[PATCH v4 14/16] tcg/loongarch64: Lower rotv_vec ops to LSX

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 14/16] tcg/loongarch64: Lower rotv_vec ops to LSX
Posted by Jiajie Chen 1 year, 2 months ago
Lower the following ops:

- rotrv_vec
- rotlv_vec

Signed-off-by: Jiajie Chen <c@jia.je>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target.c.inc | 14 ++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index c21c917083..8f448823b0 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1743,6 +1743,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn sari_vec_insn[4] = {
         OPC_VSRAI_B, OPC_VSRAI_H, OPC_VSRAI_W, OPC_VSRAI_D
     };
+    static const LoongArchInsn rotrv_vec_insn[4] = {
+        OPC_VROTR_B, OPC_VROTR_H, OPC_VROTR_W, OPC_VROTR_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1890,6 +1893,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_sari_vec:
         tcg_out32(s, encode_vdvjuk3_insn(sari_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_rotrv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(rotrv_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_rotlv_vec:
+        /* rotlv_vec a1, a2 = rotrv_vec a1, -a2 */
+        tcg_out32(s, encode_vdvj_insn(neg_vec_insn[vece], temp_vec, a2));
+        tcg_out32(s, encode_vdvjvk_insn(rotrv_vec_insn[vece], a0, a1,
+                                        temp_vec));
+        break;
     case INDEX_op_bitsel_vec:
         /* vbitsel vd, vj, vk, va = bitsel_vec vd, va, vk, vj */
         tcg_out_opc_vbitsel_v(s, a0, a3, a2, a1);
@@ -2119,6 +2131,8 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_shlv_vec:
     case INDEX_op_shrv_vec:
     case INDEX_op_sarv_vec:
+    case INDEX_op_rotrv_vec:
+    case INDEX_op_rotlv_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 d7b806e252..d5c69bc192 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -191,7 +191,7 @@ extern bool use_lsx_instructions;
 #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
+#define TCG_TARGET_HAS_rotv_vec         1
 #define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       1
-- 
2.42.0