RISC-V: Add `movMODEcc' implementation for generic targets

Provide RTL expansion of conditional-move operations for generic targets
using a suitable sequence of base integer machine instructions according
to cost evaluation by if-conversion.  Add `-mmovcc' command line option
to enable this transformation, off by default.

For the generic sequences small immediates as per the `arith_operand'
predicate are cost-equivalent to registers as we can use them as input,
alternative to a register, to the respective AND[I] machine operations,
however we need to reject immediates fulfilling `lui_operand', because
they would require reloading into a register, making the operation more
costly.  Therefore add `movcc_operand' predicate and use it accordingly.

There is a need to adjust zbs-bext-02.c, which can also serve as emitted
code example, because with certain compilation options an AND operation
can now legitimately appear in output despite BEXT having been produced
as expected, such as with `-march=rv64gc -O2':

foo:
	mv	a3,a0
	li	a5,0
	mv	a0,a1
	li	a2,64
	li	a1,1
.L3:
	sll	a4,a1,a5
	and	a4,a4,a3
	addiw	a5,a5,1
	beq	a4,zero,.L2
	addiw	a0,a0,1
.L2:
	bne	a5,a2,.L3
	ret

vs `-march=rv64gc_zbs -O2':

foo:
	mv	a4,a0
	li	a5,0
	mv	a0,a1
	li	a3,64
.L3:
	bext	a2,a4,a5
	beq	a2,zero,.L2
	addiw	a0,a0,1
.L2:
	addiw	a5,a5,1
	bne	a5,a3,.L3
	ret

and then with `-march=rv64gc -mmovcc -mbranch-cost=7':

foo:
	mv	a6,a0
	li	a4,0
	mv	a0,a1
	li	a7,1
	li	a1,64
.L3:
	sll	a5,a7,a4
	and	a5,a5,a6
	snez	a5,a5
	neg	a5,a5
	not	a2,a5
	addiw	a3,a0,1
	and	a5,a5,a3
	and	a0,a2,a0
	addiw	a4,a4,1
	or	a0,a5,a0
	bne	a4,a1,.L3
	ret

vs `-march=rv64gc_zbs -mmovcc -mbranch-cost=7':

foo:
	mv	a6,a0
	li	a4,0
	mv	a0,a1
	li	a1,64
.L3:
	bext	a5,a6,a4
	neg	a5,a5
	not	a2,a5
	addiw	a3,a0,1
	and	a5,a5,a3
	and	a0,a2,a0
	addiw	a4,a4,1
	or	a0,a5,a0
	bne	a4,a1,.L3
	ret

However BEXT is supposed to replace an SLL operation so adjust the test
case to reject SLL rather than AND, letting the test case pass even with
`/-mmovcc/-mbranch-cost=7' specified as DejaGNU test flags (and in the
absence of target-specific conditional-move operations enabled either by
default or with other test flags).

	gcc/
	* config/riscv/predicates.md (movcc_operand): New predicate.
	* config/riscv/riscv.cc (riscv_expand_conditional_move): Handle
	generic targets.
	* config/riscv/riscv.md (mov<mode>cc): Likewise.
	* config/riscv/riscv.opt (mmovcc): New option.
	* doc/invoke.texi (Option Summary): Document it.

	gcc/testsuite/
	* gcc.target/riscv/zbs-bext-02.c: Adjust to reject SLL rather
	than AND.

6 files changed, 58 insertions, 11 deletions

diff --git a/gcc/config/riscv/predicates.md b/gcc/config/riscv/predicates.md
index 90567a8..f943f31 100644
--- a/gcc/config/riscv/predicates.md
+++ b/gcc/config/riscv/predicates.md
@@ -41,6 +41,12 @@
   (ior (match_operand 0 "arith_operand")
        (match_operand 0 "lui_operand")))
 
+(define_predicate "movcc_operand"
+  (if_then_else (match_test "TARGET_SFB_ALU || TARGET_XTHEADCONDMOV
+			     || TARGET_ZICOND_LIKE")
+		(match_operand 0 "sfb_alu_operand")
+		(match_operand 0 "arith_operand")))
+
 (define_predicate "const_csr_operand"
   (and (match_code "const_int")
        (match_test "IN_RANGE (INTVAL (op), 0, 31)")))
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 5198da6..df08e9c 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -4128,7 +4128,9 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
   rtx op0 = XEXP (op, 0);
   rtx op1 = XEXP (op, 1);
 
-  if ((TARGET_ZICOND_LIKE && GET_MODE_CLASS (mode) == MODE_INT)
+  if (((TARGET_ZICOND_LIKE
+	|| (arith_operand (cons, mode) && arith_operand (alt, mode)))
+       && (GET_MODE_CLASS (mode) == MODE_INT))
       || TARGET_SFB_ALU || TARGET_XTHEADCONDMOV)
     {
       machine_mode mode0 = GET_MODE (op0);
@@ -4142,6 +4144,15 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
 	  || (mode1 != word_mode && mode1 != VOIDmode))
 	return false;
 
+      /* In the fallback generic case use MODE rather than WORD_MODE for
+	 the output of the SCC instruction, to match the mode of the NEG
+	 operation below.  The output of SCC is 0 or 1 boolean, so it is
+	 valid for input in any scalar integer mode.  */
+      rtx tmp = gen_reg_rtx ((TARGET_ZICOND_LIKE
+			      || TARGET_SFB_ALU || TARGET_XTHEADCONDMOV)
+			     ? word_mode : mode);
+      bool invert = false;
+
       /* Canonicalize the comparison.  It must be an equality comparison
 	 of integer operands, or with SFB it can be any comparison of
 	 integer operands.  If it isn't, then emit an SCC instruction
@@ -4150,7 +4161,6 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
 	  || !INTEGRAL_MODE_P (mode0))
 	{
 	  bool *invert_ptr = nullptr;
-	  bool invert = false;
 
 	  /* If riscv_expand_int_scc inverts the condition, then it will
 	     flip the value of INVERT.  We need to know where so that
@@ -4158,11 +4168,9 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
 	  if (code == LE || code == LEU || code == GE || code == GEU)
 	    invert_ptr = &invert;
 
-	  /* Emit an scc like instruction into a temporary
-	     so that we can use an EQ/NE comparison.  */
-	  rtx tmp = gen_reg_rtx (word_mode);
-
-	  /* We can support both FP and integer conditional moves.  */
+	  /* Emit an SCC-like instruction into a temporary so that we can
+	     use an EQ/NE comparison.  We can support both FP and integer
+	     conditional moves.  */
 	  if (INTEGRAL_MODE_P (mode0))
 	    riscv_expand_int_scc (tmp, code, op0, op1, invert_ptr);
 	  else if (FLOAT_MODE_P (mode0)
@@ -4178,6 +4186,8 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
 	  op0 = XEXP (op, 0);
 	  op1 = XEXP (op, 1);
 	}
+      else if (!TARGET_ZICOND_LIKE && !TARGET_SFB_ALU && !TARGET_XTHEADCONDMOV)
+	riscv_expand_int_scc (tmp, code, op0, op1, &invert);
 
       if (TARGET_SFB_ALU || TARGET_XTHEADCONDMOV)
 	{
@@ -4195,6 +4205,23 @@ riscv_expand_conditional_move (rtx dest, rtx op, rtx cons, rtx alt)
 							      cons, alt)));
 	  return true;
 	}
+      else if (!TARGET_ZICOND_LIKE)
+	{
+	  if (invert)
+	    std::swap (cons, alt);
+
+	  rtx reg1 = gen_reg_rtx (mode);
+	  rtx reg2 = gen_reg_rtx (mode);
+	  rtx reg3 = gen_reg_rtx (mode);
+	  rtx reg4 = gen_reg_rtx (mode);
+
+	  riscv_emit_unary (NEG, reg1, tmp);
+	  riscv_emit_binary (AND, reg2, reg1, cons);
+	  riscv_emit_unary (NOT, reg3, reg1);
+	  riscv_emit_binary (AND, reg4, reg3, alt);
+	  riscv_emit_binary (IOR, dest, reg2, reg4);
+	  return true;
+	}
       /* 0, reg or 0, imm */
       else if (cons == CONST0_RTX (mode)
 	       && (REG_P (alt)
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index e6d90c2..37860cf 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -2658,9 +2658,10 @@
 (define_expand "mov<mode>cc"
   [(set (match_operand:GPR 0 "register_operand")
 	(if_then_else:GPR (match_operand 1 "comparison_operator")
-			  (match_operand:GPR 2 "sfb_alu_operand")
-			  (match_operand:GPR 3 "sfb_alu_operand")))]
-  "TARGET_SFB_ALU || TARGET_XTHEADCONDMOV || TARGET_ZICOND_LIKE"
+			  (match_operand:GPR 2 "movcc_operand")
+			  (match_operand:GPR 3 "movcc_operand")))]
+  "TARGET_SFB_ALU || TARGET_XTHEADCONDMOV || TARGET_ZICOND_LIKE
+   || TARGET_MOVCC"
 {
   if (riscv_expand_conditional_move (operands[0], operands[1],
 				     operands[2], operands[3]))
diff --git a/gcc/config/riscv/riscv.opt b/gcc/config/riscv/riscv.opt
index 555288e..11526f9 100644
--- a/gcc/config/riscv/riscv.opt
+++ b/gcc/config/riscv/riscv.opt
@@ -460,6 +460,10 @@ misa-spec=
 Target RejectNegative Joined Enum(isa_spec_class) Var(riscv_isa_spec) Init(TARGET_DEFAULT_ISA_SPEC)
 Set the version of RISC-V ISA spec.
 
+mmovcc
+Target Var(TARGET_MOVCC)
+Enable conditional moves unconditionally.
+
 minline-atomics
 Target Var(TARGET_INLINE_SUBWORD_ATOMIC) Init(1)
 Always inline subword atomic operations.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 086be0f..7666de1 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1245,6 +1245,7 @@ See RS/6000 and PowerPC Options.
 -mstack-protector-guard=@var{guard}  -mstack-protector-guard-reg=@var{reg}
 -mstack-protector-guard-offset=@var{offset}
 -mcsr-check -mno-csr-check
+-mmovcc  -mno-movcc
 -minline-atomics  -mno-inline-atomics
 -minline-strlen  -mno-inline-strlen
 -minline-strcmp  -mno-inline-strcmp
@@ -29681,6 +29682,14 @@ Do or don't use smaller but slower prologue and epilogue code that uses
 library function calls.  The default is to use fast inline prologues and
 epilogues.
 
+@opindex mmovcc
+@item -mmovcc
+@itemx -mno-movcc
+Do or don't produce branchless conditional-move code sequences even with
+targets that do not have specific instructions for conditional operations.
+If enabled, sequences of ALU operations are produced using base integer
+ISA instructions where profitable.
+
 @opindex minline-atomics
 @item -minline-atomics
 @itemx -mno-inline-atomics
diff --git a/gcc/testsuite/gcc.target/riscv/zbs-bext-02.c b/gcc/testsuite/gcc.target/riscv/zbs-bext-02.c
index 8c5d8c7..81d826d 100644
--- a/gcc/testsuite/gcc.target/riscv/zbs-bext-02.c
+++ b/gcc/testsuite/gcc.target/riscv/zbs-bext-02.c
@@ -15,4 +15,4 @@ foo(const long long B, int a)
 
 /* { dg-final { scan-assembler-times "bext\t" 1 } } */
 /* { dg-final { scan-assembler-not {\mbset} } } */
-/* { dg-final { scan-assembler-not {\mand} } } */
+/* { dg-final { scan-assembler-not {\msll} } } */