RISC-V: Support RVV VFNMACC rounding mode intrinsic API

This patch would like to support the rounding mode API for the
VFNMACC for the below samples.

* __riscv_vfnmacc_vv_f32m1_rm
* __riscv_vfnmacc_vv_f32m1_rm_m
* __riscv_vfnmacc_vf_f32m1_rm
* __riscv_vfnmacc_vf_f32m1_rm_m

Signed-off-by: Pan Li <pan2.li@intel.com>

gcc/ChangeLog:

	* config/riscv/riscv-vector-builtins-bases.cc
	(class vfnmacc_frm): New class for vfnmacc.
	(vfnmacc_frm_obj): New declaration.
	(BASE): Ditto.
	* config/riscv/riscv-vector-builtins-bases.h: Ditto.
	* config/riscv/riscv-vector-builtins-functions.def
	(vfnmacc_frm): New function definition.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/float-point-single-negate-multiply-add.c:
	New test.

gcc/config/riscv/riscv-vector-builtins-bases.cc

@@ -379,6 +379,28 @@ public:
   }
 };
 
+/* Implements below instructions for frm
+   - vfnmacc
+*/
+class vfnmacc_frm : public function_base
+{
+public:
+  bool has_rounding_mode_operand_p () const override { return true; }
+
+  bool has_merge_operand_p () const override { return false; }
+
+  rtx expand (function_expander &e) const override
+  {
+    if (e.op_info->op == OP_TYPE_vf)
+      return e.use_ternop_insn (
+	true, code_for_pred_mul_neg_scalar (MINUS, e.vector_mode ()));
+    if (e.op_info->op == OP_TYPE_vv)
+      return e.use_ternop_insn (
+	true, code_for_pred_mul_neg (MINUS, e.vector_mode ()));
+    gcc_unreachable ();
+  }
+};
+
 /* Implements vrsub.  */
 class vrsub : public function_base
 {
@@ -2144,6 +2166,7 @@ static CONSTEXPR const vfnmsac vfnmsac_obj;
 static CONSTEXPR const vfmadd vfmadd_obj;
 static CONSTEXPR const vfnmsub vfnmsub_obj;
 static CONSTEXPR const vfnmacc vfnmacc_obj;
+static CONSTEXPR const vfnmacc_frm vfnmacc_frm_obj;
 static CONSTEXPR const vfmsac vfmsac_obj;
 static CONSTEXPR const vfnmadd vfnmadd_obj;
 static CONSTEXPR const vfmsub vfmsub_obj;
@@ -2380,6 +2403,7 @@ BASE (vfnmsac)
 BASE (vfmadd)
 BASE (vfnmsub)
 BASE (vfnmacc)
+BASE (vfnmacc_frm)
 BASE (vfmsac)
 BASE (vfnmadd)
 BASE (vfmsub)

gcc/config/riscv/riscv-vector-builtins-bases.h

@@ -165,6 +165,7 @@ extern const function_base *const vfnmsac;
 extern const function_base *const vfmadd;
 extern const function_base *const vfnmsub;
 extern const function_base *const vfnmacc;
+extern const function_base *const vfnmacc_frm;
 extern const function_base *const vfmsac;
 extern const function_base *const vfnmadd;
 extern const function_base *const vfmsub;

gcc/config/riscv/riscv-vector-builtins-functions.def

@@ -350,6 +350,8 @@ DEF_RVV_FUNCTION (vfmsub, alu, full_preds, f_vvvv_ops)
 DEF_RVV_FUNCTION (vfmsub, alu, full_preds, f_vvfv_ops)
 DEF_RVV_FUNCTION (vfmacc_frm, alu_frm, full_preds, f_vvvv_ops)
 DEF_RVV_FUNCTION (vfmacc_frm, alu_frm, full_preds, f_vvfv_ops)
+DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvvv_ops)
+DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvfv_ops)
 
 // 13.7. Vector Widening Floating-Point Fused Multiply-Add Instructions
 DEF_RVV_FUNCTION (vfwmacc, alu, full_preds, f_wwvv_ops)

gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-negate-multiply-add.c

@@ -0,0 +1,47 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+typedef float float32_t;
+
+vfloat32m1_t
+test_riscv_vfnmacc_vv_f32m1_rm (vfloat32m1_t vd, vfloat32m1_t op1,
+			        vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmacc_vv_f32m1_rm (vd, op1, op2, 0, vl);
+}
+
+vfloat32m1_t
+test_vfnmacc_vv_f32m1_rm_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1,
+			    vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmacc_vv_f32m1_rm_m (mask, vd, op1, op2, 1, vl);
+}
+
+vfloat32m1_t
+test_vfnmacc_vf_f32m1_rm (vfloat32m1_t vd, float32_t op1, vfloat32m1_t op2,
+			  size_t vl) {
+  return __riscv_vfnmacc_vf_f32m1_rm (vd, op1, op2, 2, vl);
+}
+
+vfloat32m1_t
+test_vfnmacc_vf_f32m1_rm_m (vfloat32m1_t vd, vbool32_t mask, float32_t op1,
+			    vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmacc_vf_f32m1_rm_m (mask, vd, op1, op2, 3, vl);
+}
+
+vfloat32m1_t
+test_riscv_vfnmacc_vv_f32m1 (vfloat32m1_t vd, vfloat32m1_t op1,
+			     vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmacc_vv_f32m1 (vd, op1, op2, vl);
+}
+
+vfloat32m1_t
+test_vfnmacc_vv_f32m1_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1,
+			 vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmacc_vv_f32m1_m (mask, vd, op1, op2, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfnmacc\.v[vf]\s+v[0-9]+,\s*[fav]+[0-9]+,\s*v[0-9]+} 6 } } */
+/* { dg-final { scan-assembler-times {frrm\s+[axs][0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {fsrm\s+[axs][0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {fsrmi\s+[01234]} 4 } } */