@@ -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)
@@ -375,23 +375,23 @@ DEF_HELPER_5(vsllwil_wu_hu, void, env, i32, i32, i32, i32)
DEF_HELPER_5(vsllwil_du_wu, void, env, i32, i32, i32, i32)
DEF_HELPER_4(vextl_qu_du, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlr_b, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlr_h, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlr_w, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlr_d, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlri_b, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlri_h, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlri_w, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrlri_d, void, env, i32, i32, i32)
-
-DEF_HELPER_4(vsrar_b, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrar_h, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrar_w, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrar_d, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrari_b, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrari_h, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrari_w, void, env, i32, i32, i32)
-DEF_HELPER_4(vsrari_d, void, env, i32, i32, i32)
+DEF_HELPER_5(vsrlr_b, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlr_h, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlr_w, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlr_d, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlri_b, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlri_h, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlri_w, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(vsrlri_d, void, env, i32, i32, i32, i32)
+
+DEF_HELPER_5(vsrar_b, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrar_h, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrar_w, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrar_d, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrari_b, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrari_h, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrari_w, void, env, int, i32, i32, i32)
+DEF_HELPER_5(vsrari_d, void, env, int, i32, i32, i32)
DEF_HELPER_4(vsrln_b_h, void, env, i32, i32, i32)
DEF_HELPER_4(vsrln_h_w, void, env, i32, i32, i32)
@@ -462,6 +462,24 @@ TRANS(xvsllwil_wu_hu, gen_vv_i, 32, gen_helper_vsllwil_wu_hu)
TRANS(xvsllwil_du_wu, gen_vv_i, 32, gen_helper_vsllwil_du_wu)
TRANS(xvextl_qu_du, gen_vv, 32, gen_helper_vextl_qu_du)
+TRANS(xvsrlr_b, gen_vvv, 32, gen_helper_vsrlr_b)
+TRANS(xvsrlr_h, gen_vvv, 32, gen_helper_vsrlr_h)
+TRANS(xvsrlr_w, gen_vvv, 32, gen_helper_vsrlr_w)
+TRANS(xvsrlr_d, gen_vvv, 32, gen_helper_vsrlr_d)
+TRANS(xvsrlri_b, gen_vv_i, 32, gen_helper_vsrlri_b)
+TRANS(xvsrlri_h, gen_vv_i, 32, gen_helper_vsrlri_h)
+TRANS(xvsrlri_w, gen_vv_i, 32, gen_helper_vsrlri_w)
+TRANS(xvsrlri_d, gen_vv_i, 32, gen_helper_vsrlri_d)
+
+TRANS(xvsrar_b, gen_vvv, 32, gen_helper_vsrar_b)
+TRANS(xvsrar_h, gen_vvv, 32, gen_helper_vsrar_h)
+TRANS(xvsrar_w, gen_vvv, 32, gen_helper_vsrar_w)
+TRANS(xvsrar_d, gen_vvv, 32, gen_helper_vsrar_d)
+TRANS(xvsrari_b, gen_vv_i, 32, gen_helper_vsrari_b)
+TRANS(xvsrari_h, gen_vv_i, 32, gen_helper_vsrari_h)
+TRANS(xvsrari_w, gen_vv_i, 32, gen_helper_vsrari_w)
+TRANS(xvsrari_d, gen_vv_i, 32, gen_helper_vsrari_d)
+
TRANS(xvreplgr2vr_b, gvec_dup, 32, MO_8)
TRANS(xvreplgr2vr_h, gvec_dup, 32, MO_16)
TRANS(xvreplgr2vr_w, gvec_dup, 32, MO_32)
@@ -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
@@ -1012,15 +1012,16 @@ do_vsrlr(W, uint32_t)
do_vsrlr(D, uint64_t)
#define VSRLR(NAME, BIT, T, E) \
-void HELPER(NAME)(CPULoongArchState *env, \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t oprsz, \
uint32_t vd, uint32_t vj, uint32_t vk) \
{ \
- int i; \
+ int i, len; \
VReg *Vd = &(env->fpr[vd].vreg); \
VReg *Vj = &(env->fpr[vj].vreg); \
VReg *Vk = &(env->fpr[vk].vreg); \
\
- for (i = 0; i < LSX_LEN/BIT; i++) { \
+ len = (oprsz == 16) ? LSX_LEN : LASX_LEN; \
+ for (i = 0; i < len / BIT; i++) { \
Vd->E(i) = do_vsrlr_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
} \
}
@@ -1031,14 +1032,15 @@ VSRLR(vsrlr_w, 32, uint32_t, W)
VSRLR(vsrlr_d, 64, uint64_t, D)
#define VSRLRI(NAME, BIT, E) \
-void HELPER(NAME)(CPULoongArchState *env, \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t oprsz, \
uint32_t vd, uint32_t vj, uint32_t imm) \
{ \
- int i; \
+ int i, len; \
VReg *Vd = &(env->fpr[vd].vreg); \
VReg *Vj = &(env->fpr[vj].vreg); \
\
- for (i = 0; i < LSX_LEN/BIT; i++) { \
+ len = (oprsz == 16) ? LSX_LEN : LASX_LEN; \
+ for (i = 0; i < len / BIT; i++) { \
Vd->E(i) = do_vsrlr_ ## E(Vj->E(i), imm); \
} \
}
@@ -1064,15 +1066,16 @@ do_vsrar(W, int32_t)
do_vsrar(D, int64_t)
#define VSRAR(NAME, BIT, T, E) \
-void HELPER(NAME)(CPULoongArchState *env, \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t oprsz, \
uint32_t vd, uint32_t vj, uint32_t vk) \
{ \
- int i; \
+ int i, len; \
VReg *Vd = &(env->fpr[vd].vreg); \
VReg *Vj = &(env->fpr[vj].vreg); \
VReg *Vk = &(env->fpr[vk].vreg); \
\
- for (i = 0; i < LSX_LEN/BIT; i++) { \
+ len = (oprsz == 16) ? LSX_LEN : LASX_LEN; \
+ for (i = 0; i < len / BIT; i++) { \
Vd->E(i) = do_vsrar_ ## E(Vj->E(i), ((T)Vk->E(i))%BIT); \
} \
}
@@ -1083,14 +1086,15 @@ VSRAR(vsrar_w, 32, uint32_t, W)
VSRAR(vsrar_d, 64, uint64_t, D)
#define VSRARI(NAME, BIT, E) \
-void HELPER(NAME)(CPULoongArchState *env, \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t oprsz, \
uint32_t vd, uint32_t vj, uint32_t imm) \
{ \
- int i; \
+ int i, len; \
VReg *Vd = &(env->fpr[vd].vreg); \
VReg *Vj = &(env->fpr[vj].vreg); \
\
- for (i = 0; i < LSX_LEN/BIT; i++) { \
+ len = (oprsz == 16) ? LSX_LEN : LASX_LEN; \
+ for (i = 0; i < len / BIT; i++) { \
Vd->E(i) = do_vsrar_ ## E(Vj->E(i), imm); \
} \
}
This patch includes: - XVSRLR[I].{B/H/W/D}; - XVSRAR[I].{B/H/W/D}. Signed-off-by: Song Gao <gaosong@loongson.cn> --- target/loongarch/disas.c | 18 +++++++++++ target/loongarch/helper.h | 34 ++++++++++---------- target/loongarch/insn_trans/trans_lasx.c.inc | 18 +++++++++++ target/loongarch/insns.decode | 17 ++++++++++ target/loongarch/vec_helper.c | 28 +++++++++------- 5 files changed, 86 insertions(+), 29 deletions(-)