PR target/59163

	* config/i386/i386.c (ix86_legitimate_combined_insn): If for
	!TARGET_AVX there is misaligned MEM operand with vector mode
	and get_attr_ssememalign is 0, return false.
	(ix86_expand_special_args_builtin): Add get_pointer_alignment
	computed alignment and for non-temporal loads/stores also
	at least GET_MODE_ALIGNMENT as MEM_ALIGN.
	* config/i386/sse.md
	(<sse>_loadu<ssemodesuffix><avxsizesuffix><mask_name>,
	<sse>_storeu<ssemodesuffix><avxsizesuffix>,
	<sse2_avx_avx512f>_loaddqu<mode><mask_name>,
	<sse2_avx_avx512f>_storedqu<mode>, <sse3>_lddqu<avxsizesuffix>,
	sse_vmrcpv4sf2, sse_vmrsqrtv4sf2, sse2_cvtdq2pd, sse_movhlps,
	sse_movlhps, sse_storehps, sse_loadhps, sse_loadlps,
	*vec_interleave_highv2df, *vec_interleave_lowv2df,
	*vec_extractv2df_1_sse, sse2_movsd, sse4_1_<code>v8qiv8hi2,
	sse4_1_<code>v4qiv4si2, sse4_1_<code>v4hiv4si2,
	sse4_1_<code>v2qiv2di2, sse4_1_<code>v2hiv2di2,
	sse4_1_<code>v2siv2di2, sse4_2_pcmpestr, *sse4_2_pcmpestr_unaligned,
	sse4_2_pcmpestri, sse4_2_pcmpestrm, sse4_2_pcmpestr_cconly,
	sse4_2_pcmpistr, *sse4_2_pcmpistr_unaligned, sse4_2_pcmpistri,
	sse4_2_pcmpistrm, sse4_2_pcmpistr_cconly): Add ssememalign attribute.
	* config/i386/i386.md (ssememalign): New define_attr.

	* g++.dg/torture/pr59163.C: New test.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@205661 138bc75d-0d04-0410-961f-82ee72b054a4

3 files changed, 107 insertions, 4 deletions

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 21963bb28b7..f9b06d13b89 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -5733,6 +5733,17 @@ ix86_legitimate_combined_insn (rtx insn)
 	  bool win;
 	  int j;
 
+	  /* For pre-AVX disallow unaligned loads/stores where the
+	     instructions don't support it.  */
+	  if (!TARGET_AVX
+	      && VECTOR_MODE_P (GET_MODE (op))
+	      && misaligned_operand (op, GET_MODE (op)))
+	    {
+	      int min_align = get_attr_ssememalign (insn);
+	      if (min_align == 0)
+		return false;
+	    }
+
 	  /* A unary operator may be accepted by the predicate, but it
 	     is irrelevant for matching constraints.  */
 	  if (UNARY_P (op))
@@ -32481,11 +32492,12 @@ ix86_expand_args_builtin (const struct builtin_description *d,
 
 static rtx
 ix86_expand_special_args_builtin (const struct builtin_description *d,
-				    tree exp, rtx target)
+				  tree exp, rtx target)
 {
   tree arg;
   rtx pat, op;
   unsigned int i, nargs, arg_adjust, memory;
+  bool aligned_mem = false;
   struct
     {
       rtx op;
@@ -32531,6 +32543,15 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
       nargs = 1;
       klass = load;
       memory = 0;
+      switch (icode)
+	{
+	case CODE_FOR_sse4_1_movntdqa:
+	case CODE_FOR_avx2_movntdqa:
+	  aligned_mem = true;
+	  break;
+	default:
+	  break;
+	}
       break;
     case VOID_FTYPE_PV2SF_V4SF:
     case VOID_FTYPE_PV4DI_V4DI:
@@ -32548,6 +32569,26 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
       klass = store;
       /* Reserve memory operand for target.  */
       memory = ARRAY_SIZE (args);
+      switch (icode)
+	{
+	/* These builtins and instructions require the memory
+	   to be properly aligned.  */
+	case CODE_FOR_avx_movntv4di:
+	case CODE_FOR_sse2_movntv2di:
+	case CODE_FOR_avx_movntv8sf:
+	case CODE_FOR_sse_movntv4sf:
+	case CODE_FOR_sse4a_vmmovntv4sf:
+	case CODE_FOR_avx_movntv4df:
+	case CODE_FOR_sse2_movntv2df:
+	case CODE_FOR_sse4a_vmmovntv2df:
+	case CODE_FOR_sse2_movntidi:
+	case CODE_FOR_sse_movntq:
+	case CODE_FOR_sse2_movntisi:
+	  aligned_mem = true;
+	  break;
+	default:
+	  break;
+	}
       break;
     case V4SF_FTYPE_V4SF_PCV2SF:
     case V2DF_FTYPE_V2DF_PCDOUBLE:
@@ -32604,6 +32645,17 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
 	{
 	  op = ix86_zero_extend_to_Pmode (op);
 	  target = gen_rtx_MEM (tmode, op);
+	  /* target at this point has just BITS_PER_UNIT MEM_ALIGN
+	     on it.  Try to improve it using get_pointer_alignment,
+	     and if the special builtin is one that requires strict
+	     mode alignment, also from it's GET_MODE_ALIGNMENT.
+	     Failure to do so could leak to ix86_legitimate_combined_insn
+	     rejecting all changes to such insns.  */
+	  unsigned int align = get_pointer_alignment (arg);
+	  if (aligned_mem && align < GET_MODE_ALIGNMENT (tmode))
+	    align = GET_MODE_ALIGNMENT (tmode);
+	  if (MEM_ALIGN (target) < align)
+	    set_mem_align (target, align);
 	}
       else
 	target = force_reg (tmode, op);
@@ -32649,8 +32701,17 @@ ix86_expand_special_args_builtin (const struct builtin_description *d,
 	      /* This must be the memory operand.  */
 	      op = ix86_zero_extend_to_Pmode (op);
 	      op = gen_rtx_MEM (mode, op);
-	      gcc_assert (GET_MODE (op) == mode
-			  || GET_MODE (op) == VOIDmode);
+	      /* op at this point has just BITS_PER_UNIT MEM_ALIGN
+		 on it.  Try to improve it using get_pointer_alignment,
+		 and if the special builtin is one that requires strict
+		 mode alignment, also from it's GET_MODE_ALIGNMENT.
+		 Failure to do so could leak to ix86_legitimate_combined_insn
+		 rejecting all changes to such insns.  */
+	      unsigned int align = get_pointer_alignment (arg);
+	      if (aligned_mem && align < GET_MODE_ALIGNMENT (mode))
+		align = GET_MODE_ALIGNMENT (mode);
+	      if (MEM_ALIGN (op) < align)
+		set_mem_align (op, align);
 	    }
 	  else
 	    {
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 6976124d4a8..0c732c7689f 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -402,6 +402,13 @@
 	   (const_string "unknown")]
 	 (const_string "integer")))
 
+;; The minimum required alignment of vector mode memory operands of the SSE
+;; (non-VEX/EVEX) instruction in bits, if it is different from
+;; GET_MODE_ALIGNMENT of the operand, otherwise 0.  If an instruction has
+;; multiple alternatives, this should be conservative maximum of those minimum
+;; required alignments.
+(define_attr "ssememalign" "" (const_int 0))
+
 ;; The (bounding maximum) length of an instruction immediate.
 (define_attr "length_immediate" ""
   (cond [(eq_attr "type" "incdec,setcc,icmov,str,lea,other,multi,idiv,leave,
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 7a47f27e94e..f4efeaa3122 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -931,6 +931,7 @@
 }
   [(set_attr "type" "ssemov")
    (set_attr "movu" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "prefix" "maybe_vex")
    (set (attr "mode")
 	(cond [(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
@@ -961,6 +962,7 @@
 }
   [(set_attr "type" "ssemov")
    (set_attr "movu" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "prefix" "maybe_vex")
    (set (attr "mode")
 	(cond [(ior (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")
@@ -1020,6 +1022,7 @@
 }
   [(set_attr "type" "ssemov")
    (set_attr "movu" "1")
+   (set_attr "ssememalign" "8")
    (set (attr "prefix_data16")
      (if_then_else
        (match_test "TARGET_AVX")
@@ -1059,6 +1062,7 @@
 }
   [(set_attr "type" "ssemov")
    (set_attr "movu" "1")
+   (set_attr "ssememalign" "8")
    (set (attr "prefix_data16")
      (if_then_else
        (match_test "TARGET_AVX")
@@ -1105,6 +1109,7 @@
   "%vlddqu\t{%1, %0|%0, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "movu" "1")
+   (set_attr "ssememalign" "8")
    (set (attr "prefix_data16")
      (if_then_else
        (match_test "TARGET_AVX")
@@ -1369,6 +1374,7 @@
    vrcpss\t{%1, %2, %0|%0, %2, %k1}"
   [(set_attr "isa" "noavx,avx")
    (set_attr "type" "sse")
+   (set_attr "ssememalign" "32")
    (set_attr "atom_sse_attr" "rcp")
    (set_attr "btver2_sse_attr" "rcp")
    (set_attr "prefix" "orig,vex")
@@ -1509,6 +1515,7 @@
    vrsqrtss\t{%1, %2, %0|%0, %2, %k1}"
   [(set_attr "isa" "noavx,avx")
    (set_attr "type" "sse")
+   (set_attr "ssememalign" "32")
    (set_attr "prefix" "orig,vex")
    (set_attr "mode" "SF")])
 
@@ -3853,6 +3860,7 @@
   "%vcvtdq2pd\t{%1, %0|%0, %q1}"
   [(set_attr "type" "ssecvt")
    (set_attr "prefix" "maybe_vex")
+   (set_attr "ssememalign" "64")
    (set_attr "mode" "V2DF")])
 
 (define_insn "<mask_codefor>avx512f_cvtpd2dq512<mask_name>"
@@ -4725,6 +4733,7 @@
    %vmovhps\t{%2, %0|%q0, %2}"
   [(set_attr "isa" "noavx,avx,noavx,avx,*")
    (set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix" "orig,vex,orig,vex,maybe_vex")
    (set_attr "mode" "V4SF,V4SF,V2SF,V2SF,V2SF")])
 
@@ -4770,6 +4779,7 @@
    %vmovlps\t{%2, %H0|%H0, %2}"
   [(set_attr "isa" "noavx,avx,noavx,avx,*")
    (set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix" "orig,vex,orig,vex,maybe_vex")
    (set_attr "mode" "V4SF,V4SF,V2SF,V2SF,V2SF")])
 
@@ -5174,6 +5184,7 @@
    %vmovhlps\t{%1, %d0|%d0, %1}
    %vmovlps\t{%H1, %d0|%d0, %H1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "V2SF,V4SF,V2SF")])
 
@@ -5213,6 +5224,7 @@
    %vmovlps\t{%2, %H0|%H0, %2}"
   [(set_attr "isa" "noavx,avx,noavx,avx,*")
    (set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix" "orig,vex,orig,vex,maybe_vex")
    (set_attr "mode" "V2SF,V2SF,V4SF,V4SF,V2SF")])
 
@@ -5266,6 +5278,7 @@
    %vmovlps\t{%2, %0|%q0, %2}"
   [(set_attr "isa" "noavx,avx,noavx,avx,*")
    (set_attr "type" "sseshuf,sseshuf,ssemov,ssemov,ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "length_immediate" "1,1,*,*,*")
    (set_attr "prefix" "orig,vex,orig,vex,maybe_vex")
    (set_attr "mode" "V4SF,V4SF,V2SF,V2SF,V2SF")])
@@ -6224,7 +6237,8 @@
    vmovlpd\t{%H1, %2, %0|%0, %2, %H1}
    %vmovhpd\t{%1, %0|%q0, %1}"
   [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
-  (set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
+   (set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_data16" "*,*,*,1,*,1")
    (set_attr "prefix" "orig,vex,maybe_vex,orig,vex,maybe_vex")
    (set_attr "mode" "V2DF,V2DF,DF,V1DF,V1DF,V1DF")])
@@ -6368,6 +6382,7 @@
    %vmovlpd\t{%2, %H0|%H0, %2}"
   [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
    (set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_data16" "*,*,*,1,*,1")
    (set_attr "prefix" "orig,vex,maybe_vex,orig,vex,maybe_vex")
    (set_attr "mode" "V2DF,V2DF,DF,V1DF,V1DF,V1DF")])
@@ -6959,6 +6974,7 @@
    movhlps\t{%1, %0|%0, %1}
    movlps\t{%H1, %0|%0, %H1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "mode" "V2SF,V4SF,V2SF")])
 
 ;; Avoid combining registers from different units in a single alternative,
@@ -7051,6 +7067,7 @@
    #"
   [(set_attr "isa" "noavx,avx,noavx,avx,*,*,*")
    (set_attr "type" "ssemov,ssemov,sselog,sselog,ssemov,fmov,imov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_data16" "1,*,*,*,*,*,*")
    (set_attr "prefix" "orig,vex,orig,vex,*,*,*")
    (set_attr "mode" "V1DF,V1DF,V2DF,V2DF,DF,DF,DF")])
@@ -7119,6 +7136,7 @@
 	      (const_string "imov")
 	   ]
 	   (const_string "ssemov")))
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_data16" "*,1,*,*,*,*,1,*,*,*,*")
    (set_attr "length_immediate" "*,*,*,*,*,1,*,*,*,*,*")
    (set_attr "prefix" "maybe_vex,orig,vex,orig,vex,orig,orig,vex,*,*,*")
@@ -7163,6 +7181,7 @@
        (const_string "1")
        (const_string "*")))
    (set_attr "length_immediate" "*,*,*,*,*,1,*,*,*")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix" "orig,vex,orig,vex,maybe_vex,orig,orig,vex,maybe_vex")
    (set_attr "mode" "DF,DF,V1DF,V1DF,V1DF,V2DF,V1DF,V1DF,V1DF")])
 
@@ -11459,6 +11478,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>bw\t{%1, %0|%0, %q1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11499,6 +11519,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>bd\t{%1, %0|%0, %k1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "32")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11534,6 +11555,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>wd\t{%1, %0|%0, %q1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11576,6 +11598,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>bq\t{%1, %0|%0, %w1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "16")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11613,6 +11636,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>wq\t{%1, %0|%0, %k1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "32")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11646,6 +11670,7 @@
   "TARGET_SSE4_1"
   "%vpmov<extsuffix>dq\t{%1, %0|%0, %q1}"
   [(set_attr "type" "ssemov")
+   (set_attr "ssememalign" "64")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
@@ -11939,6 +11964,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "none,load")
    (set_attr "mode" "TI")])
@@ -12001,6 +12027,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "load")
    (set_attr "mode" "TI")])
@@ -12028,6 +12055,7 @@
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
    (set_attr "prefix" "maybe_vex")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "btver2_decode" "vector")
    (set_attr "memory" "none,load")
@@ -12055,6 +12083,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "btver2_decode" "vector")
@@ -12081,6 +12110,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "none,load,none,load")
    (set_attr "btver2_decode" "vector,vector,vector,vector") 
@@ -12134,6 +12164,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "none,load")
    (set_attr "mode" "TI")])
@@ -12187,6 +12218,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "load")
    (set_attr "mode" "TI")])
@@ -12209,6 +12241,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "memory" "none,load")
@@ -12233,6 +12266,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "maybe_vex")
    (set_attr "memory" "none,load")
@@ -12257,6 +12291,7 @@
   [(set_attr "type" "sselog")
    (set_attr "prefix_data16" "1")
    (set_attr "prefix_extra" "1")
+   (set_attr "ssememalign" "8")
    (set_attr "length_immediate" "1")
    (set_attr "memory" "none,load,none,load")
    (set_attr "prefix" "maybe_vex")