[PATCH v4 10/16] tcg/loongarch64: Lower vector saturated ops

Jiajie Chen posted 16 patches 1 year, 2 months ago
Maintainers: Richard Henderson <richard.henderson@linaro.org>, WANG Xuerui <git@xen0n.name>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, Aurelien Jarno <aurelien@aurel32.net>, Huacai Chen <chenhuacai@kernel.org>, Jiaxun Yang <jiaxun.yang@flygoat.com>, Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>, Palmer Dabbelt <palmer@dabbelt.com>, Alistair Francis <Alistair.Francis@wdc.com>, Stefan Weil <sw@weilnetz.de>
[PATCH v4 10/16] tcg/loongarch64: Lower vector saturated ops
Posted by Jiajie Chen 1 year, 2 months ago
Lower the following ops:

- ssadd_vec
- usadd_vec
- sssub_vec
- ussub_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 bdf22d8807..90c52c38cf 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1713,6 +1713,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn umax_vec_insn[4] = {
         OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
     };
+    static const LoongArchInsn ssadd_vec_insn[4] = {
+        OPC_VSADD_B, OPC_VSADD_H, OPC_VSADD_W, OPC_VSADD_D
+    };
+    static const LoongArchInsn usadd_vec_insn[4] = {
+        OPC_VSADD_BU, OPC_VSADD_HU, OPC_VSADD_WU, OPC_VSADD_DU
+    };
+    static const LoongArchInsn sssub_vec_insn[4] = {
+        OPC_VSSUB_B, OPC_VSSUB_H, OPC_VSSUB_W, OPC_VSSUB_D
+    };
+    static const LoongArchInsn ussub_vec_insn[4] = {
+        OPC_VSSUB_BU, OPC_VSSUB_HU, OPC_VSSUB_WU, OPC_VSSUB_DU
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1829,6 +1841,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_umax_vec:
         tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_ssadd_vec:
+        tcg_out32(s, encode_vdvjvk_insn(ssadd_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_usadd_vec:
+        tcg_out32(s, encode_vdvjvk_insn(usadd_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sssub_vec:
+        tcg_out32(s, encode_vdvjvk_insn(sssub_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_ussub_vec:
+        tcg_out32(s, encode_vdvjvk_insn(ussub_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1860,6 +1884,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_smax_vec:
     case INDEX_op_umin_vec:
     case INDEX_op_umax_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_ussub_vec:
         return 1;
     default:
         return 0;
@@ -2039,6 +2067,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_smax_vec:
     case INDEX_op_umin_vec:
     case INDEX_op_umax_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_ussub_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 ec725aaeaa..fa14558275 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -192,7 +192,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_roti_vec         0
 #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_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       0
-- 
2.42.0