target/loongarch: Implement xvmskltz/xvmskgez/xvmsknz

This patch includes:
- XVMSKLTZ.{B/H/W/D};
- XVMSKGEZ.B;
- XVMSKNZ.B.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-33-gaosong@loongson.cn>

4 files changed, 74 insertions, 24 deletions

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 1f01ec9..0571009 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -2015,6 +2015,13 @@ INSN_LASX(xvsigncov_h,       vvv)
 INSN_LASX(xvsigncov_w,       vvv)
 INSN_LASX(xvsigncov_d,       vvv)
 
+INSN_LASX(xvmskltz_b,        vv)
+INSN_LASX(xvmskltz_h,        vv)
+INSN_LASX(xvmskltz_w,        vv)
+INSN_LASX(xvmskltz_d,        vv)
+INSN_LASX(xvmskgez_b,        vv)
+INSN_LASX(xvmsknz_b,         vv)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)
diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch/insn_trans/trans_vec.c.inc
index 492bbcd..843ec6d 100644
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -3423,6 +3423,12 @@ TRANS(vmskltz_w, LSX, gen_vv, gen_helper_vmskltz_w)
 TRANS(vmskltz_d, LSX, gen_vv, gen_helper_vmskltz_d)
 TRANS(vmskgez_b, LSX, gen_vv, gen_helper_vmskgez_b)
 TRANS(vmsknz_b, LSX, gen_vv, gen_helper_vmsknz_b)
+TRANS(xvmskltz_b, LASX, gen_xx, gen_helper_vmskltz_b)
+TRANS(xvmskltz_h, LASX, gen_xx, gen_helper_vmskltz_h)
+TRANS(xvmskltz_w, LASX, gen_xx, gen_helper_vmskltz_w)
+TRANS(xvmskltz_d, LASX, gen_xx, gen_helper_vmskltz_d)
+TRANS(xvmskgez_b, LASX, gen_xx, gen_helper_vmskgez_b)
+TRANS(xvmsknz_b, LASX, gen_xx, gen_helper_vmsknz_b)
 
 #define EXPAND_BYTE(bit)  ((uint64_t)(bit ? 0xff : 0))
 
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 7bbda1a..6a161d6 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1598,6 +1598,13 @@ xvsigncov_h      0111 01010010 11101 ..... ..... .....    @vvv
 xvsigncov_w      0111 01010010 11110 ..... ..... .....    @vvv
 xvsigncov_d      0111 01010010 11111 ..... ..... .....    @vvv
 
+xvmskltz_b       0111 01101001 11000 10000 ..... .....    @vv
+xvmskltz_h       0111 01101001 11000 10001 ..... .....    @vv
+xvmskltz_w       0111 01101001 11000 10010 ..... .....    @vv
+xvmskltz_d       0111 01101001 11000 10011 ..... .....    @vv
+xvmskgez_b       0111 01101001 11000 10100 ..... .....    @vv
+xvmsknz_b        0111 01101001 11000 11000 ..... .....    @vv
+
 xvreplgr2vr_b    0111 01101001 11110 00000 ..... .....    @vr
 xvreplgr2vr_h    0111 01101001 11110 00001 ..... .....    @vr
 xvreplgr2vr_w    0111 01101001 11110 00010 ..... .....    @vr
diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index 3dc2024..f749800 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -810,14 +810,19 @@ static uint64_t do_vmskltz_b(int64_t val)
 
 void HELPER(vmskltz_b)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    temp = do_vmskltz_b(Vj->D(0));
-    temp |= (do_vmskltz_b(Vj->D(1)) << 8);
-    Vd->D(0) = temp;
-    Vd->D(1) = 0;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp = do_vmskltz_b(Vj->D(2 * i));
+        temp |= (do_vmskltz_b(Vj->D(2 * i  + 1)) << 8);
+        Vd->D(2 * i) = temp;
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 static uint64_t do_vmskltz_h(int64_t val)
@@ -831,14 +836,19 @@ static uint64_t do_vmskltz_h(int64_t val)
 
 void HELPER(vmskltz_h)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    temp = do_vmskltz_h(Vj->D(0));
-    temp |= (do_vmskltz_h(Vj->D(1)) << 4);
-    Vd->D(0) = temp;
-    Vd->D(1) = 0;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp = do_vmskltz_h(Vj->D(2 * i));
+        temp |= (do_vmskltz_h(Vj->D(2 * i + 1)) << 4);
+        Vd->D(2 * i) = temp;
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 static uint64_t do_vmskltz_w(int64_t val)
@@ -851,14 +861,19 @@ static uint64_t do_vmskltz_w(int64_t val)
 
 void HELPER(vmskltz_w)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    temp = do_vmskltz_w(Vj->D(0));
-    temp |= (do_vmskltz_w(Vj->D(1)) << 2);
-    Vd->D(0) = temp;
-    Vd->D(1) = 0;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp = do_vmskltz_w(Vj->D(2 * i));
+        temp |= (do_vmskltz_w(Vj->D(2 * i + 1)) << 2);
+        Vd->D(2 * i) = temp;
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 static uint64_t do_vmskltz_d(int64_t val)
@@ -867,26 +882,36 @@ static uint64_t do_vmskltz_d(int64_t val)
 }
 void HELPER(vmskltz_d)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    temp = do_vmskltz_d(Vj->D(0));
-    temp |= (do_vmskltz_d(Vj->D(1)) << 1);
-    Vd->D(0) = temp;
-    Vd->D(1) = 0;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp = do_vmskltz_d(Vj->D(2 * i));
+        temp |= (do_vmskltz_d(Vj->D(2 * i + 1)) << 1);
+        Vd->D(2 * i) = temp;
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 void HELPER(vmskgez_b)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    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;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp =  do_vmskltz_b(Vj->D(2 * i));
+        temp |= (do_vmskltz_b(Vj->D(2 * i + 1)) << 8);
+        Vd->D(2 * i) = (uint16_t)(~temp);
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 static uint64_t do_vmskez_b(uint64_t a)
@@ -901,14 +926,19 @@ static uint64_t do_vmskez_b(uint64_t a)
 
 void HELPER(vmsknz_b)(void *vd, void *vj, uint32_t desc)
 {
+    int i;
     uint16_t temp = 0;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
+    int oprsz = simd_oprsz(desc);
 
-    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;
+    for (i = 0; i < oprsz / 16; i++) {
+        temp = 0;
+        temp = do_vmskez_b(Vj->D(2 * i));
+        temp |= (do_vmskez_b(Vj->D(2 * i + 1)) << 8);
+        Vd->D(2 * i) = (uint16_t)(~temp);
+        Vd->D(2 * i + 1) = 0;
+    }
 }
 
 void HELPER(vnori_b)(void *vd, void *vj, uint64_t imm, uint32_t v)