@@ -203,18 +203,18 @@ DEF_HELPER_FLAGS_3(vsro, TCG_CALL_NO_RWG, void, avr, avr, avr)
DEF_HELPER_FLAGS_3(vsrv, TCG_CALL_NO_RWG, void, avr, avr, avr)
DEF_HELPER_FLAGS_3(vslv, TCG_CALL_NO_RWG, void, avr, avr, avr)
DEF_HELPER_FLAGS_3(VPRTYBQ, TCG_CALL_NO_RWG, void, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vaddsbs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vaddshs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vaddsws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsubsbs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsubshs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsubsws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vaddubs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vadduhs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vadduws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsububs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsubuhs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
-DEF_HELPER_FLAGS_5(vsubuws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDSBS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDSHS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDSWS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBSBS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBSHS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBSWS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDUBS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDUHS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VADDUWS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBUBS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBUHS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
+DEF_HELPER_FLAGS_5(VSUBUWS, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
DEF_HELPER_FLAGS_3(VADDUQM, TCG_CALL_NO_RWG, void, avr, avr, avr)
DEF_HELPER_FLAGS_4(VADDECUQ, TCG_CALL_NO_RWG, void, avr, avr, avr, avr)
DEF_HELPER_FLAGS_4(VADDEUQM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr)
@@ -832,6 +832,14 @@ VADDCUW 000100 ..... ..... ..... 00110000000 @VX
VADDCUQ 000100 ..... ..... ..... 00101000000 @VX
VADDUQM 000100 ..... ..... ..... 00100000000 @VX
+VADDSBS 000100 ..... ..... ..... 01100000000 @VX
+VADDSHS 000100 ..... ..... ..... 01101000000 @VX
+VADDSWS 000100 ..... ..... ..... 01110000000 @VX
+
+VADDUBS 000100 ..... ..... ..... 01000000000 @VX
+VADDUHS 000100 ..... ..... ..... 01001000000 @VX
+VADDUWS 000100 ..... ..... ..... 01010000000 @VX
+
VADDEUQM 000100 ..... ..... ..... ..... 111100 @VA
VADDECUQ 000100 ..... ..... ..... ..... 111101 @VA
@@ -839,6 +847,14 @@ VSUBCUW 000100 ..... ..... ..... 10110000000 @VX
VSUBCUQ 000100 ..... ..... ..... 10101000000 @VX
VSUBUQM 000100 ..... ..... ..... 10100000000 @VX
+VSUBSBS 000100 ..... ..... ..... 11100000000 @VX
+VSUBSHS 000100 ..... ..... ..... 11101000000 @VX
+VSUBSWS 000100 ..... ..... ..... 11110000000 @VX
+
+VSUBUBS 000100 ..... ..... ..... 11000000000 @VX
+VSUBUHS 000100 ..... ..... ..... 11001000000 @VX
+VSUBUWS 000100 ..... ..... ..... 11010000000 @VX
+
VSUBECUQ 000100 ..... ..... ..... ..... 111111 @VA
VSUBEUQM 000100 ..... ..... ..... ..... 111110 @VA
@@ -541,7 +541,7 @@ VARITHFPFMA(nmsubfp, float_muladd_negate_result | float_muladd_negate_c);
}
#define VARITHSAT_DO(name, op, optype, cvt, element) \
- void helper_v##name(ppc_avr_t *r, ppc_avr_t *vscr_sat, \
+ void helper_V##name(ppc_avr_t *r, ppc_avr_t *vscr_sat, \
ppc_avr_t *a, ppc_avr_t *b, uint32_t desc) \
{ \
int sat = 0; \
@@ -555,17 +555,17 @@ VARITHFPFMA(nmsubfp, float_muladd_negate_result | float_muladd_negate_c);
} \
}
#define VARITHSAT_SIGNED(suffix, element, optype, cvt) \
- VARITHSAT_DO(adds##suffix##s, +, optype, cvt, element) \
- VARITHSAT_DO(subs##suffix##s, -, optype, cvt, element)
+ VARITHSAT_DO(ADDS##suffix##S, +, optype, cvt, element) \
+ VARITHSAT_DO(SUBS##suffix##S, -, optype, cvt, element)
#define VARITHSAT_UNSIGNED(suffix, element, optype, cvt) \
- VARITHSAT_DO(addu##suffix##s, +, optype, cvt, element) \
- VARITHSAT_DO(subu##suffix##s, -, optype, cvt, element)
-VARITHSAT_SIGNED(b, s8, int16_t, cvtshsb)
-VARITHSAT_SIGNED(h, s16, int32_t, cvtswsh)
-VARITHSAT_SIGNED(w, s32, int64_t, cvtsdsw)
-VARITHSAT_UNSIGNED(b, u8, uint16_t, cvtshub)
-VARITHSAT_UNSIGNED(h, u16, uint32_t, cvtswuh)
-VARITHSAT_UNSIGNED(w, u32, uint64_t, cvtsduw)
+ VARITHSAT_DO(ADDU##suffix##S, +, optype, cvt, element) \
+ VARITHSAT_DO(SUBU##suffix##S, -, optype, cvt, element)
+VARITHSAT_SIGNED(B, s8, int16_t, cvtshsb)
+VARITHSAT_SIGNED(H, s16, int32_t, cvtswsh)
+VARITHSAT_SIGNED(W, s32, int64_t, cvtsdsw)
+VARITHSAT_UNSIGNED(B, u8, uint16_t, cvtshub)
+VARITHSAT_UNSIGNED(H, u16, uint32_t, cvtswuh)
+VARITHSAT_UNSIGNED(W, u32, uint64_t, cvtsduw)
#undef VARITHSAT_CASE
#undef VARITHSAT_DO
#undef VARITHSAT_SIGNED
@@ -1047,58 +1047,6 @@ TRANS(VRLQ, do_vector_rotl_quad, false, false)
TRANS(VRLQNM, do_vector_rotl_quad, true, false)
TRANS(VRLQMI, do_vector_rotl_quad, false, true)
-#define GEN_VXFORM_SAT(NAME, VECE, NORM, SAT, OPC2, OPC3) \
-static void glue(glue(gen_, NAME), _vec)(unsigned vece, TCGv_vec t, \
- TCGv_vec sat, TCGv_vec a, \
- TCGv_vec b) \
-{ \
- TCGv_vec x = tcg_temp_new_vec_matching(t); \
- glue(glue(tcg_gen_, NORM), _vec)(VECE, x, a, b); \
- glue(glue(tcg_gen_, SAT), _vec)(VECE, t, a, b); \
- tcg_gen_cmp_vec(TCG_COND_NE, VECE, x, x, t); \
- tcg_gen_or_vec(VECE, sat, sat, x); \
-} \
-static void glue(gen_, NAME)(DisasContext *ctx) \
-{ \
- static const TCGOpcode vecop_list[] = { \
- glue(glue(INDEX_op_, NORM), _vec), \
- glue(glue(INDEX_op_, SAT), _vec), \
- INDEX_op_cmp_vec, 0 \
- }; \
- static const GVecGen4 g = { \
- .fniv = glue(glue(gen_, NAME), _vec), \
- .fno = glue(gen_helper_, NAME), \
- .opt_opc = vecop_list, \
- .write_aofs = true, \
- .vece = VECE, \
- }; \
- if (unlikely(!ctx->altivec_enabled)) { \
- gen_exception(ctx, POWERPC_EXCP_VPU); \
- return; \
- } \
- tcg_gen_gvec_4(avr_full_offset(rD(ctx->opcode)), \
- offsetof(CPUPPCState, vscr_sat), \
- avr_full_offset(rA(ctx->opcode)), \
- avr_full_offset(rB(ctx->opcode)), \
- 16, 16, &g); \
-}
-
-GEN_VXFORM_SAT(vaddubs, MO_8, add, usadd, 0, 8);
-GEN_VXFORM_DUAL_EXT(vaddubs, PPC_ALTIVEC, PPC_NONE, 0, \
- vmul10uq, PPC_NONE, PPC2_ISA300, 0x0000F800)
-GEN_VXFORM_SAT(vadduhs, MO_16, add, usadd, 0, 9);
-GEN_VXFORM_DUAL(vadduhs, PPC_ALTIVEC, PPC_NONE, \
- vmul10euq, PPC_NONE, PPC2_ISA300)
-GEN_VXFORM_SAT(vadduws, MO_32, add, usadd, 0, 10);
-GEN_VXFORM_SAT(vaddsbs, MO_8, add, ssadd, 0, 12);
-GEN_VXFORM_SAT(vaddshs, MO_16, add, ssadd, 0, 13);
-GEN_VXFORM_SAT(vaddsws, MO_32, add, ssadd, 0, 14);
-GEN_VXFORM_SAT(vsububs, MO_8, sub, ussub, 0, 24);
-GEN_VXFORM_SAT(vsubuhs, MO_16, sub, ussub, 0, 25);
-GEN_VXFORM_SAT(vsubuws, MO_32, sub, ussub, 0, 26);
-GEN_VXFORM_SAT(vsubsbs, MO_8, sub, sssub, 0, 28);
-GEN_VXFORM_SAT(vsubshs, MO_16, sub, sssub, 0, 29);
-GEN_VXFORM_SAT(vsubsws, MO_32, sub, sssub, 0, 30);
GEN_VXFORM_TRANS(vsl, 2, 7);
GEN_VXFORM_TRANS(vsr, 2, 11);
GEN_VXFORM_ENV(vpkuhum, 7, 0);
@@ -2641,26 +2589,14 @@ static void gen_xpnd04_2(DisasContext *ctx)
}
}
-
-GEN_VXFORM_DUAL(vsubsws, PPC_ALTIVEC, PPC_NONE, \
- xpnd04_2, PPC_NONE, PPC2_ISA300)
-
GEN_VXFORM_DUAL(vsububm, PPC_ALTIVEC, PPC_NONE, \
bcdadd, PPC_NONE, PPC2_ALTIVEC_207)
-GEN_VXFORM_DUAL(vsububs, PPC_ALTIVEC, PPC_NONE, \
- bcdadd, PPC_NONE, PPC2_ALTIVEC_207)
GEN_VXFORM_DUAL(vsubuhm, PPC_ALTIVEC, PPC_NONE, \
bcdsub, PPC_NONE, PPC2_ALTIVEC_207)
-GEN_VXFORM_DUAL(vsubuhs, PPC_ALTIVEC, PPC_NONE, \
- bcdsub, PPC_NONE, PPC2_ALTIVEC_207)
-GEN_VXFORM_DUAL(vaddshs, PPC_ALTIVEC, PPC_NONE, \
- bcdcpsgn, PPC_NONE, PPC2_ISA300)
GEN_VXFORM_DUAL(vsubudm, PPC2_ALTIVEC_207, PPC_NONE, \
bcds, PPC_NONE, PPC2_ISA300)
GEN_VXFORM_DUAL(vsubuwm, PPC_ALTIVEC, PPC_NONE, \
bcdus, PPC_NONE, PPC2_ISA300)
-GEN_VXFORM_DUAL(vsubsbs, PPC_ALTIVEC, PPC_NONE, \
- bcdtrunc, PPC_NONE, PPC2_ISA300)
static void gen_vsbox(DisasContext *ctx)
{
@@ -2937,6 +2873,180 @@ static bool do_vx_vaddsubcuw(DisasContext *ctx, arg_VX *a, int add)
TRANS(VSUBCUW, do_vx_vaddsubcuw, 0)
TRANS(VADDCUW, do_vx_vaddsubcuw, 1)
+/* Integer Add/Sub Saturate Instructions */
+static inline void do_vadd_vsub_sat
+(
+ unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b,
+ void (*norm_op)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec),
+ void (*sat_op)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
+{
+ TCGv_vec x = tcg_temp_new_vec_matching(t);
+ norm_op(vece, x, a, b);
+ sat_op(vece, t, a, b);
+ tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t);
+ tcg_gen_or_vec(vece, sat, sat, x);
+}
+
+static void gen_vadd_sat_u(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ do_vadd_vsub_sat(vece, t, sat, a, b, tcg_gen_add_vec, tcg_gen_usadd_vec);
+}
+
+static void gen_vadd_sat_s(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ do_vadd_vsub_sat(vece, t, sat, a, b, tcg_gen_add_vec, tcg_gen_ssadd_vec);
+}
+
+static void gen_vsub_sat_u(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ do_vadd_vsub_sat(vece, t, sat, a, b, tcg_gen_sub_vec, tcg_gen_ussub_vec);
+}
+
+static void gen_vsub_sat_s(unsigned vece, TCGv_vec t, TCGv_vec sat,
+ TCGv_vec a, TCGv_vec b)
+{
+ do_vadd_vsub_sat(vece, t, sat, a, b, tcg_gen_sub_vec, tcg_gen_sssub_vec);
+}
+
+/*
+ * Signed/Unsigned add/sub helper ops for byte/halfword/word
+ * GVecGen4 struct variants.
+ */
+static const TCGOpcode vecop_list_sub_u[] = {
+ INDEX_op_sub_vec, INDEX_op_ussub_vec, INDEX_op_cmp_vec, 0
+};
+static const TCGOpcode vecop_list_sub_s[] = {
+ INDEX_op_sub_vec, INDEX_op_sssub_vec, INDEX_op_cmp_vec, 0
+};
+static const TCGOpcode vecop_list_add_u[] = {
+ INDEX_op_add_vec, INDEX_op_usadd_vec, INDEX_op_cmp_vec, 0
+};
+static const TCGOpcode vecop_list_add_s[] = {
+ INDEX_op_add_vec, INDEX_op_ssadd_vec, INDEX_op_cmp_vec, 0
+};
+
+static const GVecGen4 op_vsububs = {
+ .fniv = gen_vsub_sat_u,
+ .fno = gen_helper_VSUBUBS,
+ .opt_opc = vecop_list_sub_u,
+ .write_aofs = true,
+ .vece = MO_8
+};
+
+static const GVecGen4 op_vaddubs = {
+ .fniv = gen_vadd_sat_u,
+ .fno = gen_helper_VADDUBS,
+ .opt_opc = vecop_list_add_u,
+ .write_aofs = true,
+ .vece = MO_8
+};
+
+static const GVecGen4 op_vsubuhs = {
+ .fniv = gen_vsub_sat_u,
+ .fno = gen_helper_VSUBUHS,
+ .opt_opc = vecop_list_sub_u,
+ .write_aofs = true,
+ .vece = MO_16
+};
+
+static const GVecGen4 op_vadduhs = {
+ .fniv = gen_vadd_sat_u,
+ .fno = gen_helper_VADDUHS,
+ .opt_opc = vecop_list_add_u,
+ .write_aofs = true,
+ .vece = MO_16
+};
+
+static const GVecGen4 op_vsubuws = {
+ .fniv = gen_vsub_sat_u,
+ .fno = gen_helper_VSUBUWS,
+ .opt_opc = vecop_list_sub_u,
+ .write_aofs = true,
+ .vece = MO_32
+};
+
+static const GVecGen4 op_vadduws = {
+ .fniv = gen_vadd_sat_u,
+ .fno = gen_helper_VADDUWS,
+ .opt_opc = vecop_list_add_u,
+ .write_aofs = true,
+ .vece = MO_32
+};
+
+static const GVecGen4 op_vsubsbs = {
+ .fniv = gen_vsub_sat_s,
+ .fno = gen_helper_VSUBSBS,
+ .opt_opc = vecop_list_sub_s,
+ .write_aofs = true,
+ .vece = MO_8
+};
+
+static const GVecGen4 op_vaddsbs = {
+ .fniv = gen_vadd_sat_s,
+ .fno = gen_helper_VADDSBS,
+ .opt_opc = vecop_list_add_s,
+ .write_aofs = true,
+ .vece = MO_8
+};
+
+static const GVecGen4 op_vsubshs = {
+ .fniv = gen_vsub_sat_s,
+ .fno = gen_helper_VSUBSHS,
+ .opt_opc = vecop_list_sub_s,
+ .write_aofs = true,
+ .vece = MO_16
+};
+
+static const GVecGen4 op_vaddshs = {
+ .fniv = gen_vadd_sat_s,
+ .fno = gen_helper_VADDSHS,
+ .opt_opc = vecop_list_add_s,
+ .write_aofs = true,
+ .vece = MO_16
+};
+
+static const GVecGen4 op_vsubsws = {
+ .fniv = gen_vsub_sat_s,
+ .fno = gen_helper_VSUBSWS,
+ .opt_opc = vecop_list_sub_s,
+ .write_aofs = true,
+ .vece = MO_32
+};
+
+static const GVecGen4 op_vaddsws = {
+ .fniv = gen_vadd_sat_s,
+ .fno = gen_helper_VADDSWS,
+ .opt_opc = vecop_list_add_s,
+ .write_aofs = true,
+ .vece = MO_32
+};
+
+static bool do_vx_vadd_vsub_sat(DisasContext *ctx, arg_VX *a, const GVecGen4 *op)
+{
+ REQUIRE_VECTOR(ctx);
+ tcg_gen_gvec_4(avr_full_offset(a->vrt), offsetof(CPUPPCState, vscr_sat),
+ avr_full_offset(a->vra), avr_full_offset(a->vrb),
+ 16, 16, op);
+
+ return true;
+}
+
+TRANS_FLAGS(ALTIVEC, VSUBUBS, do_vx_vadd_vsub_sat, &op_vsububs)
+TRANS_FLAGS(ALTIVEC, VSUBUHS, do_vx_vadd_vsub_sat, &op_vsubuhs)
+TRANS_FLAGS(ALTIVEC, VSUBUWS, do_vx_vadd_vsub_sat, &op_vsubuws)
+TRANS_FLAGS(ALTIVEC, VSUBSBS, do_vx_vadd_vsub_sat, &op_vsubsbs)
+TRANS_FLAGS(ALTIVEC, VSUBSHS, do_vx_vadd_vsub_sat, &op_vsubshs)
+TRANS_FLAGS(ALTIVEC, VSUBSWS, do_vx_vadd_vsub_sat, &op_vsubsws)
+TRANS_FLAGS(ALTIVEC, VADDUBS, do_vx_vadd_vsub_sat, &op_vaddubs)
+TRANS_FLAGS(ALTIVEC, VADDUHS, do_vx_vadd_vsub_sat, &op_vadduhs)
+TRANS_FLAGS(ALTIVEC, VADDUWS, do_vx_vadd_vsub_sat, &op_vadduws)
+TRANS_FLAGS(ALTIVEC, VADDSBS, do_vx_vadd_vsub_sat, &op_vaddsbs)
+TRANS_FLAGS(ALTIVEC, VADDSHS, do_vx_vadd_vsub_sat, &op_vaddshs)
+TRANS_FLAGS(ALTIVEC, VADDSWS, do_vx_vadd_vsub_sat, &op_vaddsws)
+
static bool do_vx_vmuleo(DisasContext *ctx, arg_VX *a, bool even,
void (*gen_mul)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64))
{
@@ -54,18 +54,13 @@ GEN_VXFORM(vsro, 6, 17),
GEN_VXFORM(xpnd04_1, 0, 22),
GEN_VXFORM_300(bcdsr, 0, 23),
GEN_VXFORM_300(bcdsr, 0, 31),
-GEN_VXFORM_DUAL(vaddubs, vmul10uq, 0, 8, PPC_ALTIVEC, PPC_NONE),
-GEN_VXFORM_DUAL(vadduhs, vmul10euq, 0, 9, PPC_ALTIVEC, PPC_NONE),
-GEN_VXFORM(vadduws, 0, 10),
-GEN_VXFORM(vaddsbs, 0, 12),
-GEN_VXFORM_DUAL(vaddshs, bcdcpsgn, 0, 13, PPC_ALTIVEC, PPC_NONE),
-GEN_VXFORM(vaddsws, 0, 14),
-GEN_VXFORM_DUAL(vsububs, bcdadd, 0, 24, PPC_ALTIVEC, PPC_NONE),
-GEN_VXFORM_DUAL(vsubuhs, bcdsub, 0, 25, PPC_ALTIVEC, PPC_NONE),
-GEN_VXFORM(vsubuws, 0, 26),
-GEN_VXFORM_DUAL(vsubsbs, bcdtrunc, 0, 28, PPC_ALTIVEC, PPC2_ISA300),
-GEN_VXFORM(vsubshs, 0, 29),
-GEN_VXFORM_DUAL(vsubsws, xpnd04_2, 0, 30, PPC_ALTIVEC, PPC_NONE),
+GEN_VXFORM_300_EXT(vmul10uq, 0, 8, 0x0000F800),
+GEN_VXFORM_300(vmul10euq, 0, 9),
+GEN_VXFORM_300(bcdcpsgn, 0, 13),
+GEN_VXFORM_207(bcdadd, 0, 24),
+GEN_VXFORM_207(bcdsub, 0, 25),
+GEN_VXFORM_300(bcdtrunc, 0, 28),
+GEN_VXFORM_300(xpnd04_2, 0, 30),
GEN_VXFORM_300(bcdtrunc, 0, 20),
GEN_VXFORM_300(bcdutrunc, 0, 21),
GEN_VXFORM(vsl, 2, 7),