diff --git a/target/ppc/helper.h b/target/ppc/helper.h index a06193bc67..71c22efc2e 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -143,15 +143,15 @@ DEF_HELPER_FLAGS_1(ftsqrt, TCG_CALL_NO_RWG_SE, i32, i64) #define dh_ctype_acc ppc_acc_t * #define dh_typecode_acc dh_typecode_ptr -DEF_HELPER_FLAGS_3(vavgub, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vavguh, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vavguw, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_4(VAVGUB, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VAVGUH, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VAVGUW, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) DEF_HELPER_FLAGS_3(vabsdub, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_3(vabsduh, TCG_CALL_NO_RWG, void, avr, avr, avr) DEF_HELPER_FLAGS_3(vabsduw, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vavgsb, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vavgsh, TCG_CALL_NO_RWG, void, avr, avr, avr) -DEF_HELPER_FLAGS_3(vavgsw, TCG_CALL_NO_RWG, void, avr, avr, avr) +DEF_HELPER_FLAGS_4(VAVGSB, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VAVGSH, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) +DEF_HELPER_FLAGS_4(VAVGSW, TCG_CALL_NO_RWG, void, avr, avr, avr, i32) DEF_HELPER_4(vcmpeqfp, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgefp, void, env, avr, avr, avr) DEF_HELPER_4(vcmpgtfp, void, env, avr, avr, avr) diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode index b05c89efee..53dd45bbab 100644 --- a/target/ppc/insn32.decode +++ b/target/ppc/insn32.decode @@ -519,6 +519,15 @@ VCMPNEZW 000100 ..... ..... ..... . 0110000111 @VC VCMPSQ 000100 ... -- ..... ..... 00101000001 @VX_bf VCMPUQ 000100 ... -- ..... ..... 00100000001 @VX_bf +## Vector Integer Average Instructions + +VAVGSB 000100 ..... ..... ..... 10100000010 @VX +VAVGSH 000100 ..... ..... ..... 10101000010 @VX +VAVGSW 000100 ..... ..... ..... 10110000010 @VX +VAVGUB 000100 ..... ..... ..... 10000000010 @VX +VAVGUH 000100 ..... ..... ..... 10001000010 @VX +VAVGUW 000100 ..... ..... ..... 10010000010 @VX + ## Vector Bit Manipulation Instruction VGNB 000100 ..... -- ... ..... 10011001100 @VX_n diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index c6ce4665fa..bda76e54d4 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -570,25 +570,23 @@ VARITHSAT_UNSIGNED(w, u32, uint64_t, cvtsduw) #undef VARITHSAT_SIGNED #undef VARITHSAT_UNSIGNED -#define VAVG_DO(name, element, etype) \ - void helper_v##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \ - { \ - int i; \ - \ - for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ - etype x = (etype)a->element[i] + (etype)b->element[i] + 1; \ - r->element[i] = x >> 1; \ - } \ +#define VAVG(name, element, etype) \ + void helper_##name(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t v)\ + { \ + int i; \ + \ + for (i = 0; i < ARRAY_SIZE(r->element); i++) { \ + etype x = (etype)a->element[i] + (etype)b->element[i] + 1; \ + r->element[i] = x >> 1; \ + } \ } -#define VAVG(type, signed_element, signed_type, unsigned_element, \ - unsigned_type) \ - VAVG_DO(avgs##type, signed_element, signed_type) \ - VAVG_DO(avgu##type, unsigned_element, unsigned_type) -VAVG(b, s8, int16_t, u8, uint16_t) -VAVG(h, s16, int32_t, u16, uint32_t) -VAVG(w, s32, int64_t, u32, uint64_t) -#undef VAVG_DO +VAVG(VAVGSB, s8, int16_t) +VAVG(VAVGUB, u8, uint16_t) +VAVG(VAVGSH, s16, int32_t) +VAVG(VAVGUH, u16, uint32_t) +VAVG(VAVGSW, s32, int64_t) +VAVG(VAVGUW, u32, uint64_t) #undef VAVG #define VABSDU_DO(name, element) \ diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc index cbb2a3ebe7..195c601f7a 100644 --- a/target/ppc/translate/vmx-impl.c.inc +++ b/target/ppc/translate/vmx-impl.c.inc @@ -431,21 +431,9 @@ GEN_VXFORM_V(vminsb, MO_8, tcg_gen_gvec_smin, 1, 12); GEN_VXFORM_V(vminsh, MO_16, tcg_gen_gvec_smin, 1, 13); GEN_VXFORM_V(vminsw, MO_32, tcg_gen_gvec_smin, 1, 14); GEN_VXFORM_V(vminsd, MO_64, tcg_gen_gvec_smin, 1, 15); -GEN_VXFORM(vavgub, 1, 16); GEN_VXFORM(vabsdub, 1, 16); -GEN_VXFORM_DUAL(vavgub, PPC_ALTIVEC, PPC_NONE, \ - vabsdub, PPC_NONE, PPC2_ISA300) -GEN_VXFORM(vavguh, 1, 17); GEN_VXFORM(vabsduh, 1, 17); -GEN_VXFORM_DUAL(vavguh, PPC_ALTIVEC, PPC_NONE, \ - vabsduh, PPC_NONE, PPC2_ISA300) -GEN_VXFORM(vavguw, 1, 18); GEN_VXFORM(vabsduw, 1, 18); -GEN_VXFORM_DUAL(vavguw, PPC_ALTIVEC, PPC_NONE, \ - vabsduw, PPC_NONE, PPC2_ISA300) -GEN_VXFORM(vavgsb, 1, 20); -GEN_VXFORM(vavgsh, 1, 21); -GEN_VXFORM(vavgsw, 1, 22); GEN_VXFORM(vmrghb, 6, 0); GEN_VXFORM(vmrghh, 6, 1); GEN_VXFORM(vmrghw, 6, 2); @@ -3373,6 +3361,100 @@ TRANS(VMULHSD, do_vx_mulh, true , do_vx_vmulhd_i64) TRANS(VMULHUW, do_vx_mulh, false, do_vx_vmulhw_i64) TRANS(VMULHUD, do_vx_mulh, false, do_vx_vmulhd_i64) +static void do_vavg(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b, + void (*gen_shr_vec)(unsigned, TCGv_vec, TCGv_vec, int64_t)) +{ + TCGv_vec tmp = tcg_temp_new_vec_matching(t); + tcg_gen_or_vec(vece, tmp, a, b); + tcg_gen_and_vec(vece, tmp, tmp, tcg_constant_vec_matching(t, vece, 1)); + gen_shr_vec(vece, a, a, 1); + gen_shr_vec(vece, b, b, 1); + tcg_gen_add_vec(vece, t, a, b); + tcg_gen_add_vec(vece, t, t, tmp); + tcg_temp_free_vec(tmp); +} + +QEMU_FLATTEN +static void gen_vavgu(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b) +{ + do_vavg(vece, t, a, b, tcg_gen_shri_vec); +} + +QEMU_FLATTEN +static void gen_vavgs(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b) +{ + do_vavg(vece, t, a, b, tcg_gen_sari_vec); +} + +static bool do_vx_vavg(DisasContext *ctx, arg_VX *a, int sign, int vece) +{ + static const TCGOpcode vecop_list_s[] = { + INDEX_op_add_vec, INDEX_op_sari_vec, 0 + }; + static const TCGOpcode vecop_list_u[] = { + INDEX_op_add_vec, INDEX_op_shri_vec, 0 + }; + + static const GVecGen3 op[2][3] = { + { + { + .fniv = gen_vavgu, + .fno = gen_helper_VAVGUB, + .opt_opc = vecop_list_u, + .vece = MO_8 + }, + { + .fniv = gen_vavgu, + .fno = gen_helper_VAVGUH, + .opt_opc = vecop_list_u, + .vece = MO_16 + }, + { + .fniv = gen_vavgu, + .fno = gen_helper_VAVGUW, + .opt_opc = vecop_list_u, + .vece = MO_32 + }, + }, + { + { + .fniv = gen_vavgs, + .fno = gen_helper_VAVGSB, + .opt_opc = vecop_list_s, + .vece = MO_8 + }, + { + .fniv = gen_vavgs, + .fno = gen_helper_VAVGSH, + .opt_opc = vecop_list_s, + .vece = MO_16 + }, + { + .fniv = gen_vavgs, + .fno = gen_helper_VAVGSW, + .opt_opc = vecop_list_s, + .vece = MO_32 + }, + }, + }; + + REQUIRE_VECTOR(ctx); + + tcg_gen_gvec_3(avr_full_offset(a->vrt), avr_full_offset(a->vra), + avr_full_offset(a->vrb), 16, 16, &op[sign][vece]); + + + return true; +} + + +TRANS_FLAGS(ALTIVEC, VAVGSB, do_vx_vavg, 1, MO_8) +TRANS_FLAGS(ALTIVEC, VAVGSH, do_vx_vavg, 1, MO_16) +TRANS_FLAGS(ALTIVEC, VAVGSW, do_vx_vavg, 1, MO_32) +TRANS_FLAGS(ALTIVEC, VAVGUB, do_vx_vavg, 0, MO_8) +TRANS_FLAGS(ALTIVEC, VAVGUH, do_vx_vavg, 0, MO_16) +TRANS_FLAGS(ALTIVEC, VAVGUW, do_vx_vavg, 0, MO_32) + static bool do_vdiv_vmod(DisasContext *ctx, arg_VX *a, const int vece, void (*func_32)(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b), void (*func_64)(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)) diff --git a/target/ppc/translate/vmx-ops.c.inc b/target/ppc/translate/vmx-ops.c.inc index 46a620a232..02db51def0 100644 --- a/target/ppc/translate/vmx-ops.c.inc +++ b/target/ppc/translate/vmx-ops.c.inc @@ -83,12 +83,9 @@ GEN_VXFORM(vminsb, 1, 12), GEN_VXFORM(vminsh, 1, 13), GEN_VXFORM(vminsw, 1, 14), GEN_VXFORM_207(vminsd, 1, 15), -GEN_VXFORM_DUAL(vavgub, vabsdub, 1, 16, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_DUAL(vavguh, vabsduh, 1, 17, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM_DUAL(vavguw, vabsduw, 1, 18, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM(vavgsb, 1, 20), -GEN_VXFORM(vavgsh, 1, 21), -GEN_VXFORM(vavgsw, 1, 22), +GEN_VXFORM(vabsdub, 1, 16), +GEN_VXFORM(vabsduh, 1, 17), +GEN_VXFORM(vabsduw, 1, 18), GEN_VXFORM(vmrghb, 6, 0), GEN_VXFORM(vmrghh, 6, 1), GEN_VXFORM(vmrghw, 6, 2),