RE: [PATCH v1] RISC-V: Support RVV VFNMSAC rounding mode intrinsic API

["Li, Pan2" <pan2.li@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 7030 bytes --]

Committed, thanks Juzhe.

Pan

From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Friday, August 11, 2023 3:30 PM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: jeffreyalaw <jeffreyalaw@gmail.com>; Li, Pan2 <pan2.li@intel.com>; Wang, Yanzhang <yanzhang.wang@intel.com>; kito.cheng <kito.cheng@gmail.com>
Subject: Re: [PATCH v1] RISC-V: Support RVV VFNMSAC rounding mode intrinsic API

LGTM

________________________________
juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>

From: pan2.li<mailto:pan2.li@intel.com>
Date: 2023-08-11 13:54
To: gcc-patches<mailto:gcc-patches@gcc.gnu.org>
CC: juzhe.zhong<mailto:juzhe.zhong@rivai.ai>; jeffreyalaw<mailto:jeffreyalaw@gmail.com>; pan2.li<mailto:pan2.li@intel.com>; yanzhang.wang<mailto:yanzhang.wang@intel.com>; kito.cheng<mailto:kito.cheng@gmail.com>
Subject: [PATCH v1] RISC-V: Support RVV VFNMSAC rounding mode intrinsic API
From: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>

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

* __riscv_vfnmsac_vv_f32m1_rm
* __riscv_vfnmsac_vv_f32m1_rm_m
* __riscv_vfnmsac_vf_f32m1_rm
* __riscv_vfnmsac_vf_f32m1_rm_m

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

gcc/ChangeLog:

* config/riscv/riscv-vector-builtins-bases.cc
(class vfnmsac_frm): New class for vfnmsac frm.
(vfnmsac_frm_obj): New declaration.
(BASE): Ditto.
* config/riscv/riscv-vector-builtins-bases.h: Ditto.
* config/riscv/riscv-vector-builtins-functions.def
(vfnmsac_frm): New function definition.

gcc/testsuite/ChangeLog:

* gcc.target/riscv/rvv/base/float-point-nmsac.c: New test.
---
.../riscv/riscv-vector-builtins-bases.cc      | 25 ++++++++++
.../riscv/riscv-vector-builtins-bases.h       |  1 +
.../riscv/riscv-vector-builtins-functions.def |  2 +
.../riscv/rvv/base/float-point-nmsac.c        | 47 +++++++++++++++++++
4 files changed, 75 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/float-point-nmsac.c

diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 8d3970b28db..60c6e16f6ae 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -424,6 +424,29 @@ public:
   }
};
+/* Implements below instructions for frm
+   - vfnmsac
+*/
+class vfnmsac_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 (PLUS, e.vector_mode ()));
+    if (e.op_info->op == OP_TYPE_vv)
+      return e.use_ternop_insn (
+ true, code_for_pred_mul_neg (PLUS, e.vector_mode ()));
+
+    gcc_unreachable ();
+  }
+};
+
/* Implements vrsub.  */
class vrsub : public function_base
{
@@ -2186,6 +2209,7 @@ static CONSTEXPR const widen_binop_frm<MULT> vfwmul_frm_obj;
static CONSTEXPR const vfmacc vfmacc_obj;
static CONSTEXPR const vfmacc_frm vfmacc_frm_obj;
static CONSTEXPR const vfnmsac vfnmsac_obj;
+static CONSTEXPR const vfnmsac_frm vfnmsac_frm_obj;
static CONSTEXPR const vfmadd vfmadd_obj;
static CONSTEXPR const vfnmsub vfnmsub_obj;
static CONSTEXPR const vfnmacc vfnmacc_obj;
@@ -2424,6 +2448,7 @@ BASE (vfwmul_frm)
BASE (vfmacc)
BASE (vfmacc_frm)
BASE (vfnmsac)
+BASE (vfnmsac_frm)
BASE (vfmadd)
BASE (vfnmsub)
BASE (vfnmacc)
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index ca8a6dc1cc3..28eec2c3e99 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -162,6 +162,7 @@ extern const function_base *const vfwmul_frm;
extern const function_base *const vfmacc;
extern const function_base *const vfmacc_frm;
extern const function_base *const vfnmsac;
+extern const function_base *const vfnmsac_frm;
extern const function_base *const vfmadd;
extern const function_base *const vfnmsub;
extern const function_base *const vfnmacc;
diff --git a/gcc/config/riscv/riscv-vector-builtins-functions.def b/gcc/config/riscv/riscv-vector-builtins-functions.def
index 51a14e49075..c84e052c1a9 100644
--- a/gcc/config/riscv/riscv-vector-builtins-functions.def
+++ b/gcc/config/riscv/riscv-vector-builtins-functions.def
@@ -355,6 +355,8 @@ DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvvv_ops)
DEF_RVV_FUNCTION (vfnmacc_frm, alu_frm, full_preds, f_vvfv_ops)
DEF_RVV_FUNCTION (vfmsac_frm, alu_frm, full_preds, f_vvvv_ops)
DEF_RVV_FUNCTION (vfmsac_frm, alu_frm, full_preds, f_vvfv_ops)
+DEF_RVV_FUNCTION (vfnmsac_frm, alu_frm, full_preds, f_vvvv_ops)
+DEF_RVV_FUNCTION (vfnmsac_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)
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-nmsac.c b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-nmsac.c
new file mode 100644
index 00000000000..c3089234272
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-nmsac.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_vfnmsac_vv_f32m1_rm (vfloat32m1_t vd, vfloat32m1_t op1,
+         vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmsac_vv_f32m1_rm (vd, op1, op2, 0, vl);
+}
+
+vfloat32m1_t
+test_vfnmsac_vv_f32m1_rm_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1,
+     vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmsac_vv_f32m1_rm_m (mask, vd, op1, op2, 1, vl);
+}
+
+vfloat32m1_t
+test_vfnmsac_vf_f32m1_rm (vfloat32m1_t vd, float32_t op1, vfloat32m1_t op2,
+   size_t vl) {
+  return __riscv_vfnmsac_vf_f32m1_rm (vd, op1, op2, 2, vl);
+}
+
+vfloat32m1_t
+test_vfnmsac_vf_f32m1_rm_m (vfloat32m1_t vd, vbool32_t mask, float32_t op1,
+     vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmsac_vf_f32m1_rm_m (mask, vd, op1, op2, 3, vl);
+}
+
+vfloat32m1_t
+test_riscv_vfnmsac_vv_f32m1 (vfloat32m1_t vd, vfloat32m1_t op1,
+      vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmsac_vv_f32m1 (vd, op1, op2, vl);
+}
+
+vfloat32m1_t
+test_vfnmsac_vv_f32m1_m (vbool32_t mask, vfloat32m1_t vd, vfloat32m1_t op1,
+ vfloat32m1_t op2, size_t vl) {
+  return __riscv_vfnmsac_vv_f32m1_m (mask, vd, op1, op2, vl);
+}
+
+/* { dg-final { scan-assembler-times {vfnmsac\.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 } } */
--
2.34.1