf) (__m128) (B),		\
+					 (int) (I),			\
+					 (__v4sf) _mm_setzero_ps (),	\
+					 (__mmask8) (U),		\
+					 (int) (R)))
+#define _mm_roundscale_round_sd(A, B, I, R)				\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),	\
+					 (__v2df) (__m128d) (B),	\
+					 (int) (I),			\
+					 (__v2df) _mm_setzero_pd (),	\
+					 (__mmask8) (-1),		\
+					 (int) (R)))
+#define _mm_mask_roundscale_round_sd(A, U, B, C, I, R)			\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B),	\
+					 (__v2df) (__m128d) (C),	\
+					 (int) (I),			\
+					 (__v2df) (__m128d) (A),	\
+					 (__mmask8) (U),		\
+					 (int) (R)))
+#define _mm_maskz_roundscale_round_sd(U, A, B, I, R)			\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),	\
+					 (__v2df) (__m128d) (B),	\
+					 (int) (I),			\
+					 (__v2df) _mm_setzero_pd (),	\
+					 (__mmask8) (U),		\
+					 (int) (R)))
 #endif
 
 extern __inline __m512
@@ -14812,18 +14919,81 @@ extern __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_ss (__m128 __A, __m128 __B, const int __imm)
 {
-  return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
-						   (__v4sf) __B, __imm,
-						   _MM_FROUND_CUR_DIRECTION);
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+					  (__v4sf) __B, __imm,
+					  (__v4sf)
+					  _mm_setzero_ps (),
+					  (__mmask8) -1,
+					  _MM_FROUND_CUR_DIRECTION);
+}
+
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_ss (__m128 __A, __mmask8 __B, __m128 __C, __m128 __D,
+			const int __imm)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+					  (__v4sf) __D, __imm,
+					  (__v4sf) __A,
+					  (__mmask8) __B,
+					  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_ss (__mmask8 __A, __m128 __B, __m128 __C,
+			 const int __imm)
+{
+  return (__m128)
+    __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+					  (__v4sf) __C, __imm,
+					  (__v4sf)
+					  _mm_setzero_ps (),
+					  (__mmask8) __A,
+					  _MM_FROUND_CUR_DIRECTION);
 }
 
 extern __inline __m128d
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_roundscale_sd (__m128d __A, __m128d __B, const int __imm)
 {
-  return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
-						    (__v2df) __B, __imm,
-						   _MM_FROUND_CUR_DIRECTION);
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+					  (__v2df) __B, __imm,
+					  (__v2df)
+					  _mm_setzero_pd (),
+					  (__mmask8) -1,
+					  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_sd (__m128d __A, __mmask8 __B, __m128d __C, __m128d __D,
+			const int __imm)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+					  (__v2df) __D, __imm,
+					  (__v2df) __A,
+					  (__mmask8) __B,
+					  _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_sd (__mmask8 __A, __m128d __B, __m128d __C,
+			 const int __imm)
+{
+  return (__m128d)
+    __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+					  (__v2df) __C, __imm,
+					  (__v2df)
+					  _mm_setzero_pd (),
+					  (__mmask8) __A,
+					  _MM_FROUND_CUR_DIRECTION);
 }
 
 #else
@@ -14853,12 +15023,54 @@ _mm_roundscale_sd (__m128d __A, __m128d __B, const int __imm)
 					     (int)(C),			\
 					     (__v8df)_mm512_setzero_pd(),\
 					     (__mmask8)(A), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_ss(A, B, C)					\
-  ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A),	\
-  (__v4sf)(__m128)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_sd(A, B, C)					\
-  ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A),	\
-    (__v2df)(__m128d)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_ss(A, B, I)					\
+  ((__m128)								\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),		\
+					 (__v4sf) (__m128) (B),		\
+					 (int) (I),			\
+					 (__v4sf) _mm_setzero_ps (),	\
+					 (__mmask8) (-1),		\
+					 _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_ss(A, U, B, C, I)				\
+  ((__m128)								\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B),		\
+					 (__v4sf) (__m128) (C),		\
+					 (int) (I),			\
+					 (__v4sf) (__m128) (A),		\
+					 (__mmask8) (U),		\
+					 _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_ss(U, A, B, I)				\
+  ((__m128)								\
+   __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A),		\
+					 (__v4sf) (__m128) (B),		\
+					 (int) (I),			\
+					 (__v4sf) _mm_setzero_ps (),	\
+					 (__mmask8) (U),		\
+					 _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_sd(A, B, I)					\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),	\
+					 (__v2df) (__m128d) (B),	\
+					 (int) (I),			\
+					 (__v2df) _mm_setzero_pd (),	\
+					 (__mmask8) (-1),		\
+					 _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_sd(A, U, B, C, I)				\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B),	\
+					 (__v2df) (__m128d) (C),	\
+					 (int) (I),			\
+					 (__v2df) (__m128d) (A),	\
+					 (__mmask8) (U),		\
+					 _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_sd(U, A, B, I)				\
+  ((__m128d)								\
+   __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A),	\
+					 (__v2df) (__m128d) (B),	\
+					 (int) (I),			\
+					 (__v2df) _mm_setzero_pd (),	\
+					 (__mmask8) (U),		\
+					 _MM_FROUND_CUR_DIRECTION))
 #endif
 
 #ifdef __OPTIMIZE__
diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index 6ac820e..1102833 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -2828,8 +2828,8 @@ BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_sse_vmmulv4sf3_round, "__builtin_ia3
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_sse_vmmulv4sf3_mask_round, "__builtin_ia32_mulss_mask_round", IX86_BUILTIN_MULSS_MASK_ROUND, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SF_UQI_INT)
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev8df_mask_round, "__builtin_ia32_rndscalepd_mask", IX86_BUILTIN_RNDSCALEPD, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI_INT)
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev16sf_mask_round, "__builtin_ia32_rndscaleps_mask", IX86_BUILTIN_RNDSCALEPS, UNKNOWN, (int) V16SF_FTYPE_V16SF_INT_V16SF_HI_INT)
-BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev2df_round, "__builtin_ia32_rndscalesd_round", IX86_BUILTIN_RNDSCALESD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT_INT)
-BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev4sf_round, "__builtin_ia32_rndscaless_round", IX86_BUILTIN_RNDSCALESS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT_INT)
+BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev2df_mask_round, "__builtin_ia32_rndscalesd_mask_round", IX86_BUILTIN_RNDSCALESD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT_V2DF_UQI_INT)
+BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev4sf_mask_round, "__builtin_ia32_rndscaless_mask_round", IX86_BUILTIN_RNDSCALESS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT_V4SF_UQI_INT)
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_scalefv8df_mask_round, "__builtin_ia32_scalefpd512_mask", IX86_BUILTIN_SCALEFPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_UQI_INT)
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_scalefv16sf_mask_round, "__builtin_ia32_scalefps512_mask", IX86_BUILTIN_SCALEFPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT)
 BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vmscalefv2df_mask_round, "__builtin_ia32_scalefsd_mask_round", IX86_BUILTIN_SCALEFSD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DF_UQI_INT)
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 07922a1..f474eed 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -9694,18 +9694,17 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "avx512f_rndscale<mode><round_saeonly_name>"
+(define_insn "avx512f_rndscale<mode><mask_scalar_name><round_saeonly_scalar_name>"
   [(set (match_operand:VF_128 0 "register_operand" "=v")
 	(vec_merge:VF_128
 	  (unspec:VF_128
-	    [(match_operand:VF_128 1 "register_operand" "v")
-	     (match_operand:VF_128 2 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")
+	    [(match_operand:VF_128 2 "<round_saeonly_scalar_nimm_predicate>" "<round_saeonly_scalar_constraint>")
 	     (match_operand:SI 3 "const_0_to_255_operand")]
 	    UNSPEC_ROUND)
-	  (match_dup 1)
+	  (match_operand:VF_128 1 "register_operand" "v")
 	  (const_int 1)))]
   "TARGET_AVX512F"
-  "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %<iptr>2<round_saeonly_op4>, %3}"
+  "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_scalar_mask_op4>%2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %<iptr>2<round_saeonly_scalar_mask_op4>, %3}"
   [(set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<MODE>")])