target/loongarch: Implement vmskltz/vmskgez/vmsknz

This patch includes:
- VMSKLTZ.{B/H/W/D};
- VMSKGEZ.B;
- VMSKNZ.B.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-21-gaosong@loongson.cn>

5 files changed, 141 insertions, 0 deletions

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 46e808c..2725b82 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1084,3 +1084,10 @@ INSN_LSX(vsigncov_b,       vvv)
 INSN_LSX(vsigncov_h,       vvv)
 INSN_LSX(vsigncov_w,       vvv)
 INSN_LSX(vsigncov_d,       vvv)
+
+INSN_LSX(vmskltz_b,        vv)
+INSN_LSX(vmskltz_h,        vv)
+INSN_LSX(vmskltz_w,        vv)
+INSN_LSX(vmskltz_d,        vv)
+INSN_LSX(vmskgez_b,        vv)
+INSN_LSX(vmsknz_b,         vv)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index e1e5d58..34b7b2f 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -343,3 +343,10 @@ DEF_HELPER_FLAGS_4(vsigncov_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vsigncov_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vsigncov_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(vsigncov_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_3(vmskltz_b, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_h, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_w, void, env, i32, i32)
+DEF_HELPER_3(vmskltz_d, void, env, i32, i32)
+DEF_HELPER_3(vmskgez_b, void, env, i32, i32)
+DEF_HELPER_3(vmsknz_b, void, env, i32,i32)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc b/target/loongarch/insn_trans/trans_lsx.c.inc
index 644917a..64387f2 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -2867,3 +2867,10 @@ TRANS(vsigncov_b, gvec_vvv, MO_8, do_vsigncov)
 TRANS(vsigncov_h, gvec_vvv, MO_16, do_vsigncov)
 TRANS(vsigncov_w, gvec_vvv, MO_32, do_vsigncov)
 TRANS(vsigncov_d, gvec_vvv, MO_64, do_vsigncov)
+
+TRANS(vmskltz_b, gen_vv, gen_helper_vmskltz_b)
+TRANS(vmskltz_h, gen_vv, gen_helper_vmskltz_h)
+TRANS(vmskltz_w, gen_vv, gen_helper_vmskltz_w)
+TRANS(vmskltz_d, gen_vv, gen_helper_vmskltz_d)
+TRANS(vmskgez_b, gen_vv, gen_helper_vmskgez_b)
+TRANS(vmsknz_b, gen_vv, gen_helper_vmsknz_b)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 4233dd7..47c1ef7 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -783,3 +783,10 @@ vsigncov_b       0111 00010010 11100 ..... ..... .....    @vvv
 vsigncov_h       0111 00010010 11101 ..... ..... .....    @vvv
 vsigncov_w       0111 00010010 11110 ..... ..... .....    @vvv
 vsigncov_d       0111 00010010 11111 ..... ..... .....    @vvv
+
+vmskltz_b        0111 00101001 11000 10000 ..... .....    @vv
+vmskltz_h        0111 00101001 11000 10001 ..... .....    @vv
+vmskltz_w        0111 00101001 11000 10010 ..... .....    @vv
+vmskltz_d        0111 00101001 11000 10011 ..... .....    @vv
+vmskgez_b        0111 00101001 11000 10100 ..... .....    @vv
+vmsknz_b         0111 00101001 11000 11000 ..... .....    @vv
diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index 408815e..2359c63 100644
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -669,3 +669,116 @@ DO_3OP(vsigncov_b, 8, B, DO_SIGNCOV)
 DO_3OP(vsigncov_h, 16, H, DO_SIGNCOV)
 DO_3OP(vsigncov_w, 32, W, DO_SIGNCOV)
 DO_3OP(vsigncov_d, 64, D, DO_SIGNCOV)
+
+static uint64_t do_vmskltz_b(int64_t val)
+{
+    uint64_t m = 0x8080808080808080ULL;
+    uint64_t c =  val & m;
+    c |= c << 7;
+    c |= c << 14;
+    c |= c << 28;
+    return c >> 56;
+}
+
+void HELPER(vmskltz_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_b(Vj->D(0));
+    temp |= (do_vmskltz_b(Vj->D(1)) << 8);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_h(int64_t val)
+{
+    uint64_t m = 0x8000800080008000ULL;
+    uint64_t c =  val & m;
+    c |= c << 15;
+    c |= c << 30;
+    return c >> 60;
+}
+
+void HELPER(vmskltz_h)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_h(Vj->D(0));
+    temp |= (do_vmskltz_h(Vj->D(1)) << 4);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_w(int64_t val)
+{
+    uint64_t m = 0x8000000080000000ULL;
+    uint64_t c =  val & m;
+    c |= c << 31;
+    return c >> 62;
+}
+
+void HELPER(vmskltz_w)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_w(Vj->D(0));
+    temp |= (do_vmskltz_w(Vj->D(1)) << 2);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskltz_d(int64_t val)
+{
+    return (uint64_t)val >> 63;
+}
+void HELPER(vmskltz_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskltz_d(Vj->D(0));
+    temp |= (do_vmskltz_d(Vj->D(1)) << 1);
+    Vd->D(0) = temp;
+    Vd->D(1) = 0;
+}
+
+void HELPER(vmskgez_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp =  do_vmskltz_b(Vj->D(0));
+    temp |= (do_vmskltz_b(Vj->D(1)) << 8);
+    Vd->D(0) = (uint16_t)(~temp);
+    Vd->D(1) = 0;
+}
+
+static uint64_t do_vmskez_b(uint64_t a)
+{
+    uint64_t m = 0x7f7f7f7f7f7f7f7fULL;
+    uint64_t c = ~(((a & m) + m) | a | m);
+    c |= c << 7;
+    c |= c << 14;
+    c |= c << 28;
+    return c >> 56;
+}
+
+void HELPER(vmsknz_b)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    uint16_t temp = 0;
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    temp = do_vmskez_b(Vj->D(0));
+    temp |= (do_vmskez_b(Vj->D(1)) << 8);
+    Vd->D(0) = (uint16_t)(~temp);
+    Vd->D(1) = 0;
+}