@@ -1851,6 +1851,11 @@ INSN_LASX(xvabsd_hu, xxx)
INSN_LASX(xvabsd_wu, xxx)
INSN_LASX(xvabsd_du, xxx)
+INSN_LASX(xvadda_b, xxx)
+INSN_LASX(xvadda_h, xxx)
+INSN_LASX(xvadda_w, xxx)
+INSN_LASX(xvadda_d, xxx)
+
INSN_LASX(xvreplgr2vr_b, xr)
INSN_LASX(xvreplgr2vr_h, xr)
INSN_LASX(xvreplgr2vr_w, xr)
@@ -786,3 +786,8 @@ DEF_HELPER_FLAGS_4(xvabsd_bu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvabsd_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvabsd_wu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(xvabsd_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+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)
@@ -831,6 +831,47 @@ TRANS(xvabsd_hu, gvec_xxx, MO_16, do_xvabsd_u)
TRANS(xvabsd_wu, gvec_xxx, MO_32, do_xvabsd_u)
TRANS(xvabsd_du, gvec_xxx, MO_64, do_xvabsd_u)
+static void do_xvadda(unsigned vece, uint32_t xd_ofs, uint32_t xj_ofs,
+ uint32_t xk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_abs_vec, INDEX_op_add_vec, 0
+ };
+ static const GVecGen3 op[4] = {
+ {
+ .fniv = gen_vadda,
+ .fno = gen_helper_xvadda_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vadda,
+ .fno = gen_helper_xvadda_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vadda,
+ .fno = gen_helper_xvadda_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vadda,
+ .fno = gen_helper_xvadda_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_3(xd_ofs, xj_ofs, xk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(xvadda_b, gvec_xxx, MO_8, do_xvadda)
+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)
+
static bool gvec_dupx(DisasContext *ctx, arg_xr *a, MemOp mop)
{
TCGv src = gpr_src(ctx, a->rj, EXT_NONE);
@@ -1447,6 +1447,11 @@ xvabsd_hu 0111 01000110 00101 ..... ..... ..... @xxx
xvabsd_wu 0111 01000110 00110 ..... ..... ..... @xxx
xvabsd_du 0111 01000110 00111 ..... ..... ..... @xxx
+xvadda_b 0111 01000101 11000 ..... ..... ..... @xxx
+xvadda_h 0111 01000101 11001 ..... ..... ..... @xxx
+xvadda_w 0111 01000101 11010 ..... ..... ..... @xxx
+xvadda_d 0111 01000101 11011 ..... ..... ..... @xxx
+
xvreplgr2vr_b 0111 01101001 11110 00000 ..... ..... @xr
xvreplgr2vr_h 0111 01101001 11110 00001 ..... ..... @xr
xvreplgr2vr_w 0111 01101001 11110 00010 ..... ..... @xr
@@ -346,3 +346,20 @@ XDO_3OP(xvabsd_bu, 8, UXB, DO_VABSD)
XDO_3OP(xvabsd_hu, 16, UXH, DO_VABSD)
XDO_3OP(xvabsd_wu, 32, UXW, DO_VABSD)
XDO_3OP(xvabsd_du, 64, UXD, DO_VABSD)
+
+#define XDO_VADDA(NAME, BIT, E, DO_OP) \
+void HELPER(NAME)(void *xd, void *xj, void *xk, uint32_t v) \
+{ \
+ int i; \
+ XReg *Xd = (XReg *)xd; \
+ XReg *Xj = (XReg *)xj; \
+ XReg *Xk = (XReg *)xk; \
+ for (i = 0; i < LASX_LEN / BIT; i++) { \
+ Xd->E(i) = DO_OP(Xj->E(i)) + DO_OP(Xk->E(i)); \
+ } \
+}
+
+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)
@@ -318,8 +318,6 @@ DO_3OP(vabsd_hu, 16, UH, DO_VABSD)
DO_3OP(vabsd_wu, 32, UW, DO_VABSD)
DO_3OP(vabsd_du, 64, UD, DO_VABSD)
-#define DO_VABS(a) ((a < 0) ? (-a) : (a))
-
#define DO_VADDA(NAME, BIT, E, DO_OP) \
void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
{ \
@@ -56,4 +56,6 @@
#define DO_VABSD(a, b) ((a > b) ? (a - b) : (b - a))
+#define DO_VABS(a) ((a < 0) ? (-a) : (a))
+
#endif /* LOONGARCH_VEC_H */
This patch includes: - XVADDA.{B/H/W/D}. Signed-off-by: Song Gao <gaosong@loongson.cn> --- target/loongarch/disas.c | 5 +++ target/loongarch/helper.h | 5 +++ target/loongarch/insn_trans/trans_lasx.c.inc | 41 ++++++++++++++++++++ target/loongarch/insns.decode | 5 +++ target/loongarch/lasx_helper.c | 17 ++++++++ target/loongarch/lsx_helper.c | 2 - target/loongarch/vec.h | 2 + 7 files changed, 75 insertions(+), 2 deletions(-)