target/loongarch: Implement vclo vclz

This patch includes:
- VCLO.{B/H/W/D};
- VCLZ.{B/H/W/D}.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-30-gaosong@loongson.cn>

target/loongarch/disas.c

@@ -1258,3 +1258,12 @@ INSN_LSX(vssrarni_bu_h,    vv_i)
 INSN_LSX(vssrarni_hu_w,    vv_i)
 INSN_LSX(vssrarni_wu_d,    vv_i)
 INSN_LSX(vssrarni_du_q,    vv_i)
+
+INSN_LSX(vclo_b,           vv)
+INSN_LSX(vclo_h,           vv)
+INSN_LSX(vclo_w,           vv)
+INSN_LSX(vclo_d,           vv)
+INSN_LSX(vclz_b,           vv)
+INSN_LSX(vclz_h,           vv)
+INSN_LSX(vclz_w,           vv)
+INSN_LSX(vclz_d,           vv)

target/loongarch/helper.h

@@ -471,3 +471,12 @@ DEF_HELPER_4(vssrarni_bu_h, void, env, i32, i32, i32)
 DEF_HELPER_4(vssrarni_hu_w, void, env, i32, i32, i32)
 DEF_HELPER_4(vssrarni_wu_d, void, env, i32, i32, i32)
 DEF_HELPER_4(vssrarni_du_q, void, env, i32, i32, i32)
+
+DEF_HELPER_3(vclo_b, void, env, i32, i32)
+DEF_HELPER_3(vclo_h, void, env, i32, i32)
+DEF_HELPER_3(vclo_w, void, env, i32, i32)
+DEF_HELPER_3(vclo_d, void, env, i32, i32)
+DEF_HELPER_3(vclz_b, void, env, i32, i32)
+DEF_HELPER_3(vclz_h, void, env, i32, i32)
+DEF_HELPER_3(vclz_w, void, env, i32, i32)
+DEF_HELPER_3(vclz_d, void, env, i32, i32)

target/loongarch/insn_trans/trans_lsx.c.inc

@@ -3097,3 +3097,12 @@ TRANS(vssrarni_bu_h, gen_vv_i, gen_helper_vssrarni_bu_h)
 TRANS(vssrarni_hu_w, gen_vv_i, gen_helper_vssrarni_hu_w)
 TRANS(vssrarni_wu_d, gen_vv_i, gen_helper_vssrarni_wu_d)
 TRANS(vssrarni_du_q, gen_vv_i, gen_helper_vssrarni_du_q)
+
+TRANS(vclo_b, gen_vv, gen_helper_vclo_b)
+TRANS(vclo_h, gen_vv, gen_helper_vclo_h)
+TRANS(vclo_w, gen_vv, gen_helper_vclo_w)
+TRANS(vclo_d, gen_vv, gen_helper_vclo_d)
+TRANS(vclz_b, gen_vv, gen_helper_vclz_b)
+TRANS(vclz_h, gen_vv, gen_helper_vclz_h)
+TRANS(vclz_w, gen_vv, gen_helper_vclz_w)
+TRANS(vclz_d, gen_vv, gen_helper_vclz_d)

target/loongarch/insns.decode

@@ -959,3 +959,12 @@ vssrarni_bu_h    0111 00110110 11000 1 .... ..... .....   @vv_ui4
 vssrarni_hu_w    0111 00110110 11001 ..... ..... .....    @vv_ui5
 vssrarni_wu_d    0111 00110110 1101 ...... ..... .....    @vv_ui6
 vssrarni_du_q    0111 00110110 111 ....... ..... .....    @vv_ui7
+
+vclo_b           0111 00101001 11000 00000 ..... .....    @vv
+vclo_h           0111 00101001 11000 00001 ..... .....    @vv
+vclo_w           0111 00101001 11000 00010 ..... .....    @vv
+vclo_d           0111 00101001 11000 00011 ..... .....    @vv
+vclz_b           0111 00101001 11000 00100 ..... .....    @vv
+vclz_h           0111 00101001 11000 00101 ..... .....    @vv
+vclz_w           0111 00101001 11000 00110 ..... .....    @vv
+vclz_d           0111 00101001 11000 00111 ..... .....    @vv

target/loongarch/lsx_helper.c

@@ -1915,3 +1915,34 @@ void HELPER(vssrarni_du_q)(CPULoongArchState *env,
 VSSRARNUI(vssrarni_bu_h, 16, B, H)
 VSSRARNUI(vssrarni_hu_w, 32, H, W)
 VSSRARNUI(vssrarni_wu_d, 64, W, D)
+
+#define DO_2OP(NAME, BIT, E, DO_OP)                                 \
+void HELPER(NAME)(CPULoongArchState *env, uint32_t vd, uint32_t vj) \
+{                                                                   \
+    int i;                                                          \
+    VReg *Vd = &(env->fpr[vd].vreg);                                \
+    VReg *Vj = &(env->fpr[vj].vreg);                                \
+                                                                    \
+    for (i = 0; i < LSX_LEN/BIT; i++)                               \
+    {                                                               \
+        Vd->E(i) = DO_OP(Vj->E(i));                                 \
+    }                                                               \
+}
+
+#define DO_CLO_B(N)  (clz32(~N & 0xff) - 24)
+#define DO_CLO_H(N)  (clz32(~N & 0xffff) - 16)
+#define DO_CLO_W(N)  (clz32(~N))
+#define DO_CLO_D(N)  (clz64(~N))
+#define DO_CLZ_B(N)  (clz32(N) - 24)
+#define DO_CLZ_H(N)  (clz32(N) - 16)
+#define DO_CLZ_W(N)  (clz32(N))
+#define DO_CLZ_D(N)  (clz64(N))
+
+DO_2OP(vclo_b, 8, UB, DO_CLO_B)
+DO_2OP(vclo_h, 16, UH, DO_CLO_H)
+DO_2OP(vclo_w, 32, UW, DO_CLO_W)
+DO_2OP(vclo_d, 64, UD, DO_CLO_D)
+DO_2OP(vclz_b, 8, UB, DO_CLZ_B)
+DO_2OP(vclz_h, 16, UH, DO_CLZ_H)
+DO_2OP(vclz_w, 32, UW, DO_CLZ_W)
+DO_2OP(vclz_d, 64, UD, DO_CLZ_D)