RISC-V: Implement vector "average" autovec pattern.

This patch adds vector average patterns

 op[0] = (narrow) ((wide) op[1] + (wide) op[2]) >> 1;
 op[0] = (narrow) ((wide) op[1] + (wide) op[2] + 1) >> 1;

If there is no direct support, the vectorizer can synthesize the pattern
but, presumably, due to lack of narrowing operation support, won't try a
narrowing shift.  Therefore, this patch implements the expanders
instead.

gcc/ChangeLog:

	* config/riscv/autovec.md (<u>avg<v_double_trunc>3_floor):
	Implement expander.
	(<u>avg<v_double_trunc>3_ceil): Ditto.
	* config/riscv/vector-iterators.md (ashiftrt): New iterator.
	(ASHIFTRT): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/widen/vec-avg-run.c: New test.
	* gcc.target/riscv/rvv/autovec/widen/vec-avg-rv32gcv.c: New test.
	* gcc.target/riscv/rvv/autovec/widen/vec-avg-rv64gcv.c: New test.
	* gcc.target/riscv/rvv/autovec/widen/vec-avg-template.h: New test.

6 files changed, 209 insertions, 0 deletions

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 21cf2ff..acca4c2 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -2044,3 +2044,69 @@
 				    riscv_vector::reduction_type::MASK_LEN_FOLD_LEFT);
   DONE;
 })
+
+;; -------------------------------------------------------------------------
+;; ---- [INT] Average.
+;; -------------------------------------------------------------------------
+;; Implements the following "average" patterns:
+;; floor:
+;;  op[0] = (narrow) ((wide) op[1] + (wide) op[2]) >> 1;
+;; ceil:
+;;  op[0] = (narrow) ((wide) op[1] + (wide) op[2] + 1)) >> 1;
+;; -------------------------------------------------------------------------
+
+(define_expand "<u>avg<v_double_trunc>3_floor"
+ [(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand")
+   (truncate:<V_DOUBLE_TRUNC>
+    (<ext_to_rshift>:VWEXTI
+     (plus:VWEXTI
+      (any_extend:VWEXTI
+       (match_operand:<V_DOUBLE_TRUNC> 1 "register_operand"))
+      (any_extend:VWEXTI
+       (match_operand:<V_DOUBLE_TRUNC> 2 "register_operand"))))))]
+  "TARGET_VECTOR"
+{
+  /* First emit a widening addition.  */
+  rtx tmp1 = gen_reg_rtx (<MODE>mode);
+  rtx ops1[] = {tmp1, operands[1], operands[2]};
+  insn_code icode = code_for_pred_dual_widen (PLUS, <CODE>, <MODE>mode);
+  riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, ops1);
+
+  /* Then a narrowing shift.  */
+  rtx ops2[] = {operands[0], tmp1, const1_rtx};
+  icode = code_for_pred_narrow_scalar (<EXT_TO_RSHIFT>, <MODE>mode);
+  riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, ops2);
+  DONE;
+})
+
+(define_expand "<u>avg<v_double_trunc>3_ceil"
+ [(set (match_operand:<V_DOUBLE_TRUNC> 0 "register_operand")
+   (truncate:<V_DOUBLE_TRUNC>
+    (<ext_to_rshift>:VWEXTI
+     (plus:VWEXTI
+      (plus:VWEXTI
+       (any_extend:VWEXTI
+	(match_operand:<V_DOUBLE_TRUNC> 1 "register_operand"))
+       (any_extend:VWEXTI
+	(match_operand:<V_DOUBLE_TRUNC> 2 "register_operand")))
+      (const_int 1)))))]
+  "TARGET_VECTOR"
+{
+  /* First emit a widening addition.  */
+  rtx tmp1 = gen_reg_rtx (<MODE>mode);
+  rtx ops1[] = {tmp1, operands[1], operands[2]};
+  insn_code icode = code_for_pred_dual_widen (PLUS, <CODE>, <MODE>mode);
+  riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, ops1);
+
+  /* Then add 1.  */
+  rtx tmp2 = gen_reg_rtx (<MODE>mode);
+  rtx ops2[] = {tmp2, tmp1, const1_rtx};
+  icode = code_for_pred_scalar (PLUS, <MODE>mode);
+  riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, ops2);
+
+  /* Finally, a narrowing shift.  */
+  rtx ops3[] = {operands[0], tmp2, const1_rtx};
+  icode = code_for_pred_narrow_scalar (<EXT_TO_RSHIFT>, <MODE>mode);
+  riscv_vector::emit_vlmax_insn (icode, riscv_vector::RVV_BINOP, ops3);
+  DONE;
+})
diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index fc237ac..4023a03 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -2040,6 +2040,11 @@
 (define_code_attr nmsub_nmadd [(plus "nmsub") (minus "nmadd")])
 (define_code_attr nmsac_nmacc [(plus "nmsac") (minus "nmacc")])
 
+(define_code_attr ext_to_rshift [(sign_extend "ashiftrt")
+                                 (zero_extend "lshiftrt")])
+(define_code_attr EXT_TO_RSHIFT [(sign_extend "ASHIFTRT")
+                                 (zero_extend "LSHIFTRT")])
+
 (define_code_iterator and_ior [and ior])
 
 (define_code_iterator any_float_binop [plus mult minus div])
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-run.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-run.c
new file mode 100644
index 0000000..7ca193e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-run.c
@@ -0,0 +1,85 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable -lm" } */
+
+#include <limits.h>
+#include <math.h>
+#include <assert.h>
+
+#include "vec-avg-template.h"
+
+#define SZ 256
+
+#define RUNS1(TYPE, SCALE)                                                     \
+  TYPE a##TYPE[SZ + 1];                                                        \
+  TYPE b##TYPE[SZ + 1];                                                        \
+  TYPE dst##TYPE[SZ + 1];                                                      \
+  for (int cnt = 0, i = -(SZ * SCALE) / 2; i < (SZ * SCALE) / 2; i += SCALE)   \
+    {                                                                          \
+      a##TYPE[cnt] = i;                                                        \
+      b##TYPE[cnt] = i + 1;                                                    \
+      dst##TYPE[cnt++] = 0;                                                    \
+    }                                                                          \
+  vavg_##TYPE (dst##TYPE, a##TYPE, b##TYPE, SZ);                               \
+  for (int i = 0; i < SZ; i += SCALE)                                          \
+    assert (dst##TYPE[i] == floor ((a##TYPE[i] + b##TYPE[i]) / 2.0));
+
+#define RUNU1(TYPE, SCALE)                                                     \
+  TYPE a##TYPE[SZ + 1];                                                        \
+  TYPE b##TYPE[SZ + 1];                                                        \
+  TYPE dst##TYPE[SZ + 1];                                                      \
+  for (int cnt = 0, i = 0; i < (SZ * SCALE); i += SCALE)                       \
+    {                                                                          \
+      a##TYPE[cnt] = i;                                                        \
+      b##TYPE[cnt] = i + 1;                                                    \
+      dst##TYPE[cnt++] = 0;                                                    \
+    }                                                                          \
+  vavg_##TYPE (dst##TYPE, a##TYPE, b##TYPE, SZ);                               \
+  for (int i = 0; i < SZ; i += SCALE)                                          \
+    assert (dst##TYPE[i] == floor ((a##TYPE[i] + b##TYPE[i]) / 2.0));
+
+#define RUNS2(TYPE, SCALE)                                                     \
+  TYPE a2##TYPE[SZ + 1];                                                       \
+  TYPE b2##TYPE[SZ + 1];                                                       \
+  TYPE dst2##TYPE[SZ + 1];                                                     \
+  for (int cnt = 0, i = -(SZ * SCALE) / 2; i < (SZ * SCALE) / 2; i += SCALE)   \
+    {                                                                          \
+      a2##TYPE[cnt] = i;                                                       \
+      b2##TYPE[cnt] = i + 1;                                                   \
+      dst2##TYPE[cnt++] = 0;                                                   \
+    }                                                                          \
+  vavg2_##TYPE (dst2##TYPE, a2##TYPE, b2##TYPE, SZ);                           \
+  for (int i = 0; i < SZ; i += SCALE)                                          \
+    assert (dst2##TYPE[i] == ceil ((a2##TYPE[i] + b2##TYPE[i]) / 2.0));
+
+#define RUNU2(TYPE, SCALE)                                                     \
+  TYPE a2##TYPE[SZ + 1];                                                       \
+  TYPE b2##TYPE[SZ + 1];                                                       \
+  TYPE dst2##TYPE[SZ + 1];                                                     \
+  for (int cnt = 0, i = 0; i < (SZ * SCALE); i += SCALE)                       \
+    {                                                                          \
+      a2##TYPE[cnt] = i;                                                       \
+      b2##TYPE[cnt] = i + 1;                                                   \
+      dst2##TYPE[cnt++] = 0;                                                   \
+    }                                                                          \
+  vavg2_##TYPE (dst2##TYPE, a2##TYPE, b2##TYPE, SZ);                           \
+  for (int i = 0; i < SZ; i += SCALE)                                          \
+    assert (dst2##TYPE[i] == ceil ((a2##TYPE[i] + b2##TYPE[i]) / 2.0));
+
+#define RUN_ALL()                                                              \
+  RUNS1 (int8_t, 1)                                                            \
+  RUNS1 (int16_t, 256)                                                         \
+  RUNS1 (int32_t, 65536)                                                       \
+  RUNU1 (uint8_t, 1)                                                           \
+  RUNU1 (uint16_t, 256)                                                        \
+  RUNU1 (uint32_t, 65536)                                                      \
+  RUNS2 (int8_t, 1)                                                            \
+  RUNS2 (int16_t, 256)                                                         \
+  RUNS2 (int32_t, 65536)                                                       \
+  RUNU2 (uint8_t, 1)                                                           \
+  RUNU2 (uint16_t, 256)                                                        \
+  RUNU2 (uint32_t, 65536)\
+
+int main ()
+{
+  RUN_ALL ()
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv32gcv.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv32gcv.c
new file mode 100644
index 0000000..e275433
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv32gcv.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model -march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable" } */
+
+#include "vec-avg-template.h"
+
+/* { dg-final { scan-assembler-times {\tvwadd\.vv} 6 } } */
+/* { dg-final { scan-assembler-times {\tvwaddu\.vv} 6 } } */
+/* { dg-final { scan-assembler-times {\tvadd\.vi} 6 } } */
+/* { dg-final { scan-assembler-times {\tvnsrl.wi} 6 } } */
+/* { dg-final { scan-assembler-times {\tvnsra.wi} 6 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv64gcv.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv64gcv.c
new file mode 100644
index 0000000..1f0ef29
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-rv64gcv.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model -march=rv64gcv -mabi=lp64d --param=riscv-autovec-preference=scalable" } */
+
+#include "vec-avg-template.h"
+
+/* { dg-final { scan-assembler-times {\tvwadd\.vv} 6 } } */
+/* { dg-final { scan-assembler-times {\tvwaddu\.vv} 6 } } */
+/* { dg-final { scan-assembler-times {\tvadd\.vi} 6 } } */
+/* { dg-final { scan-assembler-times {\tvnsrl\.wi} 6 } } */
+/* { dg-final { scan-assembler-times {\tvnsra\.wi} 6 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-template.h b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-template.h
new file mode 100644
index 0000000..9c2a6f1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/widen/vec-avg-template.h
@@ -0,0 +1,33 @@
+#include <stdint-gcc.h>
+
+#define TEST_TYPE(TYPE, TYPE2)                                                 \
+  __attribute__ ((noipa)) void vavg_##TYPE (TYPE *dst, TYPE *a, TYPE *b,       \
+					    int n)                             \
+  {                                                                            \
+    for (int i = 0; i < n; i++)                                                \
+      dst[i] = ((TYPE2) a[i] + b[i]) >> 1;                                     \
+  }
+
+#define TEST_TYPE2(TYPE, TYPE2)                                                \
+  __attribute__ ((noipa)) void vavg2_##TYPE (TYPE *dst, TYPE *a, TYPE *b,      \
+					     int n)                            \
+  {                                                                            \
+    for (int i = 0; i < n; i++)                                                \
+      dst[i] = ((TYPE2) a[i] + b[i] + 1) >> 1;                                 \
+  }
+
+#define TEST_ALL()                                                             \
+  TEST_TYPE (int8_t, int16_t)                                                  \
+  TEST_TYPE (uint8_t, uint16_t)                                                \
+  TEST_TYPE (int16_t, int32_t)                                                 \
+  TEST_TYPE (uint16_t, uint32_t)                                               \
+  TEST_TYPE (int32_t, int64_t)                                                 \
+  TEST_TYPE (uint32_t, uint64_t)                                               \
+  TEST_TYPE2 (int8_t, int16_t)                                                 \
+  TEST_TYPE2 (uint8_t, uint16_t)                                               \
+  TEST_TYPE2 (int16_t, int32_t)                                                \
+  TEST_TYPE2 (uint16_t, uint32_t)                                              \
+  TEST_TYPE2 (int32_t, int64_t)                                                \
+  TEST_TYPE2 (uint32_t, uint64_t)
+
+TEST_ALL()