From b7a50eb7d665f2bb77cbae54461be2f16938dece Mon Sep 17 00:00:00 2001 From: David Miller Date: Thu, 28 Apr 2022 11:47:02 +0200 Subject: target/s390x: vxeh2: Update for changes to vector shifts Signed-off-by: David Miller Signed-off-by: Richard Henderson Signed-off-by: David Hildenbrand Tested-by: Thomas Huth Reviewed-by: David Hildenbrand Message-Id: <20220428094708.84835-8-david@redhat.com> Signed-off-by: Thomas Huth --- target/s390x/tcg/insn-data.def | 12 +++--- target/s390x/tcg/translate_vx.c.inc | 75 +++++++++++++++---------------------- target/s390x/tcg/vec_int_helper.c | 55 +++++++++++++++++++++++++++ 3 files changed, 92 insertions(+), 50 deletions(-) (limited to 'target/s390x/tcg') diff --git a/target/s390x/tcg/insn-data.def b/target/s390x/tcg/insn-data.def index 46add91a0e..f487a64abf 100644 --- a/target/s390x/tcg/insn-data.def +++ b/target/s390x/tcg/insn-data.def @@ -1204,19 +1204,19 @@ F(0xe778, VESRLV, VRR_c, V, 0, 0, 0, 0, vesv, 0, IF_VEC) F(0xe738, VESRL, VRS_a, V, la2, 0, 0, 0, ves, 0, IF_VEC) /* VECTOR SHIFT LEFT */ - F(0xe774, VSL, VRR_c, V, 0, 0, 0, 0, vsl, 0, IF_VEC) + E(0xe774, VSL, VRR_c, V, 0, 0, 0, 0, vsl, 0, 0, IF_VEC) /* VECTOR SHIFT LEFT BY BYTE */ - F(0xe775, VSLB, VRR_c, V, 0, 0, 0, 0, vsl, 0, IF_VEC) + E(0xe775, VSLB, VRR_c, V, 0, 0, 0, 0, vsl, 0, 1, IF_VEC) /* VECTOR SHIFT LEFT DOUBLE BY BYTE */ F(0xe777, VSLDB, VRI_d, V, 0, 0, 0, 0, vsldb, 0, IF_VEC) /* VECTOR SHIFT RIGHT ARITHMETIC */ - F(0xe77e, VSRA, VRR_c, V, 0, 0, 0, 0, vsra, 0, IF_VEC) + E(0xe77e, VSRA, VRR_c, V, 0, 0, 0, 0, vsra, 0, 0, IF_VEC) /* VECTOR SHIFT RIGHT ARITHMETIC BY BYTE */ - F(0xe77f, VSRAB, VRR_c, V, 0, 0, 0, 0, vsra, 0, IF_VEC) + E(0xe77f, VSRAB, VRR_c, V, 0, 0, 0, 0, vsra, 0, 1, IF_VEC) /* VECTOR SHIFT RIGHT LOGICAL */ - F(0xe77c, VSRL, VRR_c, V, 0, 0, 0, 0, vsrl, 0, IF_VEC) + E(0xe77c, VSRL, VRR_c, V, 0, 0, 0, 0, vsrl, 0, 0, IF_VEC) /* VECTOR SHIFT RIGHT LOGICAL BY BYTE */ - F(0xe77d, VSRLB, VRR_c, V, 0, 0, 0, 0, vsrl, 0, IF_VEC) + E(0xe77d, VSRLB, VRR_c, V, 0, 0, 0, 0, vsrl, 0, 1, IF_VEC) /* VECTOR SUBTRACT */ F(0xe7f7, VS, VRR_c, V, 0, 0, 0, 0, vs, 0, IF_VEC) /* VECTOR SUBTRACT COMPUTE BORROW INDICATION */ diff --git a/target/s390x/tcg/translate_vx.c.inc b/target/s390x/tcg/translate_vx.c.inc index 8ddbd440e2..81673ea68f 100644 --- a/target/s390x/tcg/translate_vx.c.inc +++ b/target/s390x/tcg/translate_vx.c.inc @@ -2018,23 +2018,44 @@ static DisasJumpType op_ves(DisasContext *s, DisasOps *o) return DISAS_NEXT; } -static DisasJumpType op_vsl(DisasContext *s, DisasOps *o) +static DisasJumpType gen_vsh_by_byte(DisasContext *s, DisasOps *o, + gen_helper_gvec_2i *gen, + gen_helper_gvec_3 *gen_ve2) { - TCGv_i64 shift = tcg_temp_new_i64(); + bool byte = s->insn->data; - read_vec_element_i64(shift, get_field(s, v3), 7, ES_8); - if (s->fields.op2 == 0x74) { - tcg_gen_andi_i64(shift, shift, 0x7); + if (!byte && s390_has_feat(S390_FEAT_VECTOR_ENH2)) { + gen_gvec_3_ool(get_field(s, v1), get_field(s, v2), + get_field(s, v3), 0, gen_ve2); } else { - tcg_gen_andi_i64(shift, shift, 0x78); - } + TCGv_i64 shift = tcg_temp_new_i64(); - gen_gvec_2i_ool(get_field(s, v1), get_field(s, v2), - shift, 0, gen_helper_gvec_vsl); - tcg_temp_free_i64(shift); + read_vec_element_i64(shift, get_field(s, v3), 7, ES_8); + tcg_gen_andi_i64(shift, shift, byte ? 0x78 : 7); + gen_gvec_2i_ool(get_field(s, v1), get_field(s, v2), shift, 0, gen); + tcg_temp_free_i64(shift); + } return DISAS_NEXT; } +static DisasJumpType op_vsl(DisasContext *s, DisasOps *o) +{ + return gen_vsh_by_byte(s, o, gen_helper_gvec_vsl, + gen_helper_gvec_vsl_ve2); +} + +static DisasJumpType op_vsra(DisasContext *s, DisasOps *o) +{ + return gen_vsh_by_byte(s, o, gen_helper_gvec_vsra, + gen_helper_gvec_vsra_ve2); +} + +static DisasJumpType op_vsrl(DisasContext *s, DisasOps *o) +{ + return gen_vsh_by_byte(s, o, gen_helper_gvec_vsrl, + gen_helper_gvec_vsrl_ve2); +} + static DisasJumpType op_vsldb(DisasContext *s, DisasOps *o) { const uint8_t i4 = get_field(s, i4) & 0xf; @@ -2064,40 +2085,6 @@ static DisasJumpType op_vsldb(DisasContext *s, DisasOps *o) return DISAS_NEXT; } -static DisasJumpType op_vsra(DisasContext *s, DisasOps *o) -{ - TCGv_i64 shift = tcg_temp_new_i64(); - - read_vec_element_i64(shift, get_field(s, v3), 7, ES_8); - if (s->fields.op2 == 0x7e) { - tcg_gen_andi_i64(shift, shift, 0x7); - } else { - tcg_gen_andi_i64(shift, shift, 0x78); - } - - gen_gvec_2i_ool(get_field(s, v1), get_field(s, v2), - shift, 0, gen_helper_gvec_vsra); - tcg_temp_free_i64(shift); - return DISAS_NEXT; -} - -static DisasJumpType op_vsrl(DisasContext *s, DisasOps *o) -{ - TCGv_i64 shift = tcg_temp_new_i64(); - - read_vec_element_i64(shift, get_field(s, v3), 7, ES_8); - if (s->fields.op2 == 0x7c) { - tcg_gen_andi_i64(shift, shift, 0x7); - } else { - tcg_gen_andi_i64(shift, shift, 0x78); - } - - gen_gvec_2i_ool(get_field(s, v1), get_field(s, v2), - shift, 0, gen_helper_gvec_vsrl); - tcg_temp_free_i64(shift); - return DISAS_NEXT; -} - static DisasJumpType op_vs(DisasContext *s, DisasOps *o) { const uint8_t es = get_field(s, m4); diff --git a/target/s390x/tcg/vec_int_helper.c b/target/s390x/tcg/vec_int_helper.c index b44859ee16..53ab5c5eb3 100644 --- a/target/s390x/tcg/vec_int_helper.c +++ b/target/s390x/tcg/vec_int_helper.c @@ -539,18 +539,73 @@ void HELPER(gvec_vsl)(void *v1, const void *v2, uint64_t count, s390_vec_shl(v1, v2, count); } +void HELPER(gvec_vsl_ve2)(void *v1, const void *v2, const void *v3, + uint32_t desc) +{ + S390Vector tmp; + uint32_t sh, e0, e1 = 0; + int i; + + for (i = 15; i >= 0; --i, e1 = e0) { + e0 = s390_vec_read_element8(v2, i); + sh = s390_vec_read_element8(v3, i) & 7; + + s390_vec_write_element8(&tmp, i, rol32(e0 | (e1 << 24), sh)); + } + + *(S390Vector *)v1 = tmp; +} + void HELPER(gvec_vsra)(void *v1, const void *v2, uint64_t count, uint32_t desc) { s390_vec_sar(v1, v2, count); } +void HELPER(gvec_vsra_ve2)(void *v1, const void *v2, const void *v3, + uint32_t desc) +{ + S390Vector tmp; + uint32_t sh, e0, e1 = 0; + int i = 0; + + /* Byte 0 is special only. */ + e0 = (int32_t)(int8_t)s390_vec_read_element8(v2, i); + sh = s390_vec_read_element8(v3, i) & 7; + s390_vec_write_element8(&tmp, i, e0 >> sh); + + e1 = e0; + for (i = 1; i < 16; ++i, e1 = e0) { + e0 = s390_vec_read_element8(v2, i); + sh = s390_vec_read_element8(v3, i) & 7; + s390_vec_write_element8(&tmp, i, (e0 | e1 << 8) >> sh); + } + + *(S390Vector *)v1 = tmp; +} + void HELPER(gvec_vsrl)(void *v1, const void *v2, uint64_t count, uint32_t desc) { s390_vec_shr(v1, v2, count); } +void HELPER(gvec_vsrl_ve2)(void *v1, const void *v2, const void *v3, + uint32_t desc) +{ + S390Vector tmp; + uint32_t sh, e0, e1 = 0; + + for (int i = 0; i < 16; ++i, e1 = e0) { + e0 = s390_vec_read_element8(v2, i); + sh = s390_vec_read_element8(v3, i) & 7; + + s390_vec_write_element8(&tmp, i, (e0 | (e1 << 8)) >> sh); + } + + *(S390Vector *)v1 = tmp; +} + #define DEF_VSCBI(BITS) \ void HELPER(gvec_vscbi##BITS)(void *v1, const void *v2, const void *v3, \ uint32_t desc) \ -- cgit v1.2.3-55-g7522