[30/38] tcg/aarch64: Support vector comparison select value

Message ID 20190420073442.7488-31-richard.henderson@linaro.org
State New
Headers show
Series
  • tcg vector improvements
Related show

Commit Message

Richard Henderson April 20, 2019, 7:34 a.m.
The instruction set has 3 insns that perform the same operation,
only varying in which operand must overlap the destination.  We
can represent the operation without overlap and choose based on
the operands seen.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 tcg/aarch64/tcg-target.h     |  2 +-
 tcg/aarch64/tcg-target.inc.c | 24 +++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 2 deletions(-)

-- 
2.17.1

Patch

diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index e1135e930a..e030bf3c8f 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -140,7 +140,7 @@  typedef enum {
 #define TCG_TARGET_HAS_mul_vec          1
 #define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
-#define TCG_TARGET_HAS_cmpsel_vec       0
+#define TCG_TARGET_HAS_cmpsel_vec       1
 
 #define TCG_TARGET_DEFAULT_MO (0)
 #define TCG_TARGET_HAS_MEMORY_BSWAP     1
diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c
index cf891defd4..84d402acd8 100644
--- a/tcg/aarch64/tcg-target.inc.c
+++ b/tcg/aarch64/tcg-target.inc.c
@@ -525,6 +525,9 @@  typedef enum {
     I3616_ADD       = 0x0e208400,
     I3616_AND       = 0x0e201c00,
     I3616_BIC       = 0x0e601c00,
+    I3616_BIF       = 0x2ee01c00,
+    I3616_BIT       = 0x2ea01c00,
+    I3616_BSL       = 0x2e601c00,
     I3616_EOR       = 0x2e201c00,
     I3616_MUL       = 0x0e209c00,
     I3616_ORR       = 0x0ea01c00,
@@ -2178,7 +2181,7 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
 
     TCGType type = vecl + TCG_TYPE_V64;
     unsigned is_q = vecl;
-    TCGArg a0, a1, a2;
+    TCGArg a0, a1, a2, a3;
 
     a0 = args[0];
     a1 = args[1];
@@ -2301,6 +2304,20 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         }
         break;
 
+    case INDEX_op_cmpsel_vec:
+        a3 = args[3];
+        if (a0 == a3) {
+            tcg_out_insn(s, 3616, BIT, is_q, 0, a0, a2, a1);
+        } else if (a0 == a2) {
+            tcg_out_insn(s, 3616, BIF, is_q, 0, a0, a3, a1);
+        } else {
+            if (a0 != a1) {
+                tcg_out_mov(s, type, a0, a1);
+            }
+            tcg_out_insn(s, 3616, BSL, is_q, 0, a0, a2, a3);
+        }
+        break;
+
     case INDEX_op_mov_vec:  /* Always emitted via tcg_out_mov.  */
     case INDEX_op_dupi_vec: /* Always emitted via tcg_out_movi.  */
     case INDEX_op_dup_vec:  /* Always emitted via tcg_out_dup_vec.  */
@@ -2323,6 +2340,7 @@  int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_abs_vec:
     case INDEX_op_not_vec:
     case INDEX_op_cmp_vec:
+    case INDEX_op_cmpsel_vec:
     case INDEX_op_shli_vec:
     case INDEX_op_shri_vec:
     case INDEX_op_sari_vec:
@@ -2405,6 +2423,8 @@  static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
         = { .args_ct_str = { "r", "r", "rA", "rZ", "rZ" } };
     static const TCGTargetOpDef add2
         = { .args_ct_str = { "r", "r", "rZ", "rZ", "rA", "rMZ" } };
+    static const TCGTargetOpDef w_w_w_w
+        = { .args_ct_str = { "w", "w", "w", "w" } };
 
     switch (op) {
     case INDEX_op_goto_ptr:
@@ -2577,6 +2597,8 @@  static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
         return &w_wr;
     case INDEX_op_cmp_vec:
         return &w_w_wZ;
+    case INDEX_op_cmpsel_vec:
+        return &w_w_w_w;
 
     default:
         return NULL;