diff mbox series

[committed] i386: Implement .SAT_SUB for unsigned scalar integers [PR112600]

Message ID CAFULd4YbDcpujj-196-QGaU=ara=gbYvqV7JW6AUL_hx94v5qQ@mail.gmail.com
State New
Headers show
Series [committed] i386: Implement .SAT_SUB for unsigned scalar integers [PR112600] | expand

Commit Message

Uros Bizjak June 9, 2024, 10:12 a.m. UTC
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.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Uros.
diff mbox series

Patch

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 @@  (define_expand "usubv<mode>4"
   "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 @@  (define_expand "usadd<mode>3"
   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);