target/loongarch: Implement vbitclr vbitset vbitrev
This patch includes:
- VBITCLR[I].{B/H/W/D};
- VBITSET[I].{B/H/W/D};
- VBITREV[I].{B/H/W/D}.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-32-gaosong@loongson.cn>
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 0ca51de..48c7ea4 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1272,3 +1272,28 @@
INSN_LSX(vpcnt_h, vv)
INSN_LSX(vpcnt_w, vv)
INSN_LSX(vpcnt_d, vv)
+
+INSN_LSX(vbitclr_b, vvv)
+INSN_LSX(vbitclr_h, vvv)
+INSN_LSX(vbitclr_w, vvv)
+INSN_LSX(vbitclr_d, vvv)
+INSN_LSX(vbitclri_b, vv_i)
+INSN_LSX(vbitclri_h, vv_i)
+INSN_LSX(vbitclri_w, vv_i)
+INSN_LSX(vbitclri_d, vv_i)
+INSN_LSX(vbitset_b, vvv)
+INSN_LSX(vbitset_h, vvv)
+INSN_LSX(vbitset_w, vvv)
+INSN_LSX(vbitset_d, vvv)
+INSN_LSX(vbitseti_b, vv_i)
+INSN_LSX(vbitseti_h, vv_i)
+INSN_LSX(vbitseti_w, vv_i)
+INSN_LSX(vbitseti_d, vv_i)
+INSN_LSX(vbitrev_b, vvv)
+INSN_LSX(vbitrev_h, vvv)
+INSN_LSX(vbitrev_w, vvv)
+INSN_LSX(vbitrev_d, vvv)
+INSN_LSX(vbitrevi_b, vv_i)
+INSN_LSX(vbitrevi_h, vv_i)
+INSN_LSX(vbitrevi_w, vv_i)
+INSN_LSX(vbitrevi_d, vv_i)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index 96b9b16..75120ca 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -485,3 +485,30 @@
DEF_HELPER_3(vpcnt_h, void, env, i32, i32)
DEF_HELPER_3(vpcnt_w, void, env, i32, i32)
DEF_HELPER_3(vpcnt_d, void, env, i32, i32)
+
+DEF_HELPER_FLAGS_4(vbitclr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitclri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitclri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vbitset_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitset_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitseti_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitseti_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(vbitrev_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrev_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_w, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(vbitrevi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc b/target/loongarch/insn_trans/trans_lsx.c.inc
index f4ebdca..86243b5 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -3111,3 +3111,308 @@
TRANS(vpcnt_h, gen_vv, gen_helper_vpcnt_h)
TRANS(vpcnt_w, gen_vv, gen_helper_vpcnt_w)
TRANS(vpcnt_d, gen_vv, gen_helper_vpcnt_d)
+
+static void do_vbit(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b,
+ void (*func)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
+{
+ TCGv_vec mask, lsh, t1, one;
+
+ lsh = tcg_temp_new_vec_matching(t);
+ t1 = tcg_temp_new_vec_matching(t);
+ mask = tcg_constant_vec_matching(t, vece, (8 << vece) - 1);
+ one = tcg_constant_vec_matching(t, vece, 1);
+
+ tcg_gen_and_vec(vece, lsh, b, mask);
+ tcg_gen_shlv_vec(vece, t1, one, lsh);
+ func(vece, t, a, t1);
+}
+
+static void gen_vbitclr(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+ do_vbit(vece, t, a, b, tcg_gen_andc_vec);
+}
+
+static void gen_vbitset(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+ do_vbit(vece, t, a, b, tcg_gen_or_vec);
+}
+
+static void gen_vbitrev(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
+{
+ do_vbit(vece, t, a, b, tcg_gen_xor_vec);
+}
+
+static void do_vbitclr(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shlv_vec, INDEX_op_andc_vec, 0
+ };
+ static const GVecGen3 op[4] = {
+ {
+ .fniv = gen_vbitclr,
+ .fno = gen_helper_vbitclr_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitclr,
+ .fno = gen_helper_vbitclr_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitclr,
+ .fno = gen_helper_vbitclr_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitclr,
+ .fno = gen_helper_vbitclr_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitclr_b, gvec_vvv, MO_8, do_vbitclr)
+TRANS(vbitclr_h, gvec_vvv, MO_16, do_vbitclr)
+TRANS(vbitclr_w, gvec_vvv, MO_32, do_vbitclr)
+TRANS(vbitclr_d, gvec_vvv, MO_64, do_vbitclr)
+
+static void do_vbiti(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm,
+ void (*func)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec))
+{
+ int lsh;
+ TCGv_vec t1, one;
+
+ lsh = imm & ((8 << vece) -1);
+ t1 = tcg_temp_new_vec_matching(t);
+ one = tcg_constant_vec_matching(t, vece, 1);
+
+ tcg_gen_shli_vec(vece, t1, one, lsh);
+ func(vece, t, a, t1);
+}
+
+static void gen_vbitclri(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+ do_vbiti(vece, t, a, imm, tcg_gen_andc_vec);
+}
+
+static void gen_vbitseti(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+ do_vbiti(vece, t, a, imm, tcg_gen_or_vec);
+}
+
+static void gen_vbitrevi(unsigned vece, TCGv_vec t, TCGv_vec a, int64_t imm)
+{
+ do_vbiti(vece, t, a, imm, tcg_gen_xor_vec);
+}
+
+static void do_vbitclri(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shli_vec, INDEX_op_andc_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vbitclri,
+ .fnoi = gen_helper_vbitclri_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitclri,
+ .fnoi = gen_helper_vbitclri_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitclri,
+ .fnoi = gen_helper_vbitclri_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitclri,
+ .fnoi = gen_helper_vbitclri_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitclri_b, gvec_vv_i, MO_8, do_vbitclri)
+TRANS(vbitclri_h, gvec_vv_i, MO_16, do_vbitclri)
+TRANS(vbitclri_w, gvec_vv_i, MO_32, do_vbitclri)
+TRANS(vbitclri_d, gvec_vv_i, MO_64, do_vbitclri)
+
+static void do_vbitset(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shlv_vec, 0
+ };
+ static const GVecGen3 op[4] = {
+ {
+ .fniv = gen_vbitset,
+ .fno = gen_helper_vbitset_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitset,
+ .fno = gen_helper_vbitset_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitset,
+ .fno = gen_helper_vbitset_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitset,
+ .fno = gen_helper_vbitset_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitset_b, gvec_vvv, MO_8, do_vbitset)
+TRANS(vbitset_h, gvec_vvv, MO_16, do_vbitset)
+TRANS(vbitset_w, gvec_vvv, MO_32, do_vbitset)
+TRANS(vbitset_d, gvec_vvv, MO_64, do_vbitset)
+
+static void do_vbitseti(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shli_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vbitseti,
+ .fnoi = gen_helper_vbitseti_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitseti,
+ .fnoi = gen_helper_vbitseti_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitseti,
+ .fnoi = gen_helper_vbitseti_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitseti,
+ .fnoi = gen_helper_vbitseti_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitseti_b, gvec_vv_i, MO_8, do_vbitseti)
+TRANS(vbitseti_h, gvec_vv_i, MO_16, do_vbitseti)
+TRANS(vbitseti_w, gvec_vv_i, MO_32, do_vbitseti)
+TRANS(vbitseti_d, gvec_vv_i, MO_64, do_vbitseti)
+
+static void do_vbitrev(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shlv_vec, 0
+ };
+ static const GVecGen3 op[4] = {
+ {
+ .fniv = gen_vbitrev,
+ .fno = gen_helper_vbitrev_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitrev,
+ .fno = gen_helper_vbitrev_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitrev,
+ .fno = gen_helper_vbitrev_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitrev,
+ .fno = gen_helper_vbitrev_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_3(vd_ofs, vj_ofs, vk_ofs, oprsz, maxsz, &op[vece]);
+}
+
+TRANS(vbitrev_b, gvec_vvv, MO_8, do_vbitrev)
+TRANS(vbitrev_h, gvec_vvv, MO_16, do_vbitrev)
+TRANS(vbitrev_w, gvec_vvv, MO_32, do_vbitrev)
+TRANS(vbitrev_d, gvec_vvv, MO_64, do_vbitrev)
+
+static void do_vbitrevi(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs,
+ int64_t imm, uint32_t oprsz, uint32_t maxsz)
+{
+ static const TCGOpcode vecop_list[] = {
+ INDEX_op_shli_vec, 0
+ };
+ static const GVecGen2i op[4] = {
+ {
+ .fniv = gen_vbitrevi,
+ .fnoi = gen_helper_vbitrevi_b,
+ .opt_opc = vecop_list,
+ .vece = MO_8
+ },
+ {
+ .fniv = gen_vbitrevi,
+ .fnoi = gen_helper_vbitrevi_h,
+ .opt_opc = vecop_list,
+ .vece = MO_16
+ },
+ {
+ .fniv = gen_vbitrevi,
+ .fnoi = gen_helper_vbitrevi_w,
+ .opt_opc = vecop_list,
+ .vece = MO_32
+ },
+ {
+ .fniv = gen_vbitrevi,
+ .fnoi = gen_helper_vbitrevi_d,
+ .opt_opc = vecop_list,
+ .vece = MO_64
+ },
+ };
+
+ tcg_gen_gvec_2i(vd_ofs, vj_ofs, oprsz, maxsz, imm, &op[vece]);
+}
+
+TRANS(vbitrevi_b, gvec_vv_i, MO_8, do_vbitrevi)
+TRANS(vbitrevi_h, gvec_vv_i, MO_16, do_vbitrevi)
+TRANS(vbitrevi_w, gvec_vv_i, MO_32, do_vbitrevi)
+TRANS(vbitrevi_d, gvec_vv_i, MO_64, do_vbitrevi)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index f865e83..801c977 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -973,3 +973,28 @@
vpcnt_h 0111 00101001 11000 01001 ..... ..... @vv
vpcnt_w 0111 00101001 11000 01010 ..... ..... @vv
vpcnt_d 0111 00101001 11000 01011 ..... ..... @vv
+
+vbitclr_b 0111 00010000 11000 ..... ..... ..... @vvv
+vbitclr_h 0111 00010000 11001 ..... ..... ..... @vvv
+vbitclr_w 0111 00010000 11010 ..... ..... ..... @vvv
+vbitclr_d 0111 00010000 11011 ..... ..... ..... @vvv
+vbitclri_b 0111 00110001 00000 01 ... ..... ..... @vv_ui3
+vbitclri_h 0111 00110001 00000 1 .... ..... ..... @vv_ui4
+vbitclri_w 0111 00110001 00001 ..... ..... ..... @vv_ui5
+vbitclri_d 0111 00110001 0001 ...... ..... ..... @vv_ui6
+vbitset_b 0111 00010000 11100 ..... ..... ..... @vvv
+vbitset_h 0111 00010000 11101 ..... ..... ..... @vvv
+vbitset_w 0111 00010000 11110 ..... ..... ..... @vvv
+vbitset_d 0111 00010000 11111 ..... ..... ..... @vvv
+vbitseti_b 0111 00110001 01000 01 ... ..... ..... @vv_ui3
+vbitseti_h 0111 00110001 01000 1 .... ..... ..... @vv_ui4
+vbitseti_w 0111 00110001 01001 ..... ..... ..... @vv_ui5
+vbitseti_d 0111 00110001 0101 ...... ..... ..... @vv_ui6
+vbitrev_b 0111 00010001 00000 ..... ..... ..... @vvv
+vbitrev_h 0111 00010001 00001 ..... ..... ..... @vvv
+vbitrev_w 0111 00010001 00010 ..... ..... ..... @vvv
+vbitrev_d 0111 00010001 00011 ..... ..... ..... @vvv
+vbitrevi_b 0111 00110001 10000 01 ... ..... ..... @vv_ui3
+vbitrevi_h 0111 00110001 10000 1 .... ..... ..... @vv_ui4
+vbitrevi_w 0111 00110001 10001 ..... ..... ..... @vv_ui5
+vbitrevi_d 0111 00110001 1001 ...... ..... ..... @vv_ui6
diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index 9f91a47..14e2df2 100644
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -1964,3 +1964,58 @@
VPCNT(vpcnt_h, 16, UH, ctpop16)
VPCNT(vpcnt_w, 32, UW, ctpop32)
VPCNT(vpcnt_d, 64, UD, ctpop64)
+
+#define DO_BITCLR(a, bit) (a & ~(1ull << bit))
+#define DO_BITSET(a, bit) (a | 1ull << bit)
+#define DO_BITREV(a, bit) (a ^ (1ull << bit))
+
+#define DO_BIT(NAME, BIT, E, DO_OP) \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \
+{ \
+ int i; \
+ VReg *Vd = (VReg *)vd; \
+ VReg *Vj = (VReg *)vj; \
+ VReg *Vk = (VReg *)vk; \
+ \
+ for (i = 0; i < LSX_LEN/BIT; i++) { \
+ Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i)%BIT); \
+ } \
+}
+
+DO_BIT(vbitclr_b, 8, UB, DO_BITCLR)
+DO_BIT(vbitclr_h, 16, UH, DO_BITCLR)
+DO_BIT(vbitclr_w, 32, UW, DO_BITCLR)
+DO_BIT(vbitclr_d, 64, UD, DO_BITCLR)
+DO_BIT(vbitset_b, 8, UB, DO_BITSET)
+DO_BIT(vbitset_h, 16, UH, DO_BITSET)
+DO_BIT(vbitset_w, 32, UW, DO_BITSET)
+DO_BIT(vbitset_d, 64, UD, DO_BITSET)
+DO_BIT(vbitrev_b, 8, UB, DO_BITREV)
+DO_BIT(vbitrev_h, 16, UH, DO_BITREV)
+DO_BIT(vbitrev_w, 32, UW, DO_BITREV)
+DO_BIT(vbitrev_d, 64, UD, DO_BITREV)
+
+#define DO_BITI(NAME, BIT, E, DO_OP) \
+void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
+{ \
+ int i; \
+ VReg *Vd = (VReg *)vd; \
+ VReg *Vj = (VReg *)vj; \
+ \
+ for (i = 0; i < LSX_LEN/BIT; i++) { \
+ Vd->E(i) = DO_OP(Vj->E(i), imm); \
+ } \
+}
+
+DO_BITI(vbitclri_b, 8, UB, DO_BITCLR)
+DO_BITI(vbitclri_h, 16, UH, DO_BITCLR)
+DO_BITI(vbitclri_w, 32, UW, DO_BITCLR)
+DO_BITI(vbitclri_d, 64, UD, DO_BITCLR)
+DO_BITI(vbitseti_b, 8, UB, DO_BITSET)
+DO_BITI(vbitseti_h, 16, UH, DO_BITSET)
+DO_BITI(vbitseti_w, 32, UW, DO_BITSET)
+DO_BITI(vbitseti_d, 64, UD, DO_BITSET)
+DO_BITI(vbitrevi_b, 8, UB, DO_BITREV)
+DO_BITI(vbitrevi_h, 16, UH, DO_BITREV)
+DO_BITI(vbitrevi_w, 32, UW, DO_BITREV)
+DO_BITI(vbitrevi_d, 64, UD, DO_BITREV)
