target/loongarch: Implement vadda

This patch includes:
- VADDA.{B/H/W/D}.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-13-gaosong@loongson.cn>

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index e98ea377930a948a8a4b38e08cfe73ecade9734a..1f61e67d1f8fbe0fa1215c44133fdfd8adf88294 100644 (file)
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -934,3 +934,8 @@ INSN_LSX(vabsd_bu,         vvv)
 INSN_LSX(vabsd_hu,         vvv)
 INSN_LSX(vabsd_wu,         vvv)
 INSN_LSX(vabsd_du,         vvv)
+
+INSN_LSX(vadda_b,          vvv)
+INSN_LSX(vadda_h,          vvv)
+INSN_LSX(vadda_w,          vvv)
+INSN_LSX(vadda_d,          vvv)

diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index c3a5d2566e772fdee701b8d6c4f3bf4bdaa40278..85fb8f60d2162513fe47f81b89534af8f441c358 100644 (file)
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -220,3 +220,8 @@ DEF_HELPER_FLAGS_4(vabsd_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vabsd_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vabsd_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vabsd_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(vadda_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vadda_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc b/target/loongarch/insn_trans/trans_lsx.c.inc
index 0e9301bf935984b05628d379622384c7450234b1..8ad81c851744a2d2e7e53510b7f3937375c0e496 100644 (file)
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -1261,3 +1261,56 @@ TRANS(vabsd_bu, gvec_vvv, MO_8, do_vabsd_u)
 TRANS(vabsd_hu, gvec_vvv, MO_16, do_vabsd_u)
 TRANS(vabsd_wu, gvec_vvv, MO_32, do_vabsd_u)
 TRANS(vabsd_du, gvec_vvv, MO_64, do_vabsd_u)
+
+static void gen_vadda(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t1, t2;
+
+    t1 = tcg_temp_new_vec_matching(a);
+    t2 = tcg_temp_new_vec_matching(b);
+
+    tcg_gen_abs_vec(vece, t1, a);
+    tcg_gen_abs_vec(vece, t2, b);
+    tcg_gen_add_vec(vece, t, t1, t2);
+}
+
+static void do_vadda(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+                     uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_abs_vec, INDEX_op_add_vec, 0
+        };
+    static const GVecGen3 op[4] = {
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_b,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_h,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_w,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vadda,
+            .fno = gen_helper_vadda_d,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+    };
+
+    tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vadda_b, gvec_vvv, MO_8, do_vadda)
+TRANS(vadda_h, gvec_vvv, MO_16, do_vadda)
+TRANS(vadda_w, gvec_vvv, MO_32, do_vadda)
+TRANS(vadda_d, gvec_vvv, MO_64, do_vadda)

diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 825ddedf4dc7b0c7512b4279074c8dba4e823331..6cb22f9297d6498241babf6c79ca3800e7a67ed5 100644 (file)
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -628,3 +628,8 @@ vabsd_bu         0111 00000110 00100 ..... ..... .....    @vvv
 vabsd_hu         0111 00000110 00101 ..... ..... .....    @vvv
 vabsd_wu         0111 00000110 00110 ..... ..... .....    @vvv
 vabsd_du         0111 00000110 00111 ..... ..... .....    @vvv
+
+vadda_b          0111 00000101 11000 ..... ..... .....    @vvv
+vadda_h          0111 00000101 11001 ..... ..... .....    @vvv
+vadda_w          0111 00000101 11010 ..... ..... .....    @vvv
+vadda_d          0111 00000101 11011 ..... ..... .....    @vvv

diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index f0baffa9e3f49be59aacc9622291f6d7cf2f1331..8230fe2ed5b5ebd2980e457ee655cd56c9ce67bd 100644 (file)
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -318,3 +318,22 @@ DO_3OP(vabsd_bu, 8, UB, DO_VABSD)
 DO_3OP(vabsd_hu, 16, UH, DO_VABSD)
 DO_3OP(vabsd_wu, 32, UW, DO_VABSD)
 DO_3OP(vabsd_du, 64, UD, DO_VABSD)
+
+#define DO_VABS(a)  ((a < 0) ? (-a) : (a))
+
+#define DO_VADDA(NAME, BIT, E, DO_OP)                       \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{                                                           \
+    int i;                                                  \
+    VReg *Vd = (VReg *)vd;                                  \
+    VReg *Vj = (VReg *)vj;                                  \
+    VReg *Vk = (VReg *)vk;                                  \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                     \
+        Vd->E(i) = DO_OP(Vj->E(i)) + DO_OP(Vk->E(i));       \
+    }                                                       \
+}
+
+DO_VADDA(vadda_b, 8, B, DO_VABS)
+DO_VADDA(vadda_h, 16, H, DO_VABS)
+DO_VADDA(vadda_w, 32, W, DO_VABS)
+DO_VADDA(vadda_d, 64, D, DO_VABS)