i386: Improve vector [GL]E{,U} comparison against vector constants [PR107546]

For integer vector comparisons without XOP before AVX512{F,VL} we are
constrained by only GT and EQ being supported in HW.
For GTU we play tricks to implement it using GT or unsigned saturating
subtraction, for LT/LTU we swap the operands and thus turn it into
GT/GTU.  For LE/LEU we handle it by using GT/GTU and negating the
result and for GE/GEU by using GT/GTU on swapped operands and negating
the result.
If the second operand is a CONST_VECTOR, we can usually do better though,
we can avoid the negation.  For LE/LEU cst by doing LT/LTU cst+1 (and
then cst+1 GT/GTU x) and for GE/GEU cst by doing GT/GTU cst-1, provided
there is no wrap-around on those cst+1 or cst-1.
GIMPLE canonicalizes x < cst to x <= cst-1 etc. (the rule is smaller
absolute value on constant), but only for scalars or uniform vectors,
so in some cases this undoes that canonicalization in order to avoid
the extra negation, but it handles also non-uniform constants.
E.g. with -mavx2 the testcase assembly difference is:
-       movl    $47, %eax
+       movl    $48, %eax
        vmovdqa %xmm0, %xmm1
        vmovd   %eax, %xmm0
        vpbroadcastb    %xmm0, %xmm0
-       vpminsb %xmm0, %xmm1, %xmm0
-       vpcmpeqb        %xmm1, %xmm0, %xmm0
+       vpcmpgtb        %xmm1, %xmm0, %xmm0
and
-       vmovdqa %xmm0, %xmm1
-       vmovdqa .LC1(%rip), %xmm0
-       vpminsb %xmm1, %xmm0, %xmm1
-       vpcmpeqb        %xmm1, %xmm0, %xmm0
+       vpcmpgtb        .LC1(%rip), %xmm0, %xmm0
while with just SSE2:
-       pcmpgtb .LC0(%rip), %xmm0
-       pxor    %xmm1, %xmm1
-       pcmpeqb %xmm1, %xmm0
+       movdqa  %xmm0, %xmm1
+       movdqa  .LC0(%rip), %xmm0
+       pcmpgtb %xmm1, %xmm0
and
-       movdqa  %xmm0, %xmm1
-       movdqa  .LC1(%rip), %xmm0
-       pcmpgtb %xmm1, %xmm0
-       pxor    %xmm1, %xmm1
-       pcmpeqb %xmm1, %xmm0
+       pcmpgtb .LC1(%rip), %xmm0

2022-11-08  Jakub Jelinek  <jakub@redhat.com>

	PR target/107546
	* config/i386/predicates.md (vector_or_const_vector_operand): New
	predicate.
	* config/i386/sse.md (vec_cmp<mode><sseintvecmodelower>,
	vec_cmpv2div2di, vec_cmpu<mode><sseintvecmodelower>,
	vec_cmpuv2div2di): Use nonimmediate_or_const_vector_operand
	predicate instead of nonimmediate_operand and
	vector_or_const_vector_operand instead of vector_operand.
	* config/i386/i386-expand.cc (ix86_expand_int_sse_cmp): For
	LE/LEU or GE/GEU with CONST_VECTOR cop1 try to transform those
	into LE/LEU or GT/GTU with larger or smaller by one cop1 if
	there is no wrap-around.  Force CONST_VECTOR cop0 or cop1 into
	REG.  Formatting fix.

	* gcc.target/i386/pr107546.c: New test.

4 files changed, 113 insertions, 11 deletions

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 2e0d12c0108..9c92b07d5cd 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -4510,15 +4510,86 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1,
 	case GTU:
 	  break;
 
-	case NE:
 	case LE:
 	case LEU:
+	  /* x <= cst can be handled as x < cst + 1 unless there is
+	     wrap around in cst + 1.  */
+	  if (GET_CODE (cop1) == CONST_VECTOR
+	      && GET_MODE_INNER (mode) != TImode)
+	    {
+	      unsigned int n_elts = GET_MODE_NUNITS (mode), i;
+	      machine_mode eltmode = GET_MODE_INNER (mode);
+	      for (i = 0; i < n_elts; ++i)
+		{
+		  rtx elt = CONST_VECTOR_ELT (cop1, i);
+		  if (!CONST_INT_P (elt))
+		    break;
+		  if (code == GE)
+		    {
+		      /* For LE punt if some element is signed maximum.  */
+		      if ((INTVAL (elt) & (GET_MODE_MASK (eltmode) >> 1))
+			  == (GET_MODE_MASK (eltmode) >> 1))
+			break;
+		    }
+		  /* For LEU punt if some element is unsigned maximum.  */
+		  else if (elt == constm1_rtx)
+		    break;
+		}
+	      if (i == n_elts)
+		{
+		  rtvec v = rtvec_alloc (n_elts);
+		  for (i = 0; i < n_elts; ++i)
+		    RTVEC_ELT (v, i)
+		      = GEN_INT (INTVAL (CONST_VECTOR_ELT (cop1, i)) + 1);
+		  cop1 = gen_rtx_CONST_VECTOR (mode, v);
+		  std::swap (cop0, cop1);
+		  code = code == LE ? GT : GTU;
+		  break;
+		}
+	    }
+	  /* FALLTHRU */
+	case NE:
 	  code = reverse_condition (code);
 	  *negate = true;
 	  break;
 
 	case GE:
 	case GEU:
+	  /* x >= cst can be handled as x > cst - 1 unless there is
+	     wrap around in cst - 1.  */
+	  if (GET_CODE (cop1) == CONST_VECTOR
+	      && GET_MODE_INNER (mode) != TImode)
+	    {
+	      unsigned int n_elts = GET_MODE_NUNITS (mode), i;
+	      machine_mode eltmode = GET_MODE_INNER (mode);
+	      for (i = 0; i < n_elts; ++i)
+		{
+		  rtx elt = CONST_VECTOR_ELT (cop1, i);
+		  if (!CONST_INT_P (elt))
+		    break;
+		  if (code == GE)
+		    {
+		      /* For GE punt if some element is signed minimum.  */
+		      if (INTVAL (elt) < 0
+			  && ((INTVAL (elt) & (GET_MODE_MASK (eltmode) >> 1))
+			      == 0))
+			break;
+		    }
+		  /* For GEU punt if some element is zero.  */
+		  else if (elt == const0_rtx)
+		    break;
+		}
+	      if (i == n_elts)
+		{
+		  rtvec v = rtvec_alloc (n_elts);
+		  for (i = 0; i < n_elts; ++i)
+		    RTVEC_ELT (v, i)
+		      = GEN_INT (INTVAL (CONST_VECTOR_ELT (cop1, i)) - 1);
+		  cop1 = gen_rtx_CONST_VECTOR (mode, v);
+		  code = code == GE ? GT : GTU;
+		  break;
+		}
+	    }
 	  code = reverse_condition (code);
 	  *negate = true;
 	  /* FALLTHRU */
@@ -4556,6 +4627,11 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1,
 	    }
 	}
 
+      if (GET_CODE (cop0) == CONST_VECTOR)
+	cop0 = force_reg (mode, cop0);
+      else if (GET_CODE (cop1) == CONST_VECTOR)
+	cop1 = force_reg (mode, cop1);
+
       rtx optrue = op_true ? op_true : CONSTM1_RTX (data_mode);
       rtx opfalse = op_false ? op_false : CONST0_RTX (data_mode);
       if (*negate)
@@ -4752,13 +4828,13 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1,
   if (*negate)
     std::swap (op_true, op_false);
 
+  if (GET_CODE (cop1) == CONST_VECTOR)
+    cop1 = force_reg (mode, cop1);
+
   /* Allow the comparison to be done in one mode, but the movcc to
      happen in another mode.  */
   if (data_mode == mode)
-    {
-      x = ix86_expand_sse_cmp (dest, code, cop0, cop1,
-			       op_true, op_false);
-    }
+    x = ix86_expand_sse_cmp (dest, code, cop0, cop1, op_true, op_false);
   else
     {
       gcc_assert (GET_MODE_SIZE (data_mode) == GET_MODE_SIZE (mode));
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 2a3f07224cc..f9955038386 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -1235,6 +1235,13 @@
   (ior (match_operand 0 "register_operand")
        (match_operand 0 "vector_memory_operand")))
 
+; Return true when OP is register_operand, vector_memory_operand
+; or const_vector.
+(define_predicate "vector_or_const_vector_operand"
+  (ior (match_operand 0 "register_operand")
+       (match_operand 0 "vector_memory_operand")
+       (match_code "const_vector")))
+
 (define_predicate "bcst_mem_operand"
   (and (match_code "vec_duplicate")
        (and (match_test "TARGET_AVX512F")
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index fa93ae7bf21..9a4fc01856d 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -4311,7 +4311,7 @@
   [(set (match_operand:<sseintvecmode> 0 "register_operand")
 	(match_operator:<sseintvecmode> 1 ""
 	  [(match_operand:VI_256 2 "register_operand")
-	   (match_operand:VI_256 3 "nonimmediate_operand")]))]
+	   (match_operand:VI_256 3 "nonimmediate_or_const_vector_operand")]))]
   "TARGET_AVX2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
@@ -4323,7 +4323,7 @@
   [(set (match_operand:<sseintvecmode> 0 "register_operand")
 	(match_operator:<sseintvecmode> 1 ""
 	  [(match_operand:VI124_128 2 "register_operand")
-	   (match_operand:VI124_128 3 "vector_operand")]))]
+	   (match_operand:VI124_128 3 "vector_or_const_vector_operand")]))]
   "TARGET_SSE2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
@@ -4335,7 +4335,7 @@
   [(set (match_operand:V2DI 0 "register_operand")
 	(match_operator:V2DI 1 ""
 	  [(match_operand:V2DI 2 "register_operand")
-	   (match_operand:V2DI 3 "vector_operand")]))]
+	   (match_operand:V2DI 3 "vector_or_const_vector_operand")]))]
   "TARGET_SSE4_2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
@@ -4397,7 +4397,7 @@
   [(set (match_operand:<sseintvecmode> 0 "register_operand")
 	(match_operator:<sseintvecmode> 1 ""
 	  [(match_operand:VI_256 2 "register_operand")
-	   (match_operand:VI_256 3 "nonimmediate_operand")]))]
+	   (match_operand:VI_256 3 "nonimmediate_or_const_vector_operand")]))]
   "TARGET_AVX2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
@@ -4409,7 +4409,7 @@
   [(set (match_operand:<sseintvecmode> 0 "register_operand")
 	(match_operator:<sseintvecmode> 1 ""
 	  [(match_operand:VI124_128 2 "register_operand")
-	   (match_operand:VI124_128 3 "vector_operand")]))]
+	   (match_operand:VI124_128 3 "vector_or_const_vector_operand")]))]
   "TARGET_SSE2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
@@ -4421,7 +4421,7 @@
   [(set (match_operand:V2DI 0 "register_operand")
 	(match_operator:V2DI 1 ""
 	  [(match_operand:V2DI 2 "register_operand")
-	   (match_operand:V2DI 3 "vector_operand")]))]
+	   (match_operand:V2DI 3 "vector_or_const_vector_operand")]))]
   "TARGET_SSE4_2"
 {
   bool ok = ix86_expand_int_vec_cmp (operands);
diff --git a/gcc/testsuite/gcc.target/i386/pr107546.c b/gcc/testsuite/gcc.target/i386/pr107546.c
new file mode 100644
index 00000000000..e5cf56d7620
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr107546.c
@@ -0,0 +1,19 @@
+/* PR target/107546 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mno-xop -mno-avx512f" } */
+/* { dg-final { scan-assembler-not "pcmpeqb\t" } } */
+/* { dg-final { scan-assembler-times "pcmpgtb\t" 2 } } */
+
+typedef signed char V __attribute__((vector_size(16)));
+
+V
+foo (V x)
+{
+  return x < 48;
+}
+
+V
+bar (V x)
+{
+  return x >= (V) { 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57 };
+}