[gcc r15-1122] i386: Implement .SAT_SUB for unsigned scalar integers [PR112600]

[Uros Bizjak via Gcc-cvs]

https://gcc.gnu.org/g:8bb6b2f4ae19c3aab7d7a5e5c8f5965f89d90e01

commit r15-1122-g8bb6b2f4ae19c3aab7d7a5e5c8f5965f89d90e01
Author: Uros Bizjak <ubiz...@gmail.com>
Date:   Sun Jun 9 12:09:13 2024 +0200

    i386: Implement .SAT_SUB for unsigned scalar integers [PR112600]
    
    The following testcase:
    
    unsigned
    sub_sat (unsigned x, unsigned y)
    {
      unsigned res;
      res = x - y;
      res &= -(x >= y);
      return res;
    }
    
    currently compiles (-O2) to:
    
    sub_sat:
            movl    %edi, %edx
            xorl    %eax, %eax
            subl    %esi, %edx
            cmpl    %esi, %edi
            setnb   %al
            negl    %eax
            andl    %edx, %eax
            ret
    
    We can expand through ussub{m}3 optab to use carry flag from the subtraction
    and generate code using SBB instruction implementing:
    
        unsigned res = x - y;
        res &= ~(-(x < y));
    
    sub_sat:
            subl    %esi, %edi
            sbbl    %eax, %eax
            notl    %eax
            andl    %edi, %eax
            ret
    
            PR target/112600
    
    gcc/ChangeLog:
    
            * config/i386/i386.md (ussub<mode>3): New expander.
            (sub<mode>_3): Ditto.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/i386/pr112600-b.c: New test.

Diff:
---
 gcc/config/i386/i386.md                    | 31 ++++++++++++++++++++++-
 gcc/testsuite/gcc.target/i386/pr112600-b.c | 40 ++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+), 1 deletion(-)

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index bc2ef819df6..d69bc8d6e48 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -8436,6 +8436,14 @@
   "ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands,
                                       TARGET_APX_NDD);")
 
+(define_expand "sub<mode>_3"
+  [(parallel [(set (reg:CC FLAGS_REG)
+                  (compare:CC
+                    (match_operand:SWI 1 "nonimmediate_operand")
+                    (match_operand:SWI 2 "<general_operand>")))
+             (set (match_operand:SWI 0 "register_operand")
+                  (minus:SWI (match_dup 1) (match_dup 2)))])])
+
 (define_insn "*sub<mode>_3"
   [(set (reg FLAGS_REG)
        (compare (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
@@ -9883,7 +9891,28 @@
   emit_insn (gen_add<mode>3_cc_overflow_1 (res, operands[1], operands[2]));
   emit_insn (gen_x86_mov<mode>cc_0_m1_neg (msk));
   dst = expand_simple_binop (<MODE>mode, IOR, res, msk,
-                            operands[0], 1, OPTAB_DIRECT);
+                            operands[0], 1, OPTAB_WIDEN);
+
+  if (!rtx_equal_p (dst, operands[0]))
+    emit_move_insn (operands[0], dst);
+  DONE;
+})
+
+(define_expand "ussub<mode>3"
+  [(set (match_operand:SWI 0 "register_operand")
+       (us_minus:SWI (match_operand:SWI 1 "register_operand")
+                     (match_operand:SWI 2 "<general_operand>")))]
+  ""
+{
+  rtx res = gen_reg_rtx (<MODE>mode);
+  rtx msk = gen_reg_rtx (<MODE>mode);
+  rtx dst;
+
+  emit_insn (gen_sub<mode>_3 (res, operands[1], operands[2]));
+  emit_insn (gen_x86_mov<mode>cc_0_m1_neg (msk));
+  msk = expand_simple_unop (<MODE>mode, NOT, msk, NULL, 1);
+  dst = expand_simple_binop (<MODE>mode, AND, res, msk,
+                            operands[0], 1, OPTAB_WIDEN);
 
   if (!rtx_equal_p (dst, operands[0]))
     emit_move_insn (operands[0], dst);
diff --git a/gcc/testsuite/gcc.target/i386/pr112600-b.c 
b/gcc/testsuite/gcc.target/i386/pr112600-b.c
new file mode 100644
index 00000000000..ea14bb9738b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr112600-b.c
@@ -0,0 +1,40 @@
+/* PR target/112600 */
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-times "sbb" 4 } } */
+
+unsigned char
+sub_sat_char (unsigned char x, unsigned char y)
+{
+  unsigned char res;
+  res = x - y;
+  res &= -(x >= y);
+  return res;
+}
+
+unsigned short
+sub_sat_short (unsigned short x, unsigned short y)
+{
+  unsigned short res;
+  res = x - y;
+  res &= -(x >= y);
+  return res;
+}
+
+unsigned int
+sub_sat_int (unsigned int x, unsigned int y)
+{
+  unsigned int res;
+  res = x - y;
+  res &= -(x >= y);
+  return res;
+}
+
+unsigned long
+sub_sat_long (unsigned long x, unsigned long y)
+{
+  unsigned long res;
+  res = x - y;
+  res &= -(x >= y);
+  return res;
+}