target/loongarch: Implement vext2xv

This patch includes:
- VEXT2XV.{H/W/D}.B, VEXT2XV.{HU/WU/DU}.BU;
- VEXT2XV.{W/D}.B, VEXT2XV.{WU/DU}.HU;
- VEXT2XV.D.W, VEXT2XV.DU.WU.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-31-gaosong@loongson.cn>

target/loongarch/disas.c

@@ -1997,6 +1997,19 @@ INSN_LASX(xvexth_wu_hu,      vv)
 INSN_LASX(xvexth_du_wu,      vv)
 INSN_LASX(xvexth_qu_du,      vv)
 
+INSN_LASX(vext2xv_h_b,       vv)
+INSN_LASX(vext2xv_w_b,       vv)
+INSN_LASX(vext2xv_d_b,       vv)
+INSN_LASX(vext2xv_w_h,       vv)
+INSN_LASX(vext2xv_d_h,       vv)
+INSN_LASX(vext2xv_d_w,       vv)
+INSN_LASX(vext2xv_hu_bu,     vv)
+INSN_LASX(vext2xv_wu_bu,     vv)
+INSN_LASX(vext2xv_du_bu,     vv)
+INSN_LASX(vext2xv_wu_hu,     vv)
+INSN_LASX(vext2xv_du_hu,     vv)
+INSN_LASX(vext2xv_du_wu,     vv)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)

target/loongarch/helper.h

@@ -340,6 +340,19 @@ DEF_HELPER_FLAGS_3(vexth_wu_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(vexth_du_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(vexth_qu_du, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_3(vext2xv_h_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_w_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_d_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_d_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_d_w, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_hu_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_wu_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_du_bu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_wu_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_du_hu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(vext2xv_du_wu, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
 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)

target/loongarch/insn_trans/trans_vec.c.inc

@@ -3347,6 +3347,19 @@ TRANS(xvexth_wu_hu, LASX, gen_xx, gen_helper_vexth_wu_hu)
 TRANS(xvexth_du_wu, LASX, gen_xx, gen_helper_vexth_du_wu)
 TRANS(xvexth_qu_du, LASX, gen_xx, gen_helper_vexth_qu_du)
 
+TRANS(vext2xv_h_b, LASX, gen_xx, gen_helper_vext2xv_h_b)
+TRANS(vext2xv_w_b, LASX, gen_xx, gen_helper_vext2xv_w_b)
+TRANS(vext2xv_d_b, LASX, gen_xx, gen_helper_vext2xv_d_b)
+TRANS(vext2xv_w_h, LASX, gen_xx, gen_helper_vext2xv_w_h)
+TRANS(vext2xv_d_h, LASX, gen_xx, gen_helper_vext2xv_d_h)
+TRANS(vext2xv_d_w, LASX, gen_xx, gen_helper_vext2xv_d_w)
+TRANS(vext2xv_hu_bu, LASX, gen_xx, gen_helper_vext2xv_hu_bu)
+TRANS(vext2xv_wu_bu, LASX, gen_xx, gen_helper_vext2xv_wu_bu)
+TRANS(vext2xv_du_bu, LASX, gen_xx, gen_helper_vext2xv_du_bu)
+TRANS(vext2xv_wu_hu, LASX, gen_xx, gen_helper_vext2xv_wu_hu)
+TRANS(vext2xv_du_hu, LASX, gen_xx, gen_helper_vext2xv_du_hu)
+TRANS(vext2xv_du_wu, LASX, gen_xx, gen_helper_vext2xv_du_wu)
+
 static void gen_vsigncov(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b)
 {
     TCGv_vec t1, zero;

target/loongarch/insns.decode

@@ -1580,6 +1580,19 @@ xvexth_wu_hu     0111 01101001 11101 11101 ..... .....    @vv
 xvexth_du_wu     0111 01101001 11101 11110 ..... .....    @vv
 xvexth_qu_du     0111 01101001 11101 11111 ..... .....    @vv
 
+vext2xv_h_b      0111 01101001 11110 00100 ..... .....    @vv
+vext2xv_w_b      0111 01101001 11110 00101 ..... .....    @vv
+vext2xv_d_b      0111 01101001 11110 00110 ..... .....    @vv
+vext2xv_w_h      0111 01101001 11110 00111 ..... .....    @vv
+vext2xv_d_h      0111 01101001 11110 01000 ..... .....    @vv
+vext2xv_d_w      0111 01101001 11110 01001 ..... .....    @vv
+vext2xv_hu_bu    0111 01101001 11110 01010 ..... .....    @vv
+vext2xv_wu_bu    0111 01101001 11110 01011 ..... .....    @vv
+vext2xv_du_bu    0111 01101001 11110 01100 ..... .....    @vv
+vext2xv_wu_hu    0111 01101001 11110 01101 ..... .....    @vv
+vext2xv_du_hu    0111 01101001 11110 01110 ..... .....    @vv
+vext2xv_du_wu    0111 01101001 11110 01111 ..... .....    @vv
+
 xvreplgr2vr_b    0111 01101001 11110 00000 ..... .....    @vr
 xvreplgr2vr_h    0111 01101001 11110 00001 ..... .....    @vr
 xvreplgr2vr_w    0111 01101001 11110 00010 ..... .....    @vr

target/loongarch/vec_helper.c

@@ -763,6 +763,34 @@ VEXTH(vexth_hu_bu, 16, UH, UB)
 VEXTH(vexth_wu_hu, 32, UW, UH)
 VEXTH(vexth_du_wu, 64, UD, UW)
 
+#define VEXT2XV(NAME, BIT, E1, E2)                   \
+void HELPER(NAME)(void *vd, void *vj, uint32_t desc) \
+{                                                    \
+    int i;                                           \
+    VReg temp = {};                                  \
+    VReg *Vd = (VReg *)vd;                           \
+    VReg *Vj = (VReg *)vj;                           \
+    int oprsz = simd_oprsz(desc);                    \
+                                                     \
+    for (i = 0; i < oprsz / (BIT / 8); i++) {        \
+        temp.E1(i) = Vj->E2(i);                      \
+    }                                                \
+    *Vd = temp;                                      \
+}
+
+VEXT2XV(vext2xv_h_b, 16, H, B)
+VEXT2XV(vext2xv_w_b, 32, W, B)
+VEXT2XV(vext2xv_d_b, 64, D, B)
+VEXT2XV(vext2xv_w_h, 32, W, H)
+VEXT2XV(vext2xv_d_h, 64, D, H)
+VEXT2XV(vext2xv_d_w, 64, D, W)
+VEXT2XV(vext2xv_hu_bu, 16, UH, UB)
+VEXT2XV(vext2xv_wu_bu, 32, UW, UB)
+VEXT2XV(vext2xv_du_bu, 64, UD, UB)
+VEXT2XV(vext2xv_wu_hu, 32, UW, UH)
+VEXT2XV(vext2xv_du_hu, 64, UD, UH)
+VEXT2XV(vext2xv_du_wu, 64, UD, UW)
+
 #define DO_SIGNCOV(a, b)  (a == 0 ? 0 : a < 0 ? -b : b)
 
 DO_3OP(vsigncov_b, 8, B, DO_SIGNCOV)