RISC-V: Support RVV VFSUB and VFRSUB rounding mode intrinsic API

This patch would like to support the rounding mode API for both the
VFSUB and VFRSUB as below samples.

* __riscv_vfsub_vv_f32m1_rm
* __riscv_vfsub_vv_f32m1_rm_m
* __riscv_vfsub_vf_f32m1_rm
* __riscv_vfsub_vf_f32m1_rm_m
* __riscv_vfrsub_vf_f32m1_rm
* __riscv_vfrsub_vf_f32m1_rm_m

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

	* config/riscv/riscv-vector-builtins-bases.cc
	(class reverse_binop_frm): Add new template for reversed frm.
	(vfsub_frm_obj): New obj.
	(vfrsub_frm_obj): Likewise.
	* config/riscv/riscv-vector-builtins-bases.h:
	(vfsub_frm): New declaration.
	(vfrsub_frm): Likewise.
	* config/riscv/riscv-vector-builtins-functions.def
	(vfsub_frm): New function define.
	(vfrsub_frm): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/float-point-single-rsub.c: New test.
	* gcc.target/riscv/rvv/base/float-point-single-sub.c: New test.

diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 316b35b57c8b5ca7bbfefab4880743e49b5eb43b..035cafc43b351b20a4847df6635bea1de0ef6431 100644 (file)
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -298,6 +298,23 @@ public:
   }
 };
 
+/* Implements below instructions for frm
+   - vfrsub
+*/
+template<rtx_code CODE>
+class reverse_binop_frm : public function_base
+{
+public:
+  bool has_rounding_mode_operand_p () const override { return true; }
+
+public:
+  rtx expand (function_expander &e) const override
+  {
+    return e.use_exact_insn (
+      code_for_pred_reverse_scalar (CODE, e.vector_mode ()));
+  }
+};
+
 /* Implements vrsub.  */
 class vrsub : public function_base
 {
@@ -2042,7 +2059,9 @@ static CONSTEXPR const vid vid_obj;
 static CONSTEXPR const binop<PLUS> vfadd_obj;
 static CONSTEXPR const binop<MINUS> vfsub_obj;
 static CONSTEXPR const binop_frm<PLUS> vfadd_frm_obj;
+static CONSTEXPR const binop_frm<MINUS> vfsub_frm_obj;
 static CONSTEXPR const reverse_binop<MINUS> vfrsub_obj;
+static CONSTEXPR const reverse_binop_frm<MINUS> vfrsub_frm_obj;
 static CONSTEXPR const widen_binop<PLUS> vfwadd_obj;
 static CONSTEXPR const widen_binop<MINUS> vfwsub_obj;
 static CONSTEXPR const binop<MULT> vfmul_obj;
@@ -2269,7 +2288,9 @@ BASE (vid)
 BASE (vfadd)
 BASE (vfadd_frm)
 BASE (vfsub)
+BASE (vfsub_frm)
 BASE (vfrsub)
+BASE (vfrsub_frm)
 BASE (vfwadd)
 BASE (vfwsub)
 BASE (vfmul)

diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index e771a36adc897a4a0a873684dd5addab4b4f64a0..5c6b239c2746c8389d816f9aba131c4347bc2bcb 100644 (file)
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -144,7 +144,9 @@ extern const function_base *const vid;
 extern const function_base *const vfadd;
 extern const function_base *const vfadd_frm;
 extern const function_base *const vfsub;
+extern const function_base *const vfsub_frm;
 extern const function_base *const vfrsub;
+extern const function_base *const vfrsub_frm;
 extern const function_base *const vfwadd;
 extern const function_base *const vfwsub;
 extern const function_base *const vfmul;

diff --git a/gcc/config/riscv/riscv-vector-builtins-functions.def b/gcc/config/riscv/riscv-vector-builtins-functions.def
index 035c9e4252ff6f0404fcd820abc7986664ad9375..fa1c2cef970142e8ff72175ec01df4af1eb5505b 100644 (file)
--- a/gcc/config/riscv/riscv-vector-builtins-functions.def
+++ b/gcc/config/riscv/riscv-vector-builtins-functions.def
@@ -291,6 +291,9 @@ DEF_RVV_FUNCTION (vfsub, alu, full_preds, f_vvf_ops)
 DEF_RVV_FUNCTION (vfrsub, alu, full_preds, f_vvf_ops)
 DEF_RVV_FUNCTION (vfadd_frm, alu_frm, full_preds, f_vvv_ops)
 DEF_RVV_FUNCTION (vfadd_frm, alu_frm, full_preds, f_vvf_ops)
+DEF_RVV_FUNCTION (vfsub_frm, alu_frm, full_preds, f_vvv_ops)
+DEF_RVV_FUNCTION (vfsub_frm, alu_frm, full_preds, f_vvf_ops)
+DEF_RVV_FUNCTION (vfrsub_frm, alu_frm, full_preds, f_vvf_ops)
 
 // 13.3. Vector Widening Floating-Point Add/Subtract Instructions
 DEF_RVV_FUNCTION (vfwadd, widen_alu, full_preds, f_wvv_ops)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-rsub.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-rsub.c
new file mode 100644 (file)
index 0000000..1d770ad
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-rsub.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+typedef float float32_t;
+
+vfloat32m1_t
+test_vfrsub_vf_f32m1_rm (vfloat32m1_t op1, float32_t op2, size_t vl) {
+  return __riscv_vfrsub_vf_f32m1_rm (op1, op2, 2, vl);
+}
+
+vfloat32m1_t
+test_vfrsub_vf_f32m1_rm_m (vbool32_t mask, vfloat32m1_t op1, float32_t op2,
+                          size_t vl) {
+  return __riscv_vfrsub_vf_f32m1_rm_m (mask, op1, op2, 3, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfrsub\.v[vf]\s+v[0-9]+,\s*v[0-9]+,\s*[fav]+[0-9]+} 2 } } */

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-sub.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-sub.c
new file mode 100644 (file)
index 0000000..34ed03a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-single-sub.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3 -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+typedef float float32_t;
+
+vfloat32m1_t
+test_riscv_vfsub_vv_f32m1_rm (vfloat32m1_t op1, vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfsub_vv_f32m1_rm (op1, op2, 0, vl);
+}
+
+vfloat32m1_t
+test_vfsub_vv_f32m1_rm_m (vbool32_t mask, vfloat32m1_t op1, vfloat32m1_t op2,
+                        size_t vl) {
+  return __riscv_vfsub_vv_f32m1_rm_m (mask, op1, op2, 1, vl);
+}
+
+vfloat32m1_t
+test_vfsub_vf_f32m1_rm (vfloat32m1_t op1, float32_t op2, size_t vl) {
+  return __riscv_vfsub_vf_f32m1_rm (op1, op2, 2, vl);
+}
+
+vfloat32m1_t
+test_vfsub_vf_f32m1_rm_m (vbool32_t mask, vfloat32m1_t op1, float32_t op2,
+                         size_t vl) {
+  return __riscv_vfsub_vf_f32m1_rm_m (mask, op1, op2, 3, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfsub\.v[vf]\s+v[0-9]+,\s*v[0-9]+,\s*[fav]+[0-9]+} 4 } } */