target/loongarch: Implement xvaddw/xvsubw

This patch includes:
- XVADDW{EV/OD}.{H.B/W.H/D.W/Q.D}[U];
- XVSUBW{EV/OD}.{H.B/W.H/D.W/Q.D}[U];
- XVADDW{EV/OD}.{H.BU.B/W.HU.H/D.WU.W/Q.DU.D}.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-21-gaosong@loongson.cn>

1 files changed, 86 insertions, 34 deletions

diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index 2ce0ca41a7..fc3b07e8d2 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -106,133 +106,173 @@ void HELPER(vhsubw_qu_du)(void *vd, void *vj, void *vk, uint32_t desc)
 }
 
 #define DO_EVEN(NAME, BIT, E1, E2, DO_OP)                        \
-void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)      \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc)   \
 {                                                                \
     int i;                                                       \
     VReg *Vd = (VReg *)vd;                                       \
     VReg *Vj = (VReg *)vj;                                       \
     VReg *Vk = (VReg *)vk;                                       \
     typedef __typeof(Vd->E1(0)) TD;                              \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                          \
+    int oprsz = simd_oprsz(desc);                                \
+                                                                 \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {                    \
         Vd->E1(i) = DO_OP((TD)Vj->E2(2 * i) ,(TD)Vk->E2(2 * i)); \
     }                                                            \
 }
 
 #define DO_ODD(NAME, BIT, E1, E2, DO_OP)                                 \
-void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)              \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc)           \
 {                                                                        \
     int i;                                                               \
     VReg *Vd = (VReg *)vd;                                               \
     VReg *Vj = (VReg *)vj;                                               \
     VReg *Vk = (VReg *)vk;                                               \
     typedef __typeof(Vd->E1(0)) TD;                                      \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                                  \
+    int oprsz = simd_oprsz(desc);                                        \
+                                                                         \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {                            \
         Vd->E1(i) = DO_OP((TD)Vj->E2(2 * i + 1), (TD)Vk->E2(2 * i + 1)); \
     }                                                                    \
 }
 
-void HELPER(vaddwev_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwev_q_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_makes64(Vj->D(0)), int128_makes64(Vk->D(0)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_makes64(Vj->D(2 * i)),
+                              int128_makes64(Vk->D(2 * i)));
+    }
 }
 
 DO_EVEN(vaddwev_h_b, 16, H, B, DO_ADD)
 DO_EVEN(vaddwev_w_h, 32, W, H, DO_ADD)
 DO_EVEN(vaddwev_d_w, 64, D, W, DO_ADD)
 
-void HELPER(vaddwod_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwod_q_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(1)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_makes64(Vj->D(2 * i +1)),
+                              int128_makes64(Vk->D(2 * i +1)));
+    }
 }
 
 DO_ODD(vaddwod_h_b, 16, H, B, DO_ADD)
 DO_ODD(vaddwod_w_h, 32, W, H, DO_ADD)
 DO_ODD(vaddwod_d_w, 64, D, W, DO_ADD)
 
-void HELPER(vsubwev_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vsubwev_q_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_sub(int128_makes64(Vj->D(0)), int128_makes64(Vk->D(0)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_sub(int128_makes64(Vj->D(2 * i)),
+                              int128_makes64(Vk->D(2 * i)));
+    }
 }
 
 DO_EVEN(vsubwev_h_b, 16, H, B, DO_SUB)
 DO_EVEN(vsubwev_w_h, 32, W, H, DO_SUB)
 DO_EVEN(vsubwev_d_w, 64, D, W, DO_SUB)
 
-void HELPER(vsubwod_q_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vsubwod_q_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_sub(int128_makes64(Vj->D(1)), int128_makes64(Vk->D(1)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_sub(int128_makes64(Vj->D(2 * i + 1)),
+                              int128_makes64(Vk->D(2 * i + 1)));
+    }
 }
 
 DO_ODD(vsubwod_h_b, 16, H, B, DO_SUB)
 DO_ODD(vsubwod_w_h, 32, W, H, DO_SUB)
 DO_ODD(vsubwod_d_w, 64, D, W, DO_SUB)
 
-void HELPER(vaddwev_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwev_q_du)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(0)),
-                          int128_make64((uint64_t)Vk->D(0)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_make64(Vj->UD(2 * i)),
+                              int128_make64(Vk->UD(2 * i)));
+    }
 }
 
 DO_EVEN(vaddwev_h_bu, 16, UH, UB, DO_ADD)
 DO_EVEN(vaddwev_w_hu, 32, UW, UH, DO_ADD)
 DO_EVEN(vaddwev_d_wu, 64, UD, UW, DO_ADD)
 
-void HELPER(vaddwod_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwod_q_du)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(1)),
-                          int128_make64((uint64_t)Vk->D(1)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_make64(Vj->UD(2 * i + 1)),
+                              int128_make64(Vk->UD(2 * i + 1)));
+    }
 }
 
 DO_ODD(vaddwod_h_bu, 16, UH, UB, DO_ADD)
 DO_ODD(vaddwod_w_hu, 32, UW, UH, DO_ADD)
 DO_ODD(vaddwod_d_wu, 64, UD, UW, DO_ADD)
 
-void HELPER(vsubwev_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vsubwev_q_du)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_sub(int128_make64((uint64_t)Vj->D(0)),
-                          int128_make64((uint64_t)Vk->D(0)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_sub(int128_make64(Vj->UD(2 * i)),
+                              int128_make64(Vk->UD(2 * i)));
+    }
 }
 
 DO_EVEN(vsubwev_h_bu, 16, UH, UB, DO_SUB)
 DO_EVEN(vsubwev_w_hu, 32, UW, UH, DO_SUB)
 DO_EVEN(vsubwev_d_wu, 64, UD, UW, DO_SUB)
 
-void HELPER(vsubwod_q_du)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vsubwod_q_du)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_sub(int128_make64((uint64_t)Vj->D(1)),
-                          int128_make64((uint64_t)Vk->D(1)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_sub(int128_make64(Vj->UD(2 * i + 1)),
+                              int128_make64(Vk->UD(2 * i + 1)));
+    }
 }
 
 DO_ODD(vsubwod_h_bu, 16, UH, UB, DO_SUB)
@@ -240,7 +280,7 @@ DO_ODD(vsubwod_w_hu, 32, UW, UH, DO_SUB)
 DO_ODD(vsubwod_d_wu, 64, UD, UW, DO_SUB)
 
 #define DO_EVEN_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)             \
-void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)           \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc)        \
 {                                                                     \
     int i;                                                            \
     VReg *Vd = (VReg *)vd;                                            \
@@ -248,13 +288,15 @@ void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)           \
     VReg *Vk = (VReg *)vk;                                            \
     typedef __typeof(Vd->ES1(0)) TDS;                                 \
     typedef __typeof(Vd->EU1(0)) TDU;                                 \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                               \
+    int oprsz = simd_oprsz(desc);                                     \
+                                                                      \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {                         \
         Vd->ES1(i) = DO_OP((TDU)Vj->EU2(2 * i) ,(TDS)Vk->ES2(2 * i)); \
     }                                                                 \
 }
 
 #define DO_ODD_U_S(NAME, BIT, ES1, EU1, ES2, EU2, DO_OP)                      \
-void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)                   \
+void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc)                \
 {                                                                             \
     int i;                                                                    \
     VReg *Vd = (VReg *)vd;                                                    \
@@ -262,33 +304,43 @@ void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v)                   \
     VReg *Vk = (VReg *)vk;                                                    \
     typedef __typeof(Vd->ES1(0)) TDS;                                         \
     typedef __typeof(Vd->EU1(0)) TDU;                                         \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                                       \
+    int oprsz = simd_oprsz(desc);                                             \
+                                                                              \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {                                 \
         Vd->ES1(i) = DO_OP((TDU)Vj->EU2(2 * i + 1), (TDS)Vk->ES2(2 * i + 1)); \
     }                                                                         \
 }
 
-void HELPER(vaddwev_q_du_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwev_q_du_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(0)),
-                          int128_makes64(Vk->D(0)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_make64(Vj->UD(2 * i)),
+                              int128_makes64(Vk->D(2 * i)));
+    }
 }
 
 DO_EVEN_U_S(vaddwev_h_bu_b, 16, H, UH, B, UB, DO_ADD)
 DO_EVEN_U_S(vaddwev_w_hu_h, 32, W, UW, H, UH, DO_ADD)
 DO_EVEN_U_S(vaddwev_d_wu_w, 64, D, UD, W, UW, DO_ADD)
 
-void HELPER(vaddwod_q_du_d)(void *vd, void *vj, void *vk, uint32_t v)
+void HELPER(vaddwod_q_du_d)(void *vd, void *vj, void *vk, uint32_t desc)
 {
+    int i;
     VReg *Vd = (VReg *)vd;
     VReg *Vj = (VReg *)vj;
     VReg *Vk = (VReg *)vk;
+    int oprsz = simd_oprsz(desc);
 
-    Vd->Q(0) = int128_add(int128_make64((uint64_t)Vj->D(1)),
-                          int128_makes64(Vk->D(1)));
+    for (i = 0; i < oprsz / 16; i++) {
+        Vd->Q(i) = int128_add(int128_make64(Vj->UD(2 * i + 1)),
+                              int128_makes64(Vk->D(2 * i + 1)));
+    }
 }
 
 DO_ODD_U_S(vaddwod_h_bu_b, 16, H, UH, B, UB, DO_ADD)