diff options
author | Richard Henderson <richard.henderson@linaro.org> | 2019-03-17 00:27:29 +0000 |
---|---|---|
committer | Richard Henderson <richard.henderson@linaro.org> | 2019-05-13 14:44:03 -0700 |
commit | 53229a7703eeb2bbe101a19a33ef22aaf960c65b (patch) | |
tree | 9537c1a62ddef09de2d814ee03ffeba3fd06ac13 /tcg/tcg-op-gvec.c | |
parent | ce27c5d1a38e93da38653af71fb468c5eded4c7b (diff) | |
download | qemu-53229a7703eeb2bbe101a19a33ef22aaf960c65b.zip qemu-53229a7703eeb2bbe101a19a33ef22aaf960c65b.tar.gz qemu-53229a7703eeb2bbe101a19a33ef22aaf960c65b.tar.bz2 |
tcg: Specify optional vector requirements with a list
Replace the single opcode in .opc with a null-terminated
array in .opt_opc. We still require that all opcodes be
used with the same .vece.
Validate the contents of this list with CONFIG_DEBUG_TCG.
All tcg_gen_*_vec functions will check any list active
during .fniv expansion. Swap the active list in and out
as we expand other opcodes, or take control away from the
front-end function.
Convert all existing vector aware front ends.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'tcg/tcg-op-gvec.c')
-rw-r--r-- | tcg/tcg-op-gvec.c | 249 |
1 files changed, 144 insertions, 105 deletions
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index f831adb..3fcb235 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -26,6 +26,13 @@ #define MAX_UNROLL 4 +#ifdef CONFIG_DEBUG_TCG +static const TCGOpcode vecop_list_empty[1] = { 0 }; +#else +#define vecop_list_empty NULL +#endif + + /* Verify vector size and alignment rules. OFS should be the OR of all of the operand offsets so that we can check them all at once. */ static void check_size_align(uint32_t oprsz, uint32_t maxsz, uint32_t ofs) @@ -360,31 +367,29 @@ static void gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in) * on elements of size VECE in the selected type. Do not select V64 if * PREFER_I64 is true. Return 0 if no vector type is selected. */ -static TCGType choose_vector_type(TCGOpcode op, unsigned vece, uint32_t size, - bool prefer_i64) +static TCGType choose_vector_type(const TCGOpcode *list, unsigned vece, + uint32_t size, bool prefer_i64) { if (TCG_TARGET_HAS_v256 && check_size_impl(size, 32)) { - if (op == 0) { - return TCG_TYPE_V256; - } - /* Recall that ARM SVE allows vector sizes that are not a + /* + * Recall that ARM SVE allows vector sizes that are not a * power of 2, but always a multiple of 16. The intent is * that e.g. size == 80 would be expanded with 2x32 + 1x16. * It is hard to imagine a case in which v256 is supported * but v128 is not, but check anyway. */ - if (tcg_can_emit_vec_op(op, TCG_TYPE_V256, vece) + if (tcg_can_emit_vecop_list(list, TCG_TYPE_V256, vece) && (size % 32 == 0 - || tcg_can_emit_vec_op(op, TCG_TYPE_V128, vece))) { + || tcg_can_emit_vecop_list(list, TCG_TYPE_V128, vece))) { return TCG_TYPE_V256; } } if (TCG_TARGET_HAS_v128 && check_size_impl(size, 16) - && (op == 0 || tcg_can_emit_vec_op(op, TCG_TYPE_V128, vece))) { + && tcg_can_emit_vecop_list(list, TCG_TYPE_V128, vece)) { return TCG_TYPE_V128; } if (TCG_TARGET_HAS_v64 && !prefer_i64 && check_size_impl(size, 8) - && (op == 0 || tcg_can_emit_vec_op(op, TCG_TYPE_V64, vece))) { + && tcg_can_emit_vecop_list(list, TCG_TYPE_V64, vece)) { return TCG_TYPE_V64; } return 0; @@ -418,7 +423,7 @@ static void do_dup(unsigned vece, uint32_t dofs, uint32_t oprsz, /* Implement inline with a vector type, if possible. * Prefer integer when 64-bit host and no variable dup. */ - type = choose_vector_type(0, vece, oprsz, + type = choose_vector_type(NULL, vece, oprsz, (TCG_TARGET_REG_BITS == 64 && in_32 == NULL && (in_64 == NULL || vece == MO_64))); if (type != 0) { @@ -991,6 +996,8 @@ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz, const GVecGen2 *g) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGType type; uint32_t some; @@ -999,7 +1006,7 @@ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } switch (type) { case TCG_TYPE_V256: @@ -1032,13 +1039,14 @@ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, } else { assert(g->fno != NULL); tcg_gen_gvec_2_ool(dofs, aofs, oprsz, maxsz, g->data, g->fno); - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); @@ -1049,6 +1057,8 @@ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz, int64_t c, const GVecGen2i *g) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGType type; uint32_t some; @@ -1057,7 +1067,7 @@ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } switch (type) { case TCG_TYPE_V256: @@ -1099,13 +1109,14 @@ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, maxsz, c, g->fnoi); tcg_temp_free_i64(tcg_c); } - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); @@ -1123,9 +1134,11 @@ void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } if (type != 0) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGv_vec t_vec = tcg_temp_new_vec(type); uint32_t some; @@ -1163,6 +1176,7 @@ void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, g_assert_not_reached(); } tcg_temp_free_vec(t_vec); + tcg_swap_vecop_list(hold_list); } else if (g->fni8 && check_size_impl(oprsz, 8)) { TCGv_i64 t64 = tcg_temp_new_i64(); @@ -1190,6 +1204,8 @@ void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz, const GVecGen3 *g) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGType type; uint32_t some; @@ -1198,7 +1214,7 @@ void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } switch (type) { case TCG_TYPE_V256: @@ -1236,13 +1252,14 @@ void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, assert(g->fno != NULL); tcg_gen_gvec_3_ool(dofs, aofs, bofs, oprsz, maxsz, g->data, g->fno); - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); @@ -1254,6 +1271,8 @@ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz, int64_t c, const GVecGen3i *g) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGType type; uint32_t some; @@ -1262,7 +1281,7 @@ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } switch (type) { case TCG_TYPE_V256: @@ -1300,13 +1319,14 @@ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, } else { assert(g->fno != NULL); tcg_gen_gvec_3_ool(dofs, aofs, bofs, oprsz, maxsz, c, g->fno); - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); @@ -1317,6 +1337,8 @@ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, uint32_t maxsz, const GVecGen4 *g) { + const TCGOpcode *this_list = g->opt_opc ? : vecop_list_empty; + const TCGOpcode *hold_list = tcg_swap_vecop_list(this_list); TCGType type; uint32_t some; @@ -1325,7 +1347,7 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, type = 0; if (g->fniv) { - type = choose_vector_type(g->opc, g->vece, oprsz, g->prefer_i64); + type = choose_vector_type(g->opt_opc, g->vece, oprsz, g->prefer_i64); } switch (type) { case TCG_TYPE_V256: @@ -1366,13 +1388,14 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, assert(g->fno != NULL); tcg_gen_gvec_4_ool(dofs, aofs, bofs, cofs, oprsz, maxsz, g->data, g->fno); - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); @@ -1567,6 +1590,8 @@ void tcg_gen_vec_add32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) tcg_temp_free_i64(t2); } +static const TCGOpcode vecop_list_add[] = { INDEX_op_add_vec, 0 }; + void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { @@ -1574,22 +1599,22 @@ void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, { .fni8 = tcg_gen_vec_add8_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_add8, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_8 }, { .fni8 = tcg_gen_vec_add16_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_add16, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_16 }, { .fni4 = tcg_gen_add_i32, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_add32, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_32 }, { .fni8 = tcg_gen_add_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_add64, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1605,22 +1630,22 @@ void tcg_gen_gvec_adds(unsigned vece, uint32_t dofs, uint32_t aofs, { .fni8 = tcg_gen_vec_add8_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_adds8, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_8 }, { .fni8 = tcg_gen_vec_add16_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_adds16, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_16 }, { .fni4 = tcg_gen_add_i32, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_adds32, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .vece = MO_32 }, { .fni8 = tcg_gen_add_i64, .fniv = tcg_gen_add_vec, .fno = gen_helper_gvec_adds64, - .opc = INDEX_op_add_vec, + .opt_opc = vecop_list_add, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1637,6 +1662,8 @@ void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_temp_free_i64(tmp); } +static const TCGOpcode vecop_list_sub[] = { INDEX_op_sub_vec, 0 }; + void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs, TCGv_i64 c, uint32_t oprsz, uint32_t maxsz) { @@ -1644,22 +1671,22 @@ void tcg_gen_gvec_subs(unsigned vece, uint32_t dofs, uint32_t aofs, { .fni8 = tcg_gen_vec_sub8_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_subs8, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_8 }, { .fni8 = tcg_gen_vec_sub16_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_subs16, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_16 }, { .fni4 = tcg_gen_sub_i32, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_subs32, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_32 }, { .fni8 = tcg_gen_sub_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_subs64, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1723,22 +1750,22 @@ void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, { .fni8 = tcg_gen_vec_sub8_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_sub8, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_8 }, { .fni8 = tcg_gen_vec_sub16_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_sub16, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_16 }, { .fni4 = tcg_gen_sub_i32, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_sub32, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .vece = MO_32 }, { .fni8 = tcg_gen_sub_i64, .fniv = tcg_gen_sub_vec, .fno = gen_helper_gvec_sub64, - .opc = INDEX_op_sub_vec, + .opt_opc = vecop_list_sub, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1747,27 +1774,29 @@ void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); } +static const TCGOpcode vecop_list_mul[] = { INDEX_op_mul_vec, 0 }; + void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { static const GVecGen3 g[4] = { { .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_mul8, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_8 }, { .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_mul16, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_16 }, { .fni4 = tcg_gen_mul_i32, .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_mul32, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_32 }, { .fni8 = tcg_gen_mul_i64, .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_mul64, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1782,21 +1811,21 @@ void tcg_gen_gvec_muls(unsigned vece, uint32_t dofs, uint32_t aofs, static const GVecGen2s g[4] = { { .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_muls8, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_8 }, { .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_muls16, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_16 }, { .fni4 = tcg_gen_mul_i32, .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_muls32, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .vece = MO_32 }, { .fni8 = tcg_gen_mul_i64, .fniv = tcg_gen_mul_vec, .fno = gen_helper_gvec_muls64, - .opc = INDEX_op_mul_vec, + .opt_opc = vecop_list_mul, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -1816,22 +1845,23 @@ void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_ssadd_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_ssadd_vec, .fno = gen_helper_gvec_ssadd8, - .opc = INDEX_op_ssadd_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_ssadd_vec, .fno = gen_helper_gvec_ssadd16, - .opc = INDEX_op_ssadd_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fniv = tcg_gen_ssadd_vec, .fno = gen_helper_gvec_ssadd32, - .opc = INDEX_op_ssadd_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fniv = tcg_gen_ssadd_vec, .fno = gen_helper_gvec_ssadd64, - .opc = INDEX_op_ssadd_vec, + .opt_opc = vecop_list, .vece = MO_64 }, }; tcg_debug_assert(vece <= MO_64); @@ -1841,22 +1871,23 @@ void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_sssub(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_sssub_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_sssub_vec, .fno = gen_helper_gvec_sssub8, - .opc = INDEX_op_sssub_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_sssub_vec, .fno = gen_helper_gvec_sssub16, - .opc = INDEX_op_sssub_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fniv = tcg_gen_sssub_vec, .fno = gen_helper_gvec_sssub32, - .opc = INDEX_op_sssub_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fniv = tcg_gen_sssub_vec, .fno = gen_helper_gvec_sssub64, - .opc = INDEX_op_sssub_vec, + .opt_opc = vecop_list, .vece = MO_64 }, }; tcg_debug_assert(vece <= MO_64); @@ -1882,24 +1913,25 @@ static void tcg_gen_usadd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_usadd_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_usadd_vec, .fno = gen_helper_gvec_usadd8, - .opc = INDEX_op_usadd_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_usadd_vec, .fno = gen_helper_gvec_usadd16, - .opc = INDEX_op_usadd_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_usadd_i32, .fniv = tcg_gen_usadd_vec, .fno = gen_helper_gvec_usadd32, - .opc = INDEX_op_usadd_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_usadd_i64, .fniv = tcg_gen_usadd_vec, .fno = gen_helper_gvec_usadd64, - .opc = INDEX_op_usadd_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -1925,24 +1957,25 @@ static void tcg_gen_ussub_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_ussub_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_ussub_vec, .fno = gen_helper_gvec_ussub8, - .opc = INDEX_op_ussub_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_ussub_vec, .fno = gen_helper_gvec_ussub16, - .opc = INDEX_op_ussub_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_ussub_i32, .fniv = tcg_gen_ussub_vec, .fno = gen_helper_gvec_ussub32, - .opc = INDEX_op_ussub_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_ussub_i64, .fniv = tcg_gen_ussub_vec, .fno = gen_helper_gvec_ussub64, - .opc = INDEX_op_ussub_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -1952,24 +1985,25 @@ void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_smin_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_smin_vec, .fno = gen_helper_gvec_smin8, - .opc = INDEX_op_smin_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_smin_vec, .fno = gen_helper_gvec_smin16, - .opc = INDEX_op_smin_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_smin_i32, .fniv = tcg_gen_smin_vec, .fno = gen_helper_gvec_smin32, - .opc = INDEX_op_smin_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_smin_i64, .fniv = tcg_gen_smin_vec, .fno = gen_helper_gvec_smin64, - .opc = INDEX_op_smin_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -1979,24 +2013,25 @@ void tcg_gen_gvec_smin(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_umin_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_umin_vec, .fno = gen_helper_gvec_umin8, - .opc = INDEX_op_umin_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_umin_vec, .fno = gen_helper_gvec_umin16, - .opc = INDEX_op_umin_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_umin_i32, .fniv = tcg_gen_umin_vec, .fno = gen_helper_gvec_umin32, - .opc = INDEX_op_umin_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_umin_i64, .fniv = tcg_gen_umin_vec, .fno = gen_helper_gvec_umin64, - .opc = INDEX_op_umin_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -2006,24 +2041,25 @@ void tcg_gen_gvec_umin(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_smax_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_smax_vec, .fno = gen_helper_gvec_smax8, - .opc = INDEX_op_smax_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_smax_vec, .fno = gen_helper_gvec_smax16, - .opc = INDEX_op_smax_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_smax_i32, .fniv = tcg_gen_smax_vec, .fno = gen_helper_gvec_smax32, - .opc = INDEX_op_smax_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_smax_i64, .fniv = tcg_gen_smax_vec, .fno = gen_helper_gvec_smax64, - .opc = INDEX_op_smax_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -2033,24 +2069,25 @@ void tcg_gen_gvec_smax(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_umax(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_umax_vec, 0 }; static const GVecGen3 g[4] = { { .fniv = tcg_gen_umax_vec, .fno = gen_helper_gvec_umax8, - .opc = INDEX_op_umax_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fniv = tcg_gen_umax_vec, .fno = gen_helper_gvec_umax16, - .opc = INDEX_op_umax_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_umax_i32, .fniv = tcg_gen_umax_vec, .fno = gen_helper_gvec_umax32, - .opc = INDEX_op_umax_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_umax_i64, .fniv = tcg_gen_umax_vec, .fno = gen_helper_gvec_umax64, - .opc = INDEX_op_umax_vec, + .opt_opc = vecop_list, .vece = MO_64 } }; tcg_debug_assert(vece <= MO_64); @@ -2104,26 +2141,27 @@ void tcg_gen_vec_neg32_i64(TCGv_i64 d, TCGv_i64 b) void tcg_gen_gvec_neg(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_neg_vec, 0 }; static const GVecGen2 g[4] = { { .fni8 = tcg_gen_vec_neg8_i64, .fniv = tcg_gen_neg_vec, .fno = gen_helper_gvec_neg8, - .opc = INDEX_op_neg_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fni8 = tcg_gen_vec_neg16_i64, .fniv = tcg_gen_neg_vec, .fno = gen_helper_gvec_neg16, - .opc = INDEX_op_neg_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_neg_i32, .fniv = tcg_gen_neg_vec, .fno = gen_helper_gvec_neg32, - .opc = INDEX_op_neg_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_neg_i64, .fniv = tcg_gen_neg_vec, .fno = gen_helper_gvec_neg64, - .opc = INDEX_op_neg_vec, + .opt_opc = vecop_list, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -2139,7 +2177,6 @@ void tcg_gen_gvec_and(unsigned vece, uint32_t dofs, uint32_t aofs, .fni8 = tcg_gen_and_i64, .fniv = tcg_gen_and_vec, .fno = gen_helper_gvec_and, - .opc = INDEX_op_and_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; @@ -2157,7 +2194,6 @@ void tcg_gen_gvec_or(unsigned vece, uint32_t dofs, uint32_t aofs, .fni8 = tcg_gen_or_i64, .fniv = tcg_gen_or_vec, .fno = gen_helper_gvec_or, - .opc = INDEX_op_or_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; @@ -2175,7 +2211,6 @@ void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs, .fni8 = tcg_gen_xor_i64, .fniv = tcg_gen_xor_vec, .fno = gen_helper_gvec_xor, - .opc = INDEX_op_xor_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; @@ -2193,7 +2228,6 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs, .fni8 = tcg_gen_andc_i64, .fniv = tcg_gen_andc_vec, .fno = gen_helper_gvec_andc, - .opc = INDEX_op_andc_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; @@ -2211,7 +2245,6 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs, .fni8 = tcg_gen_orc_i64, .fniv = tcg_gen_orc_vec, .fno = gen_helper_gvec_orc, - .opc = INDEX_op_orc_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, }; @@ -2277,7 +2310,6 @@ static const GVecGen2s gop_ands = { .fni8 = tcg_gen_and_i64, .fniv = tcg_gen_and_vec, .fno = gen_helper_gvec_ands, - .opc = INDEX_op_and_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }; @@ -2303,7 +2335,6 @@ static const GVecGen2s gop_xors = { .fni8 = tcg_gen_xor_i64, .fniv = tcg_gen_xor_vec, .fno = gen_helper_gvec_xors, - .opc = INDEX_op_xor_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }; @@ -2329,7 +2360,6 @@ static const GVecGen2s gop_ors = { .fni8 = tcg_gen_or_i64, .fniv = tcg_gen_or_vec, .fno = gen_helper_gvec_ors, - .opc = INDEX_op_or_vec, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }; @@ -2368,26 +2398,27 @@ void tcg_gen_vec_shl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c) void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs, int64_t shift, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 }; static const GVecGen2i g[4] = { { .fni8 = tcg_gen_vec_shl8i_i64, .fniv = tcg_gen_shli_vec, .fno = gen_helper_gvec_shl8i, - .opc = INDEX_op_shli_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fni8 = tcg_gen_vec_shl16i_i64, .fniv = tcg_gen_shli_vec, .fno = gen_helper_gvec_shl16i, - .opc = INDEX_op_shli_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_shli_i32, .fniv = tcg_gen_shli_vec, .fno = gen_helper_gvec_shl32i, - .opc = INDEX_op_shli_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_shli_i64, .fniv = tcg_gen_shli_vec, .fno = gen_helper_gvec_shl64i, - .opc = INDEX_op_shli_vec, + .opt_opc = vecop_list, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -2418,26 +2449,27 @@ void tcg_gen_vec_shr16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c) void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs, int64_t shift, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 }; static const GVecGen2i g[4] = { { .fni8 = tcg_gen_vec_shr8i_i64, .fniv = tcg_gen_shri_vec, .fno = gen_helper_gvec_shr8i, - .opc = INDEX_op_shri_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fni8 = tcg_gen_vec_shr16i_i64, .fniv = tcg_gen_shri_vec, .fno = gen_helper_gvec_shr16i, - .opc = INDEX_op_shri_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_shri_i32, .fniv = tcg_gen_shri_vec, .fno = gen_helper_gvec_shr32i, - .opc = INDEX_op_shri_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_shri_i64, .fniv = tcg_gen_shri_vec, .fno = gen_helper_gvec_shr64i, - .opc = INDEX_op_shri_vec, + .opt_opc = vecop_list, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -2482,26 +2514,27 @@ void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c) void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs, int64_t shift, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode vecop_list[] = { INDEX_op_sari_vec, 0 }; static const GVecGen2i g[4] = { { .fni8 = tcg_gen_vec_sar8i_i64, .fniv = tcg_gen_sari_vec, .fno = gen_helper_gvec_sar8i, - .opc = INDEX_op_sari_vec, + .opt_opc = vecop_list, .vece = MO_8 }, { .fni8 = tcg_gen_vec_sar16i_i64, .fniv = tcg_gen_sari_vec, .fno = gen_helper_gvec_sar16i, - .opc = INDEX_op_sari_vec, + .opt_opc = vecop_list, .vece = MO_16 }, { .fni4 = tcg_gen_sari_i32, .fniv = tcg_gen_sari_vec, .fno = gen_helper_gvec_sar32i, - .opc = INDEX_op_sari_vec, + .opt_opc = vecop_list, .vece = MO_32 }, { .fni8 = tcg_gen_sari_i64, .fniv = tcg_gen_sari_vec, .fno = gen_helper_gvec_sar64i, - .opc = INDEX_op_sari_vec, + .opt_opc = vecop_list, .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; @@ -2574,6 +2607,7 @@ void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { + static const TCGOpcode cmp_list[] = { INDEX_op_cmp_vec, 0 }; static gen_helper_gvec_3 * const eq_fn[4] = { gen_helper_gvec_eq8, gen_helper_gvec_eq16, gen_helper_gvec_eq32, gen_helper_gvec_eq64 @@ -2606,6 +2640,8 @@ void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, [TCG_COND_LTU] = ltu_fn, [TCG_COND_LEU] = leu_fn, }; + + const TCGOpcode *hold_list; TCGType type; uint32_t some; @@ -2618,10 +2654,12 @@ void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, return; } - /* Implement inline with a vector type, if possible. + /* + * Implement inline with a vector type, if possible. * Prefer integer when 64-bit host and 64-bit comparison. */ - type = choose_vector_type(INDEX_op_cmp_vec, vece, oprsz, + hold_list = tcg_swap_vecop_list(cmp_list); + type = choose_vector_type(cmp_list, vece, oprsz, TCG_TARGET_REG_BITS == 64 && vece == MO_64); switch (type) { case TCG_TYPE_V256: @@ -2663,13 +2701,14 @@ void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs, assert(fn != NULL); } tcg_gen_gvec_3_ool(dofs, aofs, bofs, oprsz, maxsz, 0, fn[vece]); - return; + oprsz = maxsz; } break; default: g_assert_not_reached(); } + tcg_swap_vecop_list(hold_list); if (oprsz < maxsz) { expand_clr(dofs + oprsz, maxsz - oprsz); |