@@ -1856,6 +1856,39 @@ INSN_LASX(xvadda_h, xxx)
INSN_LASX(xvadda_w, xxx)
INSN_LASX(xvadda_d, xxx)
+INSN_LASX(xvmax_b, xxx)
+INSN_LASX(xvmax_h, xxx)
+INSN_LASX(xvmax_w, xxx)
+INSN_LASX(xvmax_d, xxx)
+INSN_LASX(xvmin_b, xxx)
+INSN_LASX(xvmin_h, xxx)
+INSN_LASX(xvmin_w, xxx)
+INSN_LASX(xvmin_d, xxx)
+INSN_LASX(xvmax_bu, xxx)
+INSN_LASX(xvmax_hu, xxx)
+INSN_LASX(xvmax_wu, xxx)
+INSN_LASX(xvmax_du, xxx)
+INSN_LASX(xvmin_bu, xxx)
+INSN_LASX(xvmin_hu, xxx)
+INSN_LASX(xvmin_wu, xxx)
+INSN_LASX(xvmin_du, xxx)
+INSN_LASX(xvmaxi_b, xx_i)
+INSN_LASX(xvmaxi_h, xx_i)
+INSN_LASX(xvmaxi_w, xx_i)
+INSN_LASX(xvmaxi_d, xx_i)
+INSN_LASX(xvmini_b, xx_i)
+INSN_LASX(xvmini_h, xx_i)
+INSN_LASX(xvmini_w, xx_i)
+INSN_LASX(xvmini_d, xx_i)
+INSN_LASX(xvmaxi_bu, xx_i)
+INSN_LASX(xvmaxi_hu, xx_i)
+INSN_LASX(xvmaxi_wu, xx_i)
+INSN_LASX(xvmaxi_du, xx_i)
+INSN_LASX(xvmini_bu, xx_i)
+INSN_LASX(xvmini_hu, xx_i)
+INSN_LASX(xvmini_wu, xx_i)
+INSN_LASX(xvmini_du, xx_i)
+
INSN_LASX(xvreplgr2vr_b, xr)
INSN_LASX(xvreplgr2vr_h, xr)
INSN_LASX(xvreplgr2vr_w, xr)
@@ -791,3 +791,21 @@ DEF_HELPER_FLAGS_4(xvadda_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvadda_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvadda_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvadda_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(xvmini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmini_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(xvmaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(xvmaxi_du, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
@@ -872,6 +872,186 @@ TRANS(xvadda_h, gvec_xxx, MO_16, do_xvadda)
TRANS(xvadda_w, gvec_xxx, MO_32, do_xvadda)
TRANS(xvadda_d, gvec_xxx, MO_64, do_xvadda)
+TRANS(xvmax_b, gvec_xxx, MO_8, tcg_gen_gvec_smax)
+TRANS(xvmax_h, gvec_xxx, MO_16, tcg_gen_gvec_smax)
+TRANS(xvmax_w, gvec_xxx, MO_32, tcg_gen_gvec_smax)
+TRANS(xvmax_d, gvec_xxx, MO_64, tcg_gen_gvec_smax)
+TRANS(xvmax_bu, gvec_xxx, MO_8, tcg_gen_gvec_umax)
+TRANS(xvmax_hu, gvec_xxx, MO_16, tcg_gen_gvec_umax)
+TRANS(xvmax_wu, gvec_xxx, MO_32, tcg_gen_gvec_umax)
+TRANS(xvmax_du, gvec_xxx, MO_64, tcg_gen_gvec_umax)
+
+TRANS(xvmin_b, gvec_xxx, MO_8, tcg_gen_gvec_smin)
+TRANS(xvmin_h, gvec_xxx, MO_16, tcg_gen_gvec_smin)
+TRANS(xvmin_w, gvec_xxx, MO_32, tcg_gen_gvec_smin)
+TRANS(xvmin_d, gvec_xxx, MO_64, tcg_gen_gvec_smin)
+TRANS(xvmin_bu, gvec_xxx, MO_8, tcg_gen_gvec_umin)
+TRANS(xvmin_hu, gvec_xxx, MO_16, tcg_gen_gvec_umin)
+TRANS(xvmin_wu, gvec_xxx, MO_32, tcg_gen_gvec_umin)
+TRANS(xvmin_du, gvec_xxx, MO_64, tcg_gen_gvec_umin)
+
+static void do_xvmini_s(unsigned vece, uint32_t xd_ofs, uint32_t xj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_smin_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vmini_s,
+ .fnoi = gen_helper_xvmini_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vmini_s,
+ .fnoi = gen_helper_xvmini_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vmini_s,
+ .fnoi = gen_helper_xvmini_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vmini_s,
+ .fnoi = gen_helper_xvmini_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(xd_ofs, xj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+static void do_xvmini_u(unsigned vece, uint32_t xd_ofs, uint32_t xj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_umin_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vmini_u,
+ .fnoi = gen_helper_xvmini_bu,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vmini_u,
+ .fnoi = gen_helper_xvmini_hu,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vmini_u,
+ .fnoi = gen_helper_xvmini_wu,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vmini_u,
+ .fnoi = gen_helper_xvmini_du,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(xd_ofs, xj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(xvmini_b, gvec_xx_i, MO_8, do_xvmini_s)
+TRANS(xvmini_h, gvec_xx_i, MO_16, do_xvmini_s)
+TRANS(xvmini_w, gvec_xx_i, MO_32, do_xvmini_s)
+TRANS(xvmini_d, gvec_xx_i, MO_64, do_xvmini_s)
+TRANS(xvmini_bu, gvec_xx_i, MO_8, do_xvmini_u)
+TRANS(xvmini_hu, gvec_xx_i, MO_16, do_xvmini_u)
+TRANS(xvmini_wu, gvec_xx_i, MO_32, do_xvmini_u)
+TRANS(xvmini_du, gvec_xx_i, MO_64, do_xvmini_u)
+
+static void do_xvmaxi_s(unsigned vece, uint32_t xd_ofs, uint32_t xj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_smax_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vmaxi_s,
+ .fnoi = gen_helper_xvmaxi_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vmaxi_s,
+ .fnoi = gen_helper_xvmaxi_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vmaxi_s,
+ .fnoi = gen_helper_xvmaxi_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vmaxi_s,
+ .fnoi = gen_helper_xvmaxi_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(xd_ofs, xj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+static void do_xvmaxi_u(unsigned vece, uint32_t xd_ofs, uint32_t xj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_umax_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vmaxi_u,
+ .fnoi = gen_helper_xvmaxi_bu,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vmaxi_u,
+ .fnoi = gen_helper_xvmaxi_hu,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vmaxi_u,
+ .fnoi = gen_helper_xvmaxi_wu,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vmaxi_u,
+ .fnoi = gen_helper_xvmaxi_du,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(xd_ofs, xj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(xvmaxi_b, gvec_xx_i, MO_8, do_xvmaxi_s)
+TRANS(xvmaxi_h, gvec_xx_i, MO_16, do_xvmaxi_s)
+TRANS(xvmaxi_w, gvec_xx_i, MO_32, do_xvmaxi_s)
+TRANS(xvmaxi_d, gvec_xx_i, MO_64, do_xvmaxi_s)
+TRANS(xvmaxi_bu, gvec_xx_i, MO_8, do_xvmaxi_u)
+TRANS(xvmaxi_hu, gvec_xx_i, MO_16, do_xvmaxi_u)
+TRANS(xvmaxi_wu, gvec_xx_i, MO_32, do_xvmaxi_u)
+TRANS(xvmaxi_du, gvec_xx_i, MO_64, do_xvmaxi_u)
+
static bool gvec_dupx(DisasContext *ctx, arg_xr *a, MemOp mop)
{
TCGv src = gpr_src(ctx, a->rj, EXT_NONE);
@@ -1313,6 +1313,7 @@ vstelm_b 0011 000110 .... ........ ..... ..... @vr_i8i4
@xx .... ........ ..... ..... xj:5 xd:5 &xx
@xxx .... ........ ..... xk:5 xj:5 xd:5 &xxx
@xr .... ........ ..... ..... rj:5 xd:5 &xr
+@xx_i5 .... ........ ..... imm:s5 xj:5 xd:5 &xx_i
@xx_ui5 .... ........ ..... imm:5 xj:5 xd:5 &xx_i
xvadd_b 0111 01000000 10100 ..... ..... ..... @xxx
@@ -1452,6 +1453,42 @@ xvadda_h 0111 01000101 11001 ..... ..... ..... @xxx
xvadda_w 0111 01000101 11010 ..... ..... ..... @xxx
xvadda_d 0111 01000101 11011 ..... ..... ..... @xxx
+xvmax_b 0111 01000111 00000 ..... ..... ..... @xxx
+xvmax_h 0111 01000111 00001 ..... ..... ..... @xxx
+xvmax_w 0111 01000111 00010 ..... ..... ..... @xxx
+xvmax_d 0111 01000111 00011 ..... ..... ..... @xxx
+xvmax_bu 0111 01000111 01000 ..... ..... ..... @xxx
+xvmax_hu 0111 01000111 01001 ..... ..... ..... @xxx
+xvmax_wu 0111 01000111 01010 ..... ..... ..... @xxx
+xvmax_du 0111 01000111 01011 ..... ..... ..... @xxx
+
+xvmaxi_b 0111 01101001 00000 ..... ..... ..... @xx_i5
+xvmaxi_h 0111 01101001 00001 ..... ..... ..... @xx_i5
+xvmaxi_w 0111 01101001 00010 ..... ..... ..... @xx_i5
+xvmaxi_d 0111 01101001 00011 ..... ..... ..... @xx_i5
+xvmaxi_bu 0111 01101001 01000 ..... ..... ..... @xx_ui5
+xvmaxi_hu 0111 01101001 01001 ..... ..... ..... @xx_ui5
+xvmaxi_wu 0111 01101001 01010 ..... ..... ..... @xx_ui5
+xvmaxi_du 0111 01101001 01011 ..... ..... ..... @xx_ui5
+
+xvmin_b 0111 01000111 00100 ..... ..... ..... @xxx
+xvmin_h 0111 01000111 00101 ..... ..... ..... @xxx
+xvmin_w 0111 01000111 00110 ..... ..... ..... @xxx
+xvmin_d 0111 01000111 00111 ..... ..... ..... @xxx
+xvmin_bu 0111 01000111 01100 ..... ..... ..... @xxx
+xvmin_hu 0111 01000111 01101 ..... ..... ..... @xxx
+xvmin_wu 0111 01000111 01110 ..... ..... ..... @xxx
+xvmin_du 0111 01000111 01111 ..... ..... ..... @xxx
+
+xvmini_b 0111 01101001 00100 ..... ..... ..... @xx_i5
+xvmini_h 0111 01101001 00101 ..... ..... ..... @xx_i5
+xvmini_w 0111 01101001 00110 ..... ..... ..... @xx_i5
+xvmini_d 0111 01101001 00111 ..... ..... ..... @xx_i5
+xvmini_bu 0111 01101001 01100 ..... ..... ..... @xx_ui5
+xvmini_hu 0111 01101001 01101 ..... ..... ..... @xx_ui5
+xvmini_wu 0111 01101001 01110 ..... ..... ..... @xx_ui5
+xvmini_du 0111 01101001 01111 ..... ..... ..... @xx_ui5
+
xvreplgr2vr_b 0111 01101001 11110 00000 ..... ..... @xr
xvreplgr2vr_h 0111 01101001 11110 00001 ..... ..... @xr
xvreplgr2vr_w 0111 01101001 11110 00010 ..... ..... @xr
@@ -363,3 +363,33 @@ XDO_VADDA(xvadda_b, 8, XB, DO_VABS)
XDO_VADDA(xvadda_h, 16, XH, DO_VABS)
XDO_VADDA(xvadda_w, 32, XW, DO_VABS)
XDO_VADDA(xvadda_d, 64, XD, DO_VABS)
+
+#define XVMINMAXI(NAME, BIT, E, DO_OP) \
+void HELPER(NAME)(void *xd, void *xj, uint64_t imm, uint32_t v) \
+{ \
+ int i; \
+ XReg *Xd = (XReg *)xd; \
+ XReg *Xj = (XReg *)xj; \
+ typedef __typeof(Xd->E(0)) TD; \
+ \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E(i) = DO_OP(Xj->E(i), (TD)imm); \
+ } \
+}
+
+XVMINMAXI(xvmini_b, 8, XB, DO_MIN)
+XVMINMAXI(xvmini_h, 16, XH, DO_MIN)
+XVMINMAXI(xvmini_w, 32, XW, DO_MIN)
+XVMINMAXI(xvmini_d, 64, XD, DO_MIN)
+XVMINMAXI(xvmaxi_b, 8, XB, DO_MAX)
+XVMINMAXI(xvmaxi_h, 16, XH, DO_MAX)
+XVMINMAXI(xvmaxi_w, 32, XW, DO_MAX)
+XVMINMAXI(xvmaxi_d, 64, XD, DO_MAX)
+XVMINMAXI(xvmini_bu, 8, UXB, DO_MIN)
+XVMINMAXI(xvmini_hu, 16, UXH, DO_MIN)
+XVMINMAXI(xvmini_wu, 32, UXW, DO_MIN)
+XVMINMAXI(xvmini_du, 64, UXD, DO_MIN)
+XVMINMAXI(xvmaxi_bu, 8, UXB, DO_MAX)
+XVMINMAXI(xvmaxi_hu, 16, UXH, DO_MAX)
+XVMINMAXI(xvmaxi_wu, 32, UXW, DO_MAX)
+XVMINMAXI(xvmaxi_du, 64, UXD, DO_MAX)
@@ -335,9 +335,6 @@ DO_VADDA(vadda_h, 16, H, DO_VABS)
DO_VADDA(vadda_w, 32, W, DO_VABS)
DO_VADDA(vadda_d, 64, D, DO_VABS)
-#define DO_MIN(a, b) (a < b ? a : b)
-#define DO_MAX(a, b) (a > b ? a : b)
-
#define VMINMAXI(NAME, BIT, E, DO_OP) \
void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
{ \
@@ -58,4 +58,7 @@
#define DO_VABS(a) ((a < 0) ? (-a) : (a))
+#define DO_MIN(a, b) (a < b ? a : b)
+#define DO_MAX(a, b) (a > b ? a : b)
+
#endif /* LOONGARCH_VEC_H */
This patch includes: - XVMAX[I].{B/H/W/D}[U]; - XVMIN[I].{B/H/W/D}[U]. Signed-off-by: Song Gao <gaosong@loongson.cn> --- target/loongarch/disas.c | 33 ++++ target/loongarch/helper.h | 18 ++ target/loongarch/insn_trans/trans_lasx.c.inc | 180 +++++++++++++++++++ target/loongarch/insns.decode | 37 ++++ target/loongarch/lasx_helper.c | 30 ++++ target/loongarch/lsx_helper.c | 3 - target/loongarch/vec.h | 3 + 7 files changed, 301 insertions(+), 3 deletions(-)