target/loongarch: Implement xvsrlr xvsrar

This patch includes:
- XVSRLR[I].{B/H/W/D};
- XVSRAR[I].{B/H/W/D}.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-38-gaosong@loongson.cn>

4 files changed, 59 insertions, 4 deletions

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index d93ecdb60d..bc5eb82b49 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -2086,6 +2086,24 @@ INSN_LASX(xvsllwil_wu_hu,    vv_i)
 INSN_LASX(xvsllwil_du_wu,    vv_i)
 INSN_LASX(xvextl_qu_du,      vv)
 
+INSN_LASX(xvsrlr_b,          vvv)
+INSN_LASX(xvsrlr_h,          vvv)
+INSN_LASX(xvsrlr_w,          vvv)
+INSN_LASX(xvsrlr_d,          vvv)
+INSN_LASX(xvsrlri_b,         vv_i)
+INSN_LASX(xvsrlri_h,         vv_i)
+INSN_LASX(xvsrlri_w,         vv_i)
+INSN_LASX(xvsrlri_d,         vv_i)
+
+INSN_LASX(xvsrar_b,          vvv)
+INSN_LASX(xvsrar_h,          vvv)
+INSN_LASX(xvsrar_w,          vvv)
+INSN_LASX(xvsrar_d,          vvv)
+INSN_LASX(xvsrari_b,         vv_i)
+INSN_LASX(xvsrari_h,         vv_i)
+INSN_LASX(xvsrari_w,         vv_i)
+INSN_LASX(xvsrari_d,         vv_i)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)
diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch/insn_trans/trans_vec.c.inc
index c35d0a51a7..8be8670259 100644
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -3739,6 +3739,14 @@ TRANS(vsrlri_b, LSX, gen_vv_i, gen_helper_vsrlri_b)
 TRANS(vsrlri_h, LSX, gen_vv_i, gen_helper_vsrlri_h)
 TRANS(vsrlri_w, LSX, gen_vv_i, gen_helper_vsrlri_w)
 TRANS(vsrlri_d, LSX, gen_vv_i, gen_helper_vsrlri_d)
+TRANS(xvsrlr_b, LASX, gen_xxx, gen_helper_vsrlr_b)
+TRANS(xvsrlr_h, LASX, gen_xxx, gen_helper_vsrlr_h)
+TRANS(xvsrlr_w, LASX, gen_xxx, gen_helper_vsrlr_w)
+TRANS(xvsrlr_d, LASX, gen_xxx, gen_helper_vsrlr_d)
+TRANS(xvsrlri_b, LASX, gen_xx_i, gen_helper_vsrlri_b)
+TRANS(xvsrlri_h, LASX, gen_xx_i, gen_helper_vsrlri_h)
+TRANS(xvsrlri_w, LASX, gen_xx_i, gen_helper_vsrlri_w)
+TRANS(xvsrlri_d, LASX, gen_xx_i, gen_helper_vsrlri_d)
 
 TRANS(vsrar_b, LSX, gen_vvv, gen_helper_vsrar_b)
 TRANS(vsrar_h, LSX, gen_vvv, gen_helper_vsrar_h)
@@ -3748,6 +3756,14 @@ TRANS(vsrari_b, LSX, gen_vv_i, gen_helper_vsrari_b)
 TRANS(vsrari_h, LSX, gen_vv_i, gen_helper_vsrari_h)
 TRANS(vsrari_w, LSX, gen_vv_i, gen_helper_vsrari_w)
 TRANS(vsrari_d, LSX, gen_vv_i, gen_helper_vsrari_d)
+TRANS(xvsrar_b, LASX, gen_xxx, gen_helper_vsrar_b)
+TRANS(xvsrar_h, LASX, gen_xxx, gen_helper_vsrar_h)
+TRANS(xvsrar_w, LASX, gen_xxx, gen_helper_vsrar_w)
+TRANS(xvsrar_d, LASX, gen_xxx, gen_helper_vsrar_d)
+TRANS(xvsrari_b, LASX, gen_xx_i, gen_helper_vsrari_b)
+TRANS(xvsrari_h, LASX, gen_xx_i, gen_helper_vsrari_h)
+TRANS(xvsrari_w, LASX, gen_xx_i, gen_helper_vsrari_w)
+TRANS(xvsrari_d, LASX, gen_xx_i, gen_helper_vsrari_d)
 
 TRANS(vsrln_b_h, LSX, gen_vvv, gen_helper_vsrln_b_h)
 TRANS(vsrln_h_w, LSX, gen_vvv, gen_helper_vsrln_h_w)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 8a7933eccc..ca0951e1cc 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1661,6 +1661,23 @@ xvsllwil_wu_hu   0111 01110000 11000 1 .... ..... .....   @vv_ui4
 xvsllwil_du_wu   0111 01110000 11001 ..... ..... .....    @vv_ui5
 xvextl_qu_du     0111 01110000 11010 00000 ..... .....    @vv
 
+xvsrlr_b         0111 01001111 00000 ..... ..... .....    @vvv
+xvsrlr_h         0111 01001111 00001 ..... ..... .....    @vvv
+xvsrlr_w         0111 01001111 00010 ..... ..... .....    @vvv
+xvsrlr_d         0111 01001111 00011 ..... ..... .....    @vvv
+xvsrlri_b        0111 01101010 01000 01 ... ..... .....   @vv_ui3
+xvsrlri_h        0111 01101010 01000 1 .... ..... .....   @vv_ui4
+xvsrlri_w        0111 01101010 01001 ..... ..... .....    @vv_ui5
+xvsrlri_d        0111 01101010 0101 ...... ..... .....    @vv_ui6
+xvsrar_b         0111 01001111 00100 ..... ..... .....    @vvv
+xvsrar_h         0111 01001111 00101 ..... ..... .....    @vvv
+xvsrar_w         0111 01001111 00110 ..... ..... .....    @vvv
+xvsrar_d         0111 01001111 00111 ..... ..... .....    @vvv
+xvsrari_b        0111 01101010 10000 01 ... ..... .....   @vv_ui3
+xvsrari_h        0111 01101010 10000 1 .... ..... .....   @vv_ui4
+xvsrari_w        0111 01101010 10001 ..... ..... .....    @vv_ui5
+xvsrari_d        0111 01101010 1001 ...... ..... .....    @vv_ui6
+
 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_helper.c b/target/loongarch/vec_helper.c
index a3376439e3..bb30d24b89 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -1025,8 +1025,9 @@ 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_vsrlr_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
     }                                                           \
 }
@@ -1042,8 +1043,9 @@ void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t desc) \
     int i;                                                         \
     VReg *Vd = (VReg *)vd;                                         \
     VReg *Vj = (VReg *)vj;                                         \
+    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_vsrlr_ ## E(Vj->E(i), imm);                  \
     }                                                              \
 }
@@ -1075,8 +1077,9 @@ 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_vsrar_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
     }                                                           \
 }
@@ -1092,8 +1095,9 @@ void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t desc) \
     int i;                                                         \
     VReg *Vd = (VReg *)vd;                                         \
     VReg *Vj = (VReg *)vj;                                         \
+    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_vsrar_ ## E(Vj->E(i), imm);                  \
     }                                                              \
 }