target/loongarch: Implement vdiv/vmod
This patch includes:
- VDIV.{B/H/W/D}[U];
- VMOD.{B/H/W/D}[U].
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-17-gaosong@loongson.cn>
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 980e6e6..6e4f676 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1044,3 +1044,20 @@
INSN_LSX(vmaddwod_w_hu_h, vvv)
INSN_LSX(vmaddwod_d_wu_w, vvv)
INSN_LSX(vmaddwod_q_du_d, vvv)
+
+INSN_LSX(vdiv_b, vvv)
+INSN_LSX(vdiv_h, vvv)
+INSN_LSX(vdiv_w, vvv)
+INSN_LSX(vdiv_d, vvv)
+INSN_LSX(vdiv_bu, vvv)
+INSN_LSX(vdiv_hu, vvv)
+INSN_LSX(vdiv_wu, vvv)
+INSN_LSX(vdiv_du, vvv)
+INSN_LSX(vmod_b, vvv)
+INSN_LSX(vmod_h, vvv)
+INSN_LSX(vmod_w, vvv)
+INSN_LSX(vmod_d, vvv)
+INSN_LSX(vmod_bu, vvv)
+INSN_LSX(vmod_hu, vvv)
+INSN_LSX(vmod_wu, vvv)
+INSN_LSX(vmod_du, vvv)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index 8cf9620..7b7c685 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -303,3 +303,20 @@
DEF_HELPER_FLAGS_4(vmaddwod_h_bu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(vmaddwod_w_hu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(vmaddwod_d_wu_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_4(vdiv_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vdiv_du, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_d, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_wu, void, env, i32, i32, i32)
+DEF_HELPER_4(vmod_du, void, env, i32, i32, i32)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc b/target/loongarch/insn_trans/trans_lsx.c.inc
index 400c3a0..b295a9c 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -2676,3 +2676,20 @@
TRANS(vmaddwod_h_bu_b, gvec_vvv, MO_8, do_vmaddwod_u_s)
TRANS(vmaddwod_w_hu_h, gvec_vvv, MO_16, do_vmaddwod_u_s)
TRANS(vmaddwod_d_wu_w, gvec_vvv, MO_32, do_vmaddwod_u_s)
+
+TRANS(vdiv_b, gen_vvv, gen_helper_vdiv_b)
+TRANS(vdiv_h, gen_vvv, gen_helper_vdiv_h)
+TRANS(vdiv_w, gen_vvv, gen_helper_vdiv_w)
+TRANS(vdiv_d, gen_vvv, gen_helper_vdiv_d)
+TRANS(vdiv_bu, gen_vvv, gen_helper_vdiv_bu)
+TRANS(vdiv_hu, gen_vvv, gen_helper_vdiv_hu)
+TRANS(vdiv_wu, gen_vvv, gen_helper_vdiv_wu)
+TRANS(vdiv_du, gen_vvv, gen_helper_vdiv_du)
+TRANS(vmod_b, gen_vvv, gen_helper_vmod_b)
+TRANS(vmod_h, gen_vvv, gen_helper_vmod_h)
+TRANS(vmod_w, gen_vvv, gen_helper_vmod_w)
+TRANS(vmod_d, gen_vvv, gen_helper_vmod_d)
+TRANS(vmod_bu, gen_vvv, gen_helper_vmod_bu)
+TRANS(vmod_hu, gen_vvv, gen_helper_vmod_hu)
+TRANS(vmod_wu, gen_vvv, gen_helper_vmod_wu)
+TRANS(vmod_du, gen_vvv, gen_helper_vmod_du)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index df23d4e..67d016e 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -740,3 +740,20 @@
vmaddwod_w_hu_h 0111 00001011 11101 ..... ..... ..... @vvv
vmaddwod_d_wu_w 0111 00001011 11110 ..... ..... ..... @vvv
vmaddwod_q_du_d 0111 00001011 11111 ..... ..... ..... @vvv
+
+vdiv_b 0111 00001110 00000 ..... ..... ..... @vvv
+vdiv_h 0111 00001110 00001 ..... ..... ..... @vvv
+vdiv_w 0111 00001110 00010 ..... ..... ..... @vvv
+vdiv_d 0111 00001110 00011 ..... ..... ..... @vvv
+vdiv_bu 0111 00001110 01000 ..... ..... ..... @vvv
+vdiv_hu 0111 00001110 01001 ..... ..... ..... @vvv
+vdiv_wu 0111 00001110 01010 ..... ..... ..... @vvv
+vdiv_du 0111 00001110 01011 ..... ..... ..... @vvv
+vmod_b 0111 00001110 00100 ..... ..... ..... @vvv
+vmod_h 0111 00001110 00101 ..... ..... ..... @vvv
+vmod_w 0111 00001110 00110 ..... ..... ..... @vvv
+vmod_d 0111 00001110 00111 ..... ..... ..... @vvv
+vmod_bu 0111 00001110 01100 ..... ..... ..... @vvv
+vmod_hu 0111 00001110 01101 ..... ..... ..... @vvv
+vmod_wu 0111 00001110 01110 ..... ..... ..... @vvv
+vmod_du 0111 00001110 01111 ..... ..... ..... @vvv
diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index 8f82091..018009b 100644
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -553,3 +553,40 @@
VMADDWOD_U_S(vmaddwod_h_bu_b, 16, H, UH, B, UB, DO_MUL)
VMADDWOD_U_S(vmaddwod_w_hu_h, 32, W, UW, H, UH, DO_MUL)
VMADDWOD_U_S(vmaddwod_d_wu_w, 64, D, UD, W, UW, DO_MUL)
+
+#define DO_DIVU(N, M) (unlikely(M == 0) ? 0 : N / M)
+#define DO_REMU(N, M) (unlikely(M == 0) ? 0 : N % M)
+#define DO_DIV(N, M) (unlikely(M == 0) ? 0 :\
+ unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M)
+#define DO_REM(N, M) (unlikely(M == 0) ? 0 :\
+ unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M)
+
+#define VDIV(NAME, BIT, E, DO_OP) \
+void HELPER(NAME)(CPULoongArchState *env, \
+ uint32_t vd, uint32_t vj, uint32_t vk) \
+{ \
+ int i; \
+ VReg *Vd = &(env->fpr[vd].vreg); \
+ VReg *Vj = &(env->fpr[vj].vreg); \
+ VReg *Vk = &(env->fpr[vk].vreg); \
+ for (i = 0; i < LSX_LEN/BIT; i++) { \
+ Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i)); \
+ } \
+}
+
+VDIV(vdiv_b, 8, B, DO_DIV)
+VDIV(vdiv_h, 16, H, DO_DIV)
+VDIV(vdiv_w, 32, W, DO_DIV)
+VDIV(vdiv_d, 64, D, DO_DIV)
+VDIV(vdiv_bu, 8, UB, DO_DIVU)
+VDIV(vdiv_hu, 16, UH, DO_DIVU)
+VDIV(vdiv_wu, 32, UW, DO_DIVU)
+VDIV(vdiv_du, 64, UD, DO_DIVU)
+VDIV(vmod_b, 8, B, DO_REM)
+VDIV(vmod_h, 16, H, DO_REM)
+VDIV(vmod_w, 32, W, DO_REM)
+VDIV(vmod_d, 64, D, DO_REM)
+VDIV(vmod_bu, 8, UB, DO_REMU)
+VDIV(vmod_hu, 16, UH, DO_REMU)
+VDIV(vmod_wu, 32, UW, DO_REMU)
+VDIV(vmod_du, 64, UD, DO_REMU)
