[PATCH v3 09/16] tcg/loongarch64: Lower vector min max ops

[Jiajie Chen]

Lower the following ops:

- smin_vec
- smax_vec
- umin_vec
- umax_vec

Signed-off-by: Jiajie Chen <c@jia.je>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 6905775698..3ffc1691cd 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1668,6 +1668,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn mul_vec_insn[4] = {
         OPC_VMUL_B, OPC_VMUL_H, OPC_VMUL_W, OPC_VMUL_D
     };
+    static const LoongArchInsn smin_vec_insn[4] = {
+        OPC_VMIN_B, OPC_VMIN_H, OPC_VMIN_W, OPC_VMIN_D
+    };
+    static const LoongArchInsn umin_vec_insn[4] = {
+        OPC_VMIN_BU, OPC_VMIN_HU, OPC_VMIN_WU, OPC_VMIN_DU
+    };
+    static const LoongArchInsn smax_vec_insn[4] = {
+        OPC_VMAX_B, OPC_VMAX_H, OPC_VMAX_W, OPC_VMAX_D
+    };
+    static const LoongArchInsn umax_vec_insn[4] = {
+        OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1804,6 +1816,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_mul_vec:
         tcg_out32(s, encode_vdvjvk_insn(mul_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_smin_vec:
+        tcg_out32(s, encode_vdvjvk_insn(smin_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_smax_vec:
+        tcg_out32(s, encode_vdvjvk_insn(smax_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_umin_vec:
+        tcg_out32(s, encode_vdvjvk_insn(umin_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_umax_vec:
+        tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1831,6 +1855,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, 
unsigned vece)
     case INDEX_op_not_vec:
     case INDEX_op_neg_vec:
     case INDEX_op_mul_vec:
+    case INDEX_op_smin_vec:
+    case INDEX_op_smax_vec:
+    case INDEX_op_umin_vec:
+    case INDEX_op_umax_vec:
         return 1;
     default:
         return 0;
@@ -2006,6 +2034,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
     case INDEX_op_xor_vec:
     case INDEX_op_nor_vec:
     case INDEX_op_mul_vec:
+    case INDEX_op_smin_vec:
+    case INDEX_op_smax_vec:
+    case INDEX_op_umin_vec:
+    case INDEX_op_umax_vec:
         return C_O1_I2(w, w, w);
 
     case INDEX_op_not_vec:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 2c2266ed31..ec725aaeaa 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -193,7 +193,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_sat_vec          0
-#define TCG_TARGET_HAS_minmax_vec       0
+#define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       0
 
-- 
2.42.0