i386: Mark x86 masked load builtins pure [PR100312]

Mark x86 AVX and AVX2 masked load builtins pure to enable dead code
elimination and more appropriate alias analysis.

2021-04-29  Uroš Bizjak  <ubizjak@gmail.com>
	    Richard Biener  <rguenther@suse.de>
gcc/
	PR target/100312
	* config/i386/i386-builtin.def (IX86_BUILTIN_MASKLOADPD)
	(IX86_BUILTIN_MASKLOADPS, IX86_BUILTIN_MASKLOADPD256)
	(IX86_BUILTIN_MASKLOADPS256, IX86_BUILTIN_MASKLOADD)
	(IX86_BUILTIN_MASKLOADQ, IX86_BUILTIN_MASKLOADD256)
	(IX86_BUILTIN_MASKLOADQ256): Move from SPECIAL_ARGS
	to PURE_ARGS category.
	* config/i386/i386-builtins.c (ix86_init_mmx_sse_builtins):
	Handle PURE_ARGS category.
	* config/i386/i386-expand.c (ix86_expand_builtin): Ditto.

diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index 4dbd4f2..80c2a2c 100644 (file)
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -187,10 +187,6 @@ BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_movntv4di, "__builtin_ia32_movntdq25
 BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_movntv4df, "__builtin_ia32_movntpd256", IX86_BUILTIN_MOVNTPD256, UNKNOWN, (int) VOID_FTYPE_PDOUBLE_V4DF)
 BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_movntv8sf, "__builtin_ia32_movntps256", IX86_BUILTIN_MOVNTPS256, UNKNOWN, (int) VOID_FTYPE_PFLOAT_V8SF)
 
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadpd, "__builtin_ia32_maskloadpd", IX86_BUILTIN_MASKLOADPD, UNKNOWN, (int) V2DF_FTYPE_PCV2DF_V2DI)
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadps, "__builtin_ia32_maskloadps", IX86_BUILTIN_MASKLOADPS, UNKNOWN, (int) V4SF_FTYPE_PCV4SF_V4SI)
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadpd256, "__builtin_ia32_maskloadpd256", IX86_BUILTIN_MASKLOADPD256, UNKNOWN, (int) V4DF_FTYPE_PCV4DF_V4DI)
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadps256, "__builtin_ia32_maskloadps256", IX86_BUILTIN_MASKLOADPS256, UNKNOWN, (int) V8SF_FTYPE_PCV8SF_V8SI)
 BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskstorepd, "__builtin_ia32_maskstorepd", IX86_BUILTIN_MASKSTOREPD, UNKNOWN, (int) VOID_FTYPE_PV2DF_V2DI_V2DF)
 BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskstoreps, "__builtin_ia32_maskstoreps", IX86_BUILTIN_MASKSTOREPS, UNKNOWN, (int) VOID_FTYPE_PV4SF_V4SI_V4SF)
 BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskstorepd256, "__builtin_ia32_maskstorepd256", IX86_BUILTIN_MASKSTOREPD256, UNKNOWN, (int) VOID_FTYPE_PV4DF_V4DI_V4DF)
@@ -198,10 +194,6 @@ BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskstoreps256, "__builtin_ia32_mask
 
 /* AVX2 */
 BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_movntdqa, "__builtin_ia32_movntdqa256", IX86_BUILTIN_MOVNTDQA256, UNKNOWN, (int) V4DI_FTYPE_PV4DI)
-BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadd, "__builtin_ia32_maskloadd", IX86_BUILTIN_MASKLOADD, UNKNOWN, (int) V4SI_FTYPE_PCV4SI_V4SI)
-BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadq, "__builtin_ia32_maskloadq", IX86_BUILTIN_MASKLOADQ, UNKNOWN, (int) V2DI_FTYPE_PCV2DI_V2DI)
-BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadd256, "__builtin_ia32_maskloadd256", IX86_BUILTIN_MASKLOADD256, UNKNOWN, (int) V8SI_FTYPE_PCV8SI_V8SI)
-BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadq256, "__builtin_ia32_maskloadq256", IX86_BUILTIN_MASKLOADQ256, UNKNOWN, (int) V4DI_FTYPE_PCV4DI_V4DI)
 BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskstored, "__builtin_ia32_maskstored", IX86_BUILTIN_MASKSTORED, UNKNOWN, (int) VOID_FTYPE_PV4SI_V4SI_V4SI)
 BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskstoreq, "__builtin_ia32_maskstoreq", IX86_BUILTIN_MASKSTOREQ, UNKNOWN, (int) VOID_FTYPE_PV2DI_V2DI_V2DI)
 BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskstored256, "__builtin_ia32_maskstored256", IX86_BUILTIN_MASKSTORED256, UNKNOWN, (int) VOID_FTYPE_PV8SI_V8SI_V8SI)
@@ -473,7 +465,22 @@ BDESC (0, OPTION_MASK_ISA2_WIDEKL, CODE_FOR_nothing, "__builtin_ia32_aesdecwide2
 BDESC (0, OPTION_MASK_ISA2_WIDEKL, CODE_FOR_nothing, "__builtin_ia32_aesencwide128kl_u8", IX86_BUILTIN_AESENCWIDE128KLU8, UNKNOWN, (int) UINT8_FTYPE_PV2DI_PCV2DI_PCVOID)
 BDESC (0, OPTION_MASK_ISA2_WIDEKL, CODE_FOR_nothing, "__builtin_ia32_aesencwide256kl_u8", IX86_BUILTIN_AESENCWIDE256KLU8, UNKNOWN, (int) UINT8_FTYPE_PV2DI_PCV2DI_PCVOID)
 
-BDESC_END (SPECIAL_ARGS, ARGS)
+BDESC_END (SPECIAL_ARGS, PURE_ARGS)
+
+/* AVX */
+BDESC_FIRST (pure_args, PURE_ARGS,
+       OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadpd, "__builtin_ia32_maskloadpd", IX86_BUILTIN_MASKLOADPD, UNKNOWN, (int) V2DF_FTYPE_PCV2DF_V2DI)
+BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadps, "__builtin_ia32_maskloadps", IX86_BUILTIN_MASKLOADPS, UNKNOWN, (int) V4SF_FTYPE_PCV4SF_V4SI)
+BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadpd256, "__builtin_ia32_maskloadpd256", IX86_BUILTIN_MASKLOADPD256, UNKNOWN, (int) V4DF_FTYPE_PCV4DF_V4DI)
+BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_maskloadps256, "__builtin_ia32_maskloadps256", IX86_BUILTIN_MASKLOADPS256, UNKNOWN, (int) V8SF_FTYPE_PCV8SF_V8SI)
+
+/* AVX2 */
+BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadd, "__builtin_ia32_maskloadd", IX86_BUILTIN_MASKLOADD, UNKNOWN, (int) V4SI_FTYPE_PCV4SI_V4SI)
+BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadq, "__builtin_ia32_maskloadq", IX86_BUILTIN_MASKLOADQ, UNKNOWN, (int) V2DI_FTYPE_PCV2DI_V2DI)
+BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadd256, "__builtin_ia32_maskloadd256", IX86_BUILTIN_MASKLOADD256, UNKNOWN, (int) V8SI_FTYPE_PCV8SI_V8SI)
+BDESC (OPTION_MASK_ISA_AVX2, 0, CODE_FOR_avx2_maskloadq256, "__builtin_ia32_maskloadq256", IX86_BUILTIN_MASKLOADQ256, UNKNOWN, (int) V4DI_FTYPE_PCV4DI_V4DI)
+
+BDESC_END (PURE_ARGS, ARGS)
 
 /* Builtins with variable number of arguments.  */
 BDESC_FIRST (args, ARGS,

diff --git a/gcc/config/i386/i386-builtins.c b/gcc/config/i386/i386-builtins.c
index 128bd39..b669110 100644 (file)
--- a/gcc/config/i386/i386-builtins.c
+++ b/gcc/config/i386/i386-builtins.c
@@ -108,8 +108,10 @@ BDESC_VERIFYS (IX86_BUILTIN__BDESC_PCMPISTR_FIRST,
               IX86_BUILTIN__BDESC_PCMPESTR_LAST, 1);
 BDESC_VERIFYS (IX86_BUILTIN__BDESC_SPECIAL_ARGS_FIRST,
               IX86_BUILTIN__BDESC_PCMPISTR_LAST, 1);
-BDESC_VERIFYS (IX86_BUILTIN__BDESC_ARGS_FIRST,
+BDESC_VERIFYS (IX86_BUILTIN__BDESC_PURE_ARGS_FIRST,
               IX86_BUILTIN__BDESC_SPECIAL_ARGS_LAST, 1);
+BDESC_VERIFYS (IX86_BUILTIN__BDESC_ARGS_FIRST,
+              IX86_BUILTIN__BDESC_PURE_ARGS_LAST, 1);
 BDESC_VERIFYS (IX86_BUILTIN__BDESC_ROUND_ARGS_FIRST,
               IX86_BUILTIN__BDESC_ARGS_LAST, 1);
 BDESC_VERIFYS (IX86_BUILTIN__BDESC_MULTI_ARG_FIRST,
@@ -527,7 +529,23 @@ ix86_init_mmx_sse_builtins (void)
                 IX86_BUILTIN__BDESC_SPECIAL_ARGS_FIRST,
                 ARRAY_SIZE (bdesc_special_args) - 1);
 
-  /* Add all builtins with variable number of operands.  */
+  /* Add all pure builtins with variable number of operands.  */
+  for (i = 0, d = bdesc_pure_args;
+       i < ARRAY_SIZE (bdesc_pure_args);
+       i++, d++)
+    {
+      BDESC_VERIFY (d->code, IX86_BUILTIN__BDESC_PURE_ARGS_FIRST, i);
+      if (d->name == 0)
+       continue;
+
+      ftype = (enum ix86_builtin_func_type) d->flag;
+      def_builtin_pure (d->mask, d->mask2, d->name, ftype, d->code);
+    }
+  BDESC_VERIFYS (IX86_BUILTIN__BDESC_PURE_ARGS_LAST,
+                IX86_BUILTIN__BDESC_PURE_ARGS_FIRST,
+                ARRAY_SIZE (bdesc_pure_args) - 1);
+
+  /* Add all const builtins with variable number of operands.  */
   for (i = 0, d = bdesc_args;
        i < ARRAY_SIZE (bdesc_args);
        i++, d++)

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 516440e..7699062 100644 (file)
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -13240,6 +13240,14 @@ rdseed_step:
                                               target);
     }
 
+  if (fcode >= IX86_BUILTIN__BDESC_PURE_ARGS_FIRST
+      && fcode <= IX86_BUILTIN__BDESC_PURE_ARGS_LAST)
+    {
+      i = fcode - IX86_BUILTIN__BDESC_PURE_ARGS_FIRST;
+      return ix86_expand_special_args_builtin (bdesc_pure_args + i, exp,
+                                              target);
+    }
+
   if (fcode >= IX86_BUILTIN__BDESC_ARGS_FIRST
       && fcode <= IX86_BUILTIN__BDESC_ARGS_LAST)
     {