RISC-V: Add RVV FNMA auto-vectorization support

Like FMA, Add FNMA (VNMSAC or VNMSUB) auto-vectorization support.

Signed-off-by: Juzhe-Zhong <juzhe.zhong@rivai.ai>

gcc/ChangeLog:

	* config/riscv/autovec.md (fnma<mode>4): New pattern.
	(*fnma<mode>): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/ternop/ternop-4.c: New test.
	* gcc.target/riscv/rvv/autovec/ternop/ternop-5.c: New test.
	* gcc.target/riscv/rvv/autovec/ternop/ternop-6.c: New test.
	* gcc.target/riscv/rvv/autovec/ternop/ternop_run-4.c: New test.
	* gcc.target/riscv/rvv/autovec/ternop/ternop_run-5.c: New test.
	* gcc.target/riscv/rvv/autovec/ternop/ternop_run-6.c: New test.

7 files changed, 432 insertions, 0 deletions

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 0314e75..d9b1571 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -583,3 +583,48 @@
   }
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")])
+
+;; -------------------------------------------------------------------------
+;; ---- [INT] VNMSAC and VNMSUB
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vnmsac
+;; - vnmsub
+;; -------------------------------------------------------------------------
+
+(define_expand "fnma<mode>4"
+  [(parallel
+    [(set (match_operand:VI 0 "register_operand"     "=vr")
+   (minus:VI
+     (match_operand:VI 3 "register_operand"   " vr")
+     (mult:VI
+       (match_operand:VI 1 "register_operand" " vr")
+       (match_operand:VI 2 "register_operand" " vr"))))
+     (clobber (match_scratch:SI 4))])]
+  "TARGET_VECTOR"
+  {})
+
+(define_insn_and_split "*fnma<mode>"
+  [(set (match_operand:VI 0 "register_operand"     "=vr, vr, ?&vr")
+ (minus:VI
+   (match_operand:VI 3 "register_operand"   " vr,  0,   vr")
+   (mult:VI
+     (match_operand:VI 1 "register_operand" " %0, vr,   vr")
+     (match_operand:VI 2 "register_operand" " vr, vr,   vr"))))
+   (clobber (match_scratch:SI 4 "=r,r,r"))]
+  "TARGET_VECTOR"
+  "#"
+  "&& reload_completed"
+  [(const_int 0)]
+  {
+    PUT_MODE (operands[4], Pmode);
+    riscv_vector::emit_vlmax_vsetvl (<MODE>mode, operands[4]);
+    if (which_alternative == 2)
+      emit_insn (gen_rtx_SET (operands[0], operands[3]));
+    rtx ops[] = {operands[0], operands[1], operands[2], operands[3], operands[0]};
+    riscv_vector::emit_vlmax_ternary_insn (code_for_pred_minus_mul (<MODE>mode),
+    riscv_vector::RVV_TERNOP, ops, operands[4]);
+    DONE;
+  }
+  [(set_attr "type" "vimuladd")
+   (set_attr "mode" "<MODE>")])
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-4.c
new file mode 100644
index 0000000..1b8b934
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-4.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE)                                                        \
+  __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dst,            \
+       TYPE *__restrict a,              \
+       TYPE *__restrict b, int n)       \
+  {                                                                            \
+    for (int i = 0; i < n; i++)                                                \
+      dst[i] += -(a[i] * b[i]);                                                \
+  }
+
+#define TEST_ALL()                                                             \
+  TEST_TYPE (int8_t)                                                           \
+  TEST_TYPE (uint8_t)                                                          \
+  TEST_TYPE (int16_t)                                                          \
+  TEST_TYPE (uint16_t)                                                         \
+  TEST_TYPE (int32_t)                                                          \
+  TEST_TYPE (uint32_t)                                                         \
+  TEST_TYPE (int64_t)                                                          \
+  TEST_TYPE (uint64_t)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvnmsub\.vv} 8 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-5.c
new file mode 100644
index 0000000..a9a7198
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-5.c
@@ -0,0 +1,34 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE)                                                        \
+  __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1,          \
+       TYPE *__restrict dest2,          \
+       TYPE *__restrict dest3,          \
+       TYPE *__restrict src1,           \
+       TYPE *__restrict src2, int n)    \
+  {                                                                            \
+    for (int i = 0; i < n; ++i)                                                \
+      {                                                                        \
+ dest1[i] += -(src1[i] * src2[i]);                                      \
+ dest2[i] += src1[i] * dest1[i];                                        \
+ dest3[i] += src2[i] * dest2[i];                                        \
+      }                                                                        \
+  }
+
+#define TEST_ALL()                                                             \
+  TEST_TYPE (int8_t)                                                           \
+  TEST_TYPE (uint8_t)                                                          \
+  TEST_TYPE (int16_t)                                                          \
+  TEST_TYPE (uint16_t)                                                         \
+  TEST_TYPE (int32_t)                                                          \
+  TEST_TYPE (uint32_t)                                                         \
+  TEST_TYPE (int64_t)                                                          \
+  TEST_TYPE (uint64_t)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvnmsac\.vv} 8 } } */
+/* { dg-final { scan-assembler-not {\tvmv} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-6.c
new file mode 100644
index 0000000..f38f303
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop-6.c
@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE)                                                        \
+  __attribute__ ((noipa)) void ternop_##TYPE (TYPE *__restrict dest1,          \
+       TYPE *__restrict dest2,          \
+       TYPE *__restrict dest3,          \
+       TYPE *__restrict src1,           \
+       TYPE *__restrict src2, int n)    \
+  {                                                                            \
+    for (int i = 0; i < n; ++i)                                                \
+      {                                                                        \
+ dest1[i] = -(src1[i] * src2[i]) + dest2[i];                            \
+ dest2[i] += src1[i] * dest1[i];                                        \
+ dest3[i] += src2[i] * dest2[i];                                        \
+      }                                                                        \
+  }
+
+#define TEST_ALL()                                                             \
+  TEST_TYPE (int8_t)                                                           \
+  TEST_TYPE (uint8_t)                                                          \
+  TEST_TYPE (int16_t)                                                          \
+  TEST_TYPE (uint16_t)                                                         \
+  TEST_TYPE (int32_t)                                                          \
+  TEST_TYPE (uint32_t)                                                         \
+  TEST_TYPE (int64_t)                                                          \
+  TEST_TYPE (uint64_t)
+
+TEST_ALL ()
+
+/* { dg-final { scan-assembler-times {\tvmv} 8 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-4.c
new file mode 100644
index 0000000..c6f1fe5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-4.c
@@ -0,0 +1,84 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+
+#include "ternop-4.c"
+
+#define TEST_LOOP(TYPE, NUM)                                                   \
+  {                                                                            \
+    TYPE array1_##NUM[NUM] = {};                                               \
+    TYPE array2_##NUM[NUM] = {};                                               \
+    TYPE array3_##NUM[NUM] = {};                                               \
+    TYPE array4_##NUM[NUM] = {};                                               \
+    for (int i = 0; i < NUM; ++i)                                              \
+      {                                                                        \
+ array1_##NUM[i] = (i & 1) + 5;                                         \
+ array2_##NUM[i] = i - NUM / 3;                                         \
+ array3_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ array4_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ asm volatile("" ::: "memory");                                         \
+      }                                                                        \
+    ternop_##TYPE (array3_##NUM, array1_##NUM, array2_##NUM, NUM);             \
+    for (int i = 0; i < NUM; i++)                                              \
+      if (array3_##NUM[i]                                                      \
+   != (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array4_##NUM[i]))  \
+ __builtin_abort ();                                                    \
+  }
+
+int __attribute__ ((optimize (0))) main ()
+{
+  TEST_LOOP (int8_t, 7)
+  TEST_LOOP (uint8_t, 7)
+  TEST_LOOP (int16_t, 7)
+  TEST_LOOP (uint16_t, 7)
+  TEST_LOOP (int32_t, 7)
+  TEST_LOOP (uint32_t, 7)
+  TEST_LOOP (int64_t, 7)
+  TEST_LOOP (uint64_t, 7)
+
+  TEST_LOOP (int8_t, 16)
+  TEST_LOOP (uint8_t, 16)
+  TEST_LOOP (int16_t, 16)
+  TEST_LOOP (uint16_t, 16)
+  TEST_LOOP (int32_t, 16)
+  TEST_LOOP (uint32_t, 16)
+  TEST_LOOP (int64_t, 16)
+  TEST_LOOP (uint64_t, 16)
+
+  TEST_LOOP (int8_t, 77)
+  TEST_LOOP (uint8_t, 77)
+  TEST_LOOP (int16_t, 77)
+  TEST_LOOP (uint16_t, 77)
+  TEST_LOOP (int32_t, 77)
+  TEST_LOOP (uint32_t, 77)
+  TEST_LOOP (int64_t, 77)
+  TEST_LOOP (uint64_t, 77)
+  
+  TEST_LOOP (int8_t, 128)
+  TEST_LOOP (uint8_t, 128)
+  TEST_LOOP (int16_t, 128)
+  TEST_LOOP (uint16_t, 128)
+  TEST_LOOP (int32_t, 128)
+  TEST_LOOP (uint32_t, 128)
+  TEST_LOOP (int64_t, 128)
+  TEST_LOOP (uint64_t, 128)
+
+  TEST_LOOP (int8_t, 15641)
+  TEST_LOOP (uint8_t, 15641)
+  TEST_LOOP (int16_t, 15641)
+  TEST_LOOP (uint16_t, 15641)
+  TEST_LOOP (int32_t, 15641)
+  TEST_LOOP (uint32_t, 15641)
+  TEST_LOOP (int64_t, 15641)
+  TEST_LOOP (uint64_t, 15641)
+  
+  TEST_LOOP (int8_t, 795)
+  TEST_LOOP (uint8_t, 795)
+  TEST_LOOP (int16_t, 795)
+  TEST_LOOP (uint16_t, 795)
+  TEST_LOOP (int32_t, 795)
+  TEST_LOOP (uint32_t, 795)
+  TEST_LOOP (int64_t, 795)
+  TEST_LOOP (uint64_t, 795)
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-5.c
new file mode 100644
index 0000000..81af4b6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-5.c
@@ -0,0 +1,104 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+
+#include "ternop-5.c"
+
+#define TEST_LOOP(TYPE, NUM)                                                   \
+  {                                                                            \
+    TYPE array1_##NUM[NUM] = {};                                               \
+    TYPE array2_##NUM[NUM] = {};                                               \
+    TYPE array3_##NUM[NUM] = {};                                               \
+    TYPE array4_##NUM[NUM] = {};                                               \
+    TYPE array5_##NUM[NUM] = {};                                               \
+    TYPE array6_##NUM[NUM] = {};                                               \
+    TYPE array7_##NUM[NUM] = {};                                               \
+    TYPE array8_##NUM[NUM] = {};                                               \
+    for (int i = 0; i < NUM; ++i)                                              \
+      {                                                                        \
+ array1_##NUM[i] = (i & 1) + 5;                                         \
+ array2_##NUM[i] = i - NUM / 3;                                         \
+ array3_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ array6_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ array4_##NUM[i] = NUM - NUM / 2 + i;                                   \
+ array7_##NUM[i] = NUM - NUM / 2 + i;                                   \
+ array5_##NUM[i] = NUM + i * 7;                                         \
+ array8_##NUM[i] = NUM + i * 7;                                         \
+ asm volatile("" ::: "memory");                                         \
+      }                                                                        \
+    ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM,     \
+    array2_##NUM, NUM);                                         \
+    for (int i = 0; i < NUM; i++)                                              \
+      {                                                                        \
+ array6_##NUM[i]                                                        \
+   = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array6_##NUM[i]);   \
+ if (array3_##NUM[i] != array6_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+ array7_##NUM[i]                                                        \
+   = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]);      \
+ if (array4_##NUM[i] != array7_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+ array8_##NUM[i]                                                        \
+   = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]);      \
+ if (array5_##NUM[i] != array8_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+      }                                                                        \
+  }
+
+int __attribute__ ((optimize (0))) main ()
+{
+  TEST_LOOP (int8_t, 7)
+  TEST_LOOP (uint8_t, 7)
+  TEST_LOOP (int16_t, 7)
+  TEST_LOOP (uint16_t, 7)
+  TEST_LOOP (int32_t, 7)
+  TEST_LOOP (uint32_t, 7)
+  TEST_LOOP (int64_t, 7)
+  TEST_LOOP (uint64_t, 7)
+
+  TEST_LOOP (int8_t, 16)
+  TEST_LOOP (uint8_t, 16)
+  TEST_LOOP (int16_t, 16)
+  TEST_LOOP (uint16_t, 16)
+  TEST_LOOP (int32_t, 16)
+  TEST_LOOP (uint32_t, 16)
+  TEST_LOOP (int64_t, 16)
+  TEST_LOOP (uint64_t, 16)
+
+  TEST_LOOP (int8_t, 77)
+  TEST_LOOP (uint8_t, 77)
+  TEST_LOOP (int16_t, 77)
+  TEST_LOOP (uint16_t, 77)
+  TEST_LOOP (int32_t, 77)
+  TEST_LOOP (uint32_t, 77)
+  TEST_LOOP (int64_t, 77)
+  TEST_LOOP (uint64_t, 77)
+
+  TEST_LOOP (int8_t, 128)
+  TEST_LOOP (uint8_t, 128)
+  TEST_LOOP (int16_t, 128)
+  TEST_LOOP (uint16_t, 128)
+  TEST_LOOP (int32_t, 128)
+  TEST_LOOP (uint32_t, 128)
+  TEST_LOOP (int64_t, 128)
+  TEST_LOOP (uint64_t, 128)
+
+  TEST_LOOP (int8_t, 15641)
+  TEST_LOOP (uint8_t, 15641)
+  TEST_LOOP (int16_t, 15641)
+  TEST_LOOP (uint16_t, 15641)
+  TEST_LOOP (int32_t, 15641)
+  TEST_LOOP (uint32_t, 15641)
+  TEST_LOOP (int64_t, 15641)
+  TEST_LOOP (uint64_t, 15641)
+
+  TEST_LOOP (int8_t, 795)
+  TEST_LOOP (uint8_t, 795)
+  TEST_LOOP (int16_t, 795)
+  TEST_LOOP (uint16_t, 795)
+  TEST_LOOP (int32_t, 795)
+  TEST_LOOP (uint32_t, 795)
+  TEST_LOOP (int64_t, 795)
+  TEST_LOOP (uint64_t, 795)
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-6.c
new file mode 100644
index 0000000..b5e579e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/ternop/ternop_run-6.c
@@ -0,0 +1,104 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable" } */
+
+#include "ternop-6.c"
+
+#define TEST_LOOP(TYPE, NUM)                                                   \
+  {                                                                            \
+    TYPE array1_##NUM[NUM] = {};                                               \
+    TYPE array2_##NUM[NUM] = {};                                               \
+    TYPE array3_##NUM[NUM] = {};                                               \
+    TYPE array4_##NUM[NUM] = {};                                               \
+    TYPE array5_##NUM[NUM] = {};                                               \
+    TYPE array6_##NUM[NUM] = {};                                               \
+    TYPE array7_##NUM[NUM] = {};                                               \
+    TYPE array8_##NUM[NUM] = {};                                               \
+    for (int i = 0; i < NUM; ++i)                                              \
+      {                                                                        \
+ array1_##NUM[i] = (i & 1) + 5;                                         \
+ array2_##NUM[i] = i - NUM / 3;                                         \
+ array3_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ array6_##NUM[i] = NUM - NUM / 3 - i;                                   \
+ array4_##NUM[i] = NUM - NUM / 2 + i;                                   \
+ array7_##NUM[i] = NUM - NUM / 2 + i;                                   \
+ array5_##NUM[i] = NUM + i * 7;                                         \
+ array8_##NUM[i] = NUM + i * 7;                                         \
+ asm volatile("" ::: "memory");                                         \
+      }                                                                        \
+    ternop_##TYPE (array3_##NUM, array4_##NUM, array5_##NUM, array1_##NUM,     \
+    array2_##NUM, NUM);                                         \
+    for (int i = 0; i < NUM; i++)                                              \
+      {                                                                        \
+ array6_##NUM[i]                                                        \
+   = (TYPE) (-(array1_##NUM[i] * array2_##NUM[i]) + array7_##NUM[i]);   \
+ if (array3_##NUM[i] != array6_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+ array7_##NUM[i]                                                        \
+   = (TYPE) (array1_##NUM[i] * array6_##NUM[i] + array7_##NUM[i]);      \
+ if (array4_##NUM[i] != array7_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+ array8_##NUM[i]                                                        \
+   = (TYPE) (array2_##NUM[i] * array7_##NUM[i] + array8_##NUM[i]);      \
+ if (array5_##NUM[i] != array8_##NUM[i])                                \
+   __builtin_abort ();                                                  \
+      }                                                                        \
+  }
+
+int __attribute__ ((optimize (0))) main ()
+{
+  TEST_LOOP (int8_t, 7)
+  TEST_LOOP (uint8_t, 7)
+  TEST_LOOP (int16_t, 7)
+  TEST_LOOP (uint16_t, 7)
+  TEST_LOOP (int32_t, 7)
+  TEST_LOOP (uint32_t, 7)
+  TEST_LOOP (int64_t, 7)
+  TEST_LOOP (uint64_t, 7)
+
+  TEST_LOOP (int8_t, 16)
+  TEST_LOOP (uint8_t, 16)
+  TEST_LOOP (int16_t, 16)
+  TEST_LOOP (uint16_t, 16)
+  TEST_LOOP (int32_t, 16)
+  TEST_LOOP (uint32_t, 16)
+  TEST_LOOP (int64_t, 16)
+  TEST_LOOP (uint64_t, 16)
+
+  TEST_LOOP (int8_t, 77)
+  TEST_LOOP (uint8_t, 77)
+  TEST_LOOP (int16_t, 77)
+  TEST_LOOP (uint16_t, 77)
+  TEST_LOOP (int32_t, 77)
+  TEST_LOOP (uint32_t, 77)
+  TEST_LOOP (int64_t, 77)
+  TEST_LOOP (uint64_t, 77)
+
+  TEST_LOOP (int8_t, 128)
+  TEST_LOOP (uint8_t, 128)
+  TEST_LOOP (int16_t, 128)
+  TEST_LOOP (uint16_t, 128)
+  TEST_LOOP (int32_t, 128)
+  TEST_LOOP (uint32_t, 128)
+  TEST_LOOP (int64_t, 128)
+  TEST_LOOP (uint64_t, 128)
+
+  TEST_LOOP (int8_t, 15641)
+  TEST_LOOP (uint8_t, 15641)
+  TEST_LOOP (int16_t, 15641)
+  TEST_LOOP (uint16_t, 15641)
+  TEST_LOOP (int32_t, 15641)
+  TEST_LOOP (uint32_t, 15641)
+  TEST_LOOP (int64_t, 15641)
+  TEST_LOOP (uint64_t, 15641)
+
+  TEST_LOOP (int8_t, 795)
+  TEST_LOOP (uint8_t, 795)
+  TEST_LOOP (int16_t, 795)
+  TEST_LOOP (uint16_t, 795)
+  TEST_LOOP (int32_t, 795)
+  TEST_LOOP (uint32_t, 795)
+  TEST_LOOP (int64_t, 795)
+  TEST_LOOP (uint64_t, 795)
+
+  return 0;
+}