[PATCH v4 11/16] tcg/loongarch64: Lower vector shift vector 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 11/16] tcg/loongarch64: Lower vector shift vector ops
Posted by Jiajie Chen 1 year, 2 months ago
Lower the following ops:

- shlv_vec
- shrv_vec
- sarv_vec

Signed-off-by: Jiajie Chen <c@jia.je>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target.c.inc | 24 ++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 90c52c38cf..6958fd219c 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1725,6 +1725,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn ussub_vec_insn[4] = {
         OPC_VSSUB_BU, OPC_VSSUB_HU, OPC_VSSUB_WU, OPC_VSSUB_DU
     };
+    static const LoongArchInsn shlv_vec_insn[4] = {
+        OPC_VSLL_B, OPC_VSLL_H, OPC_VSLL_W, OPC_VSLL_D
+    };
+    static const LoongArchInsn shrv_vec_insn[4] = {
+        OPC_VSRL_B, OPC_VSRL_H, OPC_VSRL_W, OPC_VSRL_D
+    };
+    static const LoongArchInsn sarv_vec_insn[4] = {
+        OPC_VSRA_B, OPC_VSRA_H, OPC_VSRA_W, OPC_VSRA_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1853,6 +1862,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ussub_vec:
         tcg_out32(s, encode_vdvjvk_insn(ussub_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_shlv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(shlv_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_shrv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(shrv_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sarv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(sarv_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1888,6 +1906,9 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_usadd_vec:
     case INDEX_op_sssub_vec:
     case INDEX_op_ussub_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return 1;
     default:
         return 0;
@@ -2071,6 +2092,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_usadd_vec:
     case INDEX_op_sssub_vec:
     case INDEX_op_ussub_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_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 fa14558275..7e9fb61c47 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -188,7 +188,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_mul_vec          1
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
-#define TCG_TARGET_HAS_shv_vec          0
+#define TCG_TARGET_HAS_shv_vec          1
 #define TCG_TARGET_HAS_roti_vec         0
 #define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
-- 
2.42.0