@@ -2085,6 +2085,24 @@ INSN_LASX(xvsllwil_wu_hu, xx_i)
INSN_LASX(xvsllwil_du_wu, xx_i)
INSN_LASX(xvextl_qu_du, xx)
+INSN_LASX(xvsrlr_b, xxx)
+INSN_LASX(xvsrlr_h, xxx)
+INSN_LASX(xvsrlr_w, xxx)
+INSN_LASX(xvsrlr_d, xxx)
+INSN_LASX(xvsrlri_b, xx_i)
+INSN_LASX(xvsrlri_h, xx_i)
+INSN_LASX(xvsrlri_w, xx_i)
+INSN_LASX(xvsrlri_d, xx_i)
+
+INSN_LASX(xvsrar_b, xxx)
+INSN_LASX(xvsrar_h, xxx)
+INSN_LASX(xvsrar_w, xxx)
+INSN_LASX(xvsrar_d, xxx)
+INSN_LASX(xvsrari_b, xx_i)
+INSN_LASX(xvsrari_h, xx_i)
+INSN_LASX(xvsrari_w, xx_i)
+INSN_LASX(xvsrari_d, xx_i)
+
INSN_LASX(xvreplgr2vr_b, xr)
INSN_LASX(xvreplgr2vr_h, xr)
INSN_LASX(xvreplgr2vr_w, xr)
@@ -940,3 +940,21 @@ DEF_HELPER_4(xvsllwil_hu_bu, void, env, i32, i32, i32)
DEF_HELPER_4(xvsllwil_wu_hu, void, env, i32, i32, i32)
DEF_HELPER_4(xvsllwil_du_wu, void, env, i32, i32, i32)
DEF_HELPER_3(xvextl_qu_du, void, env, i32, i32)
+
+DEF_HELPER_4(xvsrlr_b, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlr_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlr_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlr_d, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlri_b, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlri_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlri_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrlri_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(xvsrar_b, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrar_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrar_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrar_d, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrari_b, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrari_h, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrari_w, void, env, i32, i32, i32)
+DEF_HELPER_4(xvsrari_d, void, env, i32, i32, i32)
@@ -2034,6 +2034,24 @@ TRANS(xvsllwil_wu_hu, gen_xx_i, gen_helper_xvsllwil_wu_hu)
TRANS(xvsllwil_du_wu, gen_xx_i, gen_helper_xvsllwil_du_wu)
TRANS(xvextl_qu_du, gen_xx, gen_helper_xvextl_qu_du)
+TRANS(xvsrlr_b, gen_xxx, gen_helper_xvsrlr_b)
+TRANS(xvsrlr_h, gen_xxx, gen_helper_xvsrlr_h)
+TRANS(xvsrlr_w, gen_xxx, gen_helper_xvsrlr_w)
+TRANS(xvsrlr_d, gen_xxx, gen_helper_xvsrlr_d)
+TRANS(xvsrlri_b, gen_xx_i, gen_helper_xvsrlri_b)
+TRANS(xvsrlri_h, gen_xx_i, gen_helper_xvsrlri_h)
+TRANS(xvsrlri_w, gen_xx_i, gen_helper_xvsrlri_w)
+TRANS(xvsrlri_d, gen_xx_i, gen_helper_xvsrlri_d)
+
+TRANS(xvsrar_b, gen_xxx, gen_helper_xvsrar_b)
+TRANS(xvsrar_h, gen_xxx, gen_helper_xvsrar_h)
+TRANS(xvsrar_w, gen_xxx, gen_helper_xvsrar_w)
+TRANS(xvsrar_d, gen_xxx, gen_helper_xvsrar_d)
+TRANS(xvsrari_b, gen_xx_i, gen_helper_xvsrari_b)
+TRANS(xvsrari_h, gen_xx_i, gen_helper_xvsrari_h)
+TRANS(xvsrari_w, gen_xx_i, gen_helper_xvsrari_w)
+TRANS(xvsrari_d, gen_xx_i, gen_helper_xvsrari_d)
+
static bool gvec_dupx(DisasContext *ctx, arg_xr *a, MemOp mop)
{
TCGv src = gpr_src(ctx, a->rj, EXT_NONE);
@@ -1683,6 +1683,23 @@ xvsllwil_wu_hu 0111 01110000 11000 1 .... ..... ..... @xx_ui4
xvsllwil_du_wu 0111 01110000 11001 ..... ..... ..... @xx_ui5
xvextl_qu_du 0111 01110000 11010 00000 ..... ..... @xx
+xvsrlr_b 0111 01001111 00000 ..... ..... ..... @xxx
+xvsrlr_h 0111 01001111 00001 ..... ..... ..... @xxx
+xvsrlr_w 0111 01001111 00010 ..... ..... ..... @xxx
+xvsrlr_d 0111 01001111 00011 ..... ..... ..... @xxx
+xvsrlri_b 0111 01101010 01000 01 ... ..... ..... @xx_ui3
+xvsrlri_h 0111 01101010 01000 1 .... ..... ..... @xx_ui4
+xvsrlri_w 0111 01101010 01001 ..... ..... ..... @xx_ui5
+xvsrlri_d 0111 01101010 0101 ...... ..... ..... @xx_ui6
+xvsrar_b 0111 01001111 00100 ..... ..... ..... @xxx
+xvsrar_h 0111 01001111 00101 ..... ..... ..... @xxx
+xvsrar_w 0111 01001111 00110 ..... ..... ..... @xxx
+xvsrar_d 0111 01001111 00111 ..... ..... ..... @xxx
+xvsrari_b 0111 01101010 10000 01 ... ..... ..... @xx_ui3
+xvsrari_h 0111 01101010 10000 1 .... ..... ..... @xx_ui4
+xvsrari_w 0111 01101010 10001 ..... ..... ..... @xx_ui5
+xvsrari_d 0111 01101010 1001 ...... ..... ..... @xx_ui6
+
xvreplgr2vr_b 0111 01101001 11110 00000 ..... ..... @xr
xvreplgr2vr_h 0111 01101001 11110 00001 ..... ..... @xr
xvreplgr2vr_w 0111 01101001 11110 00010 ..... ..... @xr
@@ -860,3 +860,107 @@ XVSLLWIL(xvsllwil_d_w, 64, XD, XW)
XVSLLWIL(xvsllwil_hu_bu, 16, UXH, UXB)
XVSLLWIL(xvsllwil_wu_hu, 32, UXW, UXH)
XVSLLWIL(xvsllwil_du_wu, 64, UXD, UXW)
+
+#define do_xvsrlr(E, T) \
+static T do_xvsrlr_ ##E(T s1, int sh) \
+{ \
+ if (sh == 0) { \
+ return s1; \
+ } else { \
+ return (s1 >> sh) + ((s1 >> (sh - 1)) & 0x1); \
+ } \
+}
+
+do_xvsrlr(XB, uint8_t)
+do_xvsrlr(XH, uint16_t)
+do_xvsrlr(XW, uint32_t)
+do_xvsrlr(XD, uint64_t)
+
+#define XVSRLR(NAME, BIT, E1, E2) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t xk) \
+{ \
+ int i; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ XReg *Xk = &(env->fpr[xk].xreg); \
+ \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E1(i) = do_xvsrlr_ ## E1(Xj->E1(i), (Xk->E2(i)) % BIT); \
+ } \
+}
+
+XVSRLR(xvsrlr_b, 8, XB, UXB)
+XVSRLR(xvsrlr_h, 16, XH, UXH)
+XVSRLR(xvsrlr_w, 32, XW, UXW)
+XVSRLR(xvsrlr_d, 64, XD, UXD)
+
+#define XVSRLRI(NAME, BIT, E) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t imm) \
+{ \
+ int i; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E(i) = do_xvsrlr_ ## E(Xj->E(i), imm); \
+ } \
+}
+
+XVSRLRI(xvsrlri_b, 8, XB)
+XVSRLRI(xvsrlri_h, 16, XH)
+XVSRLRI(xvsrlri_w, 32, XW)
+XVSRLRI(xvsrlri_d, 64, XD)
+
+#define do_xvsrar(E, T) \
+static T do_xvsrar_ ##E(T s1, int sh) \
+{ \
+ if (sh == 0) { \
+ return s1; \
+ } else { \
+ return (s1 >> sh) + ((s1 >> (sh - 1)) & 0x1); \
+ } \
+}
+
+do_xvsrar(XB, int8_t)
+do_xvsrar(XH, int16_t)
+do_xvsrar(XW, int32_t)
+do_xvsrar(XD, int64_t)
+
+#define XVSRAR(NAME, BIT, E1, E2) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t xk) \
+{ \
+ int i; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ XReg *Xk = &(env->fpr[xk].xreg); \
+ \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E1(i) = do_xvsrar_ ## E1(Xj->E1(i), (Xk->E2(i)) % BIT); \
+ } \
+}
+
+XVSRAR(xvsrar_b, 8, XB, UXB)
+XVSRAR(xvsrar_h, 16, XH, UXH)
+XVSRAR(xvsrar_w, 32, XW, UXW)
+XVSRAR(xvsrar_d, 64, XD, UXD)
+
+#define XVSRARI(NAME, BIT, E) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t xd, uint32_t xj, uint32_t imm) \
+{ \
+ int i; \
+ XReg *Xd = &(env->fpr[xd].xreg); \
+ XReg *Xj = &(env->fpr[xj].xreg); \
+ \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E(i) = do_xvsrar_ ## E(Xj->E(i), imm); \
+ } \
+}
+
+XVSRARI(xvsrari_b, 8, XB)
+XVSRARI(xvsrari_h, 16, XH)
+XVSRARI(xvsrari_w, 32, XW)
+XVSRARI(xvsrari_d, 64, XD)
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 | 18 ++++ target/loongarch/insn_trans/trans_lasx.c.inc | 18 ++++ target/loongarch/insns.decode | 17 +++ target/loongarch/lasx_helper.c | 104 +++++++++++++++++++ 5 files changed, 175 insertions(+)