[PATCH v3 18/47] target/loongarch; Implement xvdiv/xvmod

[Song Gao]

This patch includes:
- XVDIV.{B/H/W/D}[U];
- XVMOD.{B/H/W/D}[U].

Signed-off-by: Song Gao <gaosong@loongson.cn>
---
 target/loongarch/disas.c                     | 17 +++++++++++++++++
 target/loongarch/insn_trans/trans_lasx.c.inc | 17 +++++++++++++++++
 target/loongarch/insns.decode                | 17 +++++++++++++++++
 target/loongarch/vec.h                       |  7 +++++++
 target/loongarch/vec_helper.c                | 10 ++--------
 5 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index b115fe8315..72df9f0b08 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1962,6 +1962,23 @@ INSN_LASX(xvmaddwod_w_hu_h,  vvv)
 INSN_LASX(xvmaddwod_d_wu_w,  vvv)
 INSN_LASX(xvmaddwod_q_du_d,  vvv)
 
+INSN_LASX(xvdiv_b,           vvv)
+INSN_LASX(xvdiv_h,           vvv)
+INSN_LASX(xvdiv_w,           vvv)
+INSN_LASX(xvdiv_d,           vvv)
+INSN_LASX(xvdiv_bu,          vvv)
+INSN_LASX(xvdiv_hu,          vvv)
+INSN_LASX(xvdiv_wu,          vvv)
+INSN_LASX(xvdiv_du,          vvv)
+INSN_LASX(xvmod_b,           vvv)
+INSN_LASX(xvmod_h,           vvv)
+INSN_LASX(xvmod_w,           vvv)
+INSN_LASX(xvmod_d,           vvv)
+INSN_LASX(xvmod_bu,          vvv)
+INSN_LASX(xvmod_hu,          vvv)
+INSN_LASX(xvmod_wu,          vvv)
+INSN_LASX(xvmod_du,          vvv)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)
diff --git a/target/loongarch/insn_trans/trans_lasx.c.inc 
b/target/loongarch/insn_trans/trans_lasx.c.inc
index 1f9574a83b..118635dc1a 100644
--- a/target/loongarch/insn_trans/trans_lasx.c.inc
+++ b/target/loongarch/insn_trans/trans_lasx.c.inc
@@ -287,6 +287,23 @@ TRANS(xvmaddwod_h_bu_b, gvec_vvv, 32, MO_8, 
do_vmaddwod_u_s)
 TRANS(xvmaddwod_w_hu_h, gvec_vvv, 32, MO_16, do_vmaddwod_u_s)
 TRANS(xvmaddwod_d_wu_w, gvec_vvv, 32, MO_32, do_vmaddwod_u_s)
 
+TRANS(xvdiv_b, gen_vvv, 32, gen_helper_vdiv_b)
+TRANS(xvdiv_h, gen_vvv, 32, gen_helper_vdiv_h)
+TRANS(xvdiv_w, gen_vvv, 32, gen_helper_vdiv_w)
+TRANS(xvdiv_d, gen_vvv, 32, gen_helper_vdiv_d)
+TRANS(xvdiv_bu, gen_vvv, 32, gen_helper_vdiv_bu)
+TRANS(xvdiv_hu, gen_vvv, 32, gen_helper_vdiv_hu)
+TRANS(xvdiv_wu, gen_vvv, 32, gen_helper_vdiv_wu)
+TRANS(xvdiv_du, gen_vvv, 32, gen_helper_vdiv_du)
+TRANS(xvmod_b, gen_vvv, 32, gen_helper_vmod_b)
+TRANS(xvmod_h, gen_vvv, 32, gen_helper_vmod_h)
+TRANS(xvmod_w, gen_vvv, 32, gen_helper_vmod_w)
+TRANS(xvmod_d, gen_vvv, 32, gen_helper_vmod_d)
+TRANS(xvmod_bu, gen_vvv, 32, gen_helper_vmod_bu)
+TRANS(xvmod_hu, gen_vvv, 32, gen_helper_vmod_hu)
+TRANS(xvmod_wu, gen_vvv, 32, gen_helper_vmod_wu)
+TRANS(xvmod_du, gen_vvv, 32, gen_helper_vmod_du)
+
 TRANS(xvreplgr2vr_b, gvec_dup, 32, MO_8)
 TRANS(xvreplgr2vr_h, gvec_dup, 32, MO_16)
 TRANS(xvreplgr2vr_w, gvec_dup, 32, MO_32)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index d6fb51ae64..fa25c876b4 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1545,6 +1545,23 @@ xvmaddwod_w_hu_h 0111 01001011 11101 ..... ..... .....   
 @vvv
 xvmaddwod_d_wu_w 0111 01001011 11110 ..... ..... .....    @vvv
 xvmaddwod_q_du_d 0111 01001011 11111 ..... ..... .....    @vvv
 
+xvdiv_b          0111 01001110 00000 ..... ..... .....    @vvv
+xvdiv_h          0111 01001110 00001 ..... ..... .....    @vvv
+xvdiv_w          0111 01001110 00010 ..... ..... .....    @vvv
+xvdiv_d          0111 01001110 00011 ..... ..... .....    @vvv
+xvmod_b          0111 01001110 00100 ..... ..... .....    @vvv
+xvmod_h          0111 01001110 00101 ..... ..... .....    @vvv
+xvmod_w          0111 01001110 00110 ..... ..... .....    @vvv
+xvmod_d          0111 01001110 00111 ..... ..... .....    @vvv
+xvdiv_bu         0111 01001110 01000 ..... ..... .....    @vvv
+xvdiv_hu         0111 01001110 01001 ..... ..... .....    @vvv
+xvdiv_wu         0111 01001110 01010 ..... ..... .....    @vvv
+xvdiv_du         0111 01001110 01011 ..... ..... .....    @vvv
+xvmod_bu         0111 01001110 01100 ..... ..... .....    @vvv
+xvmod_hu         0111 01001110 01101 ..... ..... .....    @vvv
+xvmod_wu         0111 01001110 01110 ..... ..... .....    @vvv
+xvmod_du         0111 01001110 01111 ..... ..... .....    @vvv
+
 xvreplgr2vr_b    0111 01101001 11110 00000 ..... .....    @vr
 xvreplgr2vr_h    0111 01101001 11110 00001 ..... .....    @vr
 xvreplgr2vr_w    0111 01101001 11110 00010 ..... .....    @vr
diff --git a/target/loongarch/vec.h b/target/loongarch/vec.h
index 06c8d7e314..ee50d53f4e 100644
--- a/target/loongarch/vec.h
+++ b/target/loongarch/vec.h
@@ -65,4 +65,11 @@
 #define DO_MADD(a, b, c)  (a + b * c)
 #define DO_MSUB(a, b, c)  (a - b * c)
 
+#define DO_DIVU(N, M) (unlikely(M == 0) ? 0 : N / M)
+#define DO_REMU(N, M) (unlikely(M == 0) ? 0 : N % M)
+#define DO_DIV(N, M)  (unlikely(M == 0) ? 0 :\
+        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M)
+#define DO_REM(N, M)  (unlikely(M == 0) ? 0 :\
+        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M)
+
 #endif /* LOONGARCH_VEC_H */
diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index 4cbbf8464f..998e561e0f 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -621,13 +621,6 @@ VMADDWOD_U_S(vmaddwod_h_bu_b, 16, H, UH, B, UB, DO_MUL)
 VMADDWOD_U_S(vmaddwod_w_hu_h, 32, W, UW, H, UH, DO_MUL)
 VMADDWOD_U_S(vmaddwod_d_wu_w, 64, D, UD, W, UW, DO_MUL)
 
-#define DO_DIVU(N, M) (unlikely(M == 0) ? 0 : N / M)
-#define DO_REMU(N, M) (unlikely(M == 0) ? 0 : N % M)
-#define DO_DIV(N, M)  (unlikely(M == 0) ? 0 :\
-        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M)
-#define DO_REM(N, M)  (unlikely(M == 0) ? 0 :\
-        unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M)
-
 #define VDIV(NAME, BIT, E, DO_OP)                              \
 void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc) \
 {                                                              \
@@ -635,8 +628,9 @@ void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t 
desc) \
     VReg *Vd = (VReg *)vd;                                     \
     VReg *Vj = (VReg *)vj;                                     \
     VReg *Vk = (VReg *)vk;                                     \
+    int oprsz = simd_oprsz(desc);                              \
                                                                \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                        \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {                  \
         Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i));                  \
     }                                                          \
 }
-- 
2.39.1