[PATCH v2 14/46] target/loongarch: Implement xvmax/xvmin

[Song Gao]

This patch includes:
- XVMAX[I].{B/H/W/D}[U];
- XVMIN[I].{B/H/W/D}[U].

Signed-off-by: Song Gao <gaosong@loongson.cn>
---
 target/loongarch/disas.c                     | 34 ++++++++++++++++++
 target/loongarch/insn_trans/trans_lasx.c.inc | 36 ++++++++++++++++++++
 target/loongarch/insns.decode                | 36 ++++++++++++++++++++
 target/loongarch/vec.h                       |  3 ++
 target/loongarch/vec_helper.c                |  8 ++---
 5 files changed, 112 insertions(+), 5 deletions(-)

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index b48822e431..63c1dc757f 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1856,6 +1856,40 @@ INSN_LASX(xvadda_h,          vvv)
 INSN_LASX(xvadda_w,          vvv)
 INSN_LASX(xvadda_d,          vvv)
 
+INSN_LASX(xvmax_b,           vvv)
+INSN_LASX(xvmax_h,           vvv)
+INSN_LASX(xvmax_w,           vvv)
+INSN_LASX(xvmax_d,           vvv)
+INSN_LASX(xvmin_b,           vvv)
+INSN_LASX(xvmin_h,           vvv)
+INSN_LASX(xvmin_w,           vvv)
+INSN_LASX(xvmin_d,           vvv)
+INSN_LASX(xvmax_bu,          vvv)
+INSN_LASX(xvmax_hu,          vvv)
+INSN_LASX(xvmax_wu,          vvv)
+INSN_LASX(xvmax_du,          vvv)
+INSN_LASX(xvmin_bu,          vvv)
+INSN_LASX(xvmin_hu,          vvv)
+INSN_LASX(xvmin_wu,          vvv)
+INSN_LASX(xvmin_du,          vvv)
+
+INSN_LASX(xvmaxi_b,          vv_i)
+INSN_LASX(xvmaxi_h,          vv_i)
+INSN_LASX(xvmaxi_w,          vv_i)
+INSN_LASX(xvmaxi_d,          vv_i)
+INSN_LASX(xvmini_b,          vv_i)
+INSN_LASX(xvmini_h,          vv_i)
+INSN_LASX(xvmini_w,          vv_i)
+INSN_LASX(xvmini_d,          vv_i)
+INSN_LASX(xvmaxi_bu,         vv_i)
+INSN_LASX(xvmaxi_hu,         vv_i)
+INSN_LASX(xvmaxi_wu,         vv_i)
+INSN_LASX(xvmaxi_du,         vv_i)
+INSN_LASX(xvmini_bu,         vv_i)
+INSN_LASX(xvmini_hu,         vv_i)
+INSN_LASX(xvmini_wu,         vv_i)
+INSN_LASX(xvmini_du,         vv_i)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)
diff --git a/target/loongarch/insn_trans/trans_lasx.c.inc 
b/target/loongarch/insn_trans/trans_lasx.c.inc
index 30cb286cb9..107c75f1b6 100644
--- a/target/loongarch/insn_trans/trans_lasx.c.inc
+++ b/target/loongarch/insn_trans/trans_lasx.c.inc
@@ -171,6 +171,42 @@ TRANS(xvadda_h, gvec_vvv, 32, MO_16, do_vadda)
 TRANS(xvadda_w, gvec_vvv, 32, MO_32, do_vadda)
 TRANS(xvadda_d, gvec_vvv, 32, MO_64, do_vadda)
 
+TRANS(xvmax_b, gvec_vvv, 32, MO_8, tcg_gen_gvec_smax)
+TRANS(xvmax_h, gvec_vvv, 32, MO_16, tcg_gen_gvec_smax)
+TRANS(xvmax_w, gvec_vvv, 32, MO_32, tcg_gen_gvec_smax)
+TRANS(xvmax_d, gvec_vvv, 32, MO_64, tcg_gen_gvec_smax)
+TRANS(xvmax_bu, gvec_vvv, 32, MO_8, tcg_gen_gvec_umax)
+TRANS(xvmax_hu, gvec_vvv, 32, MO_16, tcg_gen_gvec_umax)
+TRANS(xvmax_wu, gvec_vvv, 32, MO_32, tcg_gen_gvec_umax)
+TRANS(xvmax_du, gvec_vvv, 32, MO_64, tcg_gen_gvec_umax)
+
+TRANS(xvmin_b, gvec_vvv, 32, MO_8, tcg_gen_gvec_smin)
+TRANS(xvmin_h, gvec_vvv, 32, MO_16, tcg_gen_gvec_smin)
+TRANS(xvmin_w, gvec_vvv, 32, MO_32, tcg_gen_gvec_smin)
+TRANS(xvmin_d, gvec_vvv, 32, MO_64, tcg_gen_gvec_smin)
+TRANS(xvmin_bu, gvec_vvv, 32, MO_8, tcg_gen_gvec_umin)
+TRANS(xvmin_hu, gvec_vvv, 32, MO_16, tcg_gen_gvec_umin)
+TRANS(xvmin_wu, gvec_vvv, 32, MO_32, tcg_gen_gvec_umin)
+TRANS(xvmin_du, gvec_vvv, 32, MO_64, tcg_gen_gvec_umin)
+
+TRANS(xvmini_b, gvec_vv_i, 32, MO_8, do_vmini_s)
+TRANS(xvmini_h, gvec_vv_i, 32, MO_16, do_vmini_s)
+TRANS(xvmini_w, gvec_vv_i, 32, MO_32, do_vmini_s)
+TRANS(xvmini_d, gvec_vv_i, 32, MO_64, do_vmini_s)
+TRANS(xvmini_bu, gvec_vv_i, 32, MO_8, do_vmini_u)
+TRANS(xvmini_hu, gvec_vv_i, 32, MO_16, do_vmini_u)
+TRANS(xvmini_wu, gvec_vv_i, 32, MO_32, do_vmini_u)
+TRANS(xvmini_du, gvec_vv_i, 32, MO_64, do_vmini_u)
+
+TRANS(xvmaxi_b, gvec_vv_i, 32, MO_8, do_vmaxi_s)
+TRANS(xvmaxi_h, gvec_vv_i, 32, MO_16, do_vmaxi_s)
+TRANS(xvmaxi_w, gvec_vv_i, 32, MO_32, do_vmaxi_s)
+TRANS(xvmaxi_d, gvec_vv_i, 32, MO_64, do_vmaxi_s)
+TRANS(xvmaxi_bu, gvec_vv_i, 32, MO_8, do_vmaxi_u)
+TRANS(xvmaxi_hu, gvec_vv_i, 32, MO_16, do_vmaxi_u)
+TRANS(xvmaxi_wu, gvec_vv_i, 32, MO_32, do_vmaxi_u)
+TRANS(xvmaxi_du, gvec_vv_i, 32, MO_64, do_vmaxi_u)
+
 TRANS(xvreplgr2vr_b, gvec_dup, 32, MO_8)
 TRANS(xvreplgr2vr_h, gvec_dup, 32, MO_16)
 TRANS(xvreplgr2vr_w, gvec_dup, 32, MO_32)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index f3722e3aa7..99aefcb651 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1437,6 +1437,42 @@ xvadda_h         0111 01000101 11001 ..... ..... .....   
 @vvv
 xvadda_w         0111 01000101 11010 ..... ..... .....    @vvv
 xvadda_d         0111 01000101 11011 ..... ..... .....    @vvv
 
+xvmax_b          0111 01000111 00000 ..... ..... .....    @vvv
+xvmax_h          0111 01000111 00001 ..... ..... .....    @vvv
+xvmax_w          0111 01000111 00010 ..... ..... .....    @vvv
+xvmax_d          0111 01000111 00011 ..... ..... .....    @vvv
+xvmax_bu         0111 01000111 01000 ..... ..... .....    @vvv
+xvmax_hu         0111 01000111 01001 ..... ..... .....    @vvv
+xvmax_wu         0111 01000111 01010 ..... ..... .....    @vvv
+xvmax_du         0111 01000111 01011 ..... ..... .....    @vvv
+
+xvmaxi_b         0111 01101001 00000 ..... ..... .....    @vv_i5
+xvmaxi_h         0111 01101001 00001 ..... ..... .....    @vv_i5
+xvmaxi_w         0111 01101001 00010 ..... ..... .....    @vv_i5
+xvmaxi_d         0111 01101001 00011 ..... ..... .....    @vv_i5
+xvmaxi_bu        0111 01101001 01000 ..... ..... .....    @vv_ui5
+xvmaxi_hu        0111 01101001 01001 ..... ..... .....    @vv_ui5
+xvmaxi_wu        0111 01101001 01010 ..... ..... .....    @vv_ui5
+xvmaxi_du        0111 01101001 01011 ..... ..... .....    @vv_ui5
+
+xvmin_b          0111 01000111 00100 ..... ..... .....    @vvv
+xvmin_h          0111 01000111 00101 ..... ..... .....    @vvv
+xvmin_w          0111 01000111 00110 ..... ..... .....    @vvv
+xvmin_d          0111 01000111 00111 ..... ..... .....    @vvv
+xvmin_bu         0111 01000111 01100 ..... ..... .....    @vvv
+xvmin_hu         0111 01000111 01101 ..... ..... .....    @vvv
+xvmin_wu         0111 01000111 01110 ..... ..... .....    @vvv
+xvmin_du         0111 01000111 01111 ..... ..... .....    @vvv
+
+xvmini_b         0111 01101001 00100 ..... ..... .....    @vv_i5
+xvmini_h         0111 01101001 00101 ..... ..... .....    @vv_i5
+xvmini_w         0111 01101001 00110 ..... ..... .....    @vv_i5
+xvmini_d         0111 01101001 00111 ..... ..... .....    @vv_i5
+xvmini_bu        0111 01101001 01100 ..... ..... .....    @vv_ui5
+xvmini_hu        0111 01101001 01101 ..... ..... .....    @vv_ui5
+xvmini_wu        0111 01101001 01110 ..... ..... .....    @vv_ui5
+xvmini_du        0111 01101001 01111 ..... ..... .....    @vv_ui5
+
 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.h b/target/loongarch/vec.h
index 30f1a7775f..a053ffc624 100644
--- a/target/loongarch/vec.h
+++ b/target/loongarch/vec.h
@@ -57,4 +57,7 @@
 
 #define DO_VABS(a)      ((a < 0) ? (-a) : (a))
 
+#define DO_MIN(a, b)    (a < b ? a : b)
+#define DO_MAX(a, b)    (a > b ? a : b)
+
 #endif /* LOONGARCH_VEC_H */
diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index 343aef696e..a3348872c9 100644
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -400,18 +400,16 @@ DO_VADDA(vadda_h, 16, H, DO_VABS)
 DO_VADDA(vadda_w, 32, W, DO_VABS)
 DO_VADDA(vadda_d, 64, D, DO_VABS)
 
-#define DO_MIN(a, b) (a < b ? a : b)
-#define DO_MAX(a, b) (a > b ? a : b)
-
 #define VMINMAXI(NAME, BIT, E, DO_OP)                           \
 void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t v) \
 {                                                               \
-    int i;                                                      \
+    int i, len;                                                 \
     VReg *Vd = (VReg *)vd;                                      \
     VReg *Vj = (VReg *)vj;                                      \
     typedef __typeof(Vd->E(0)) TD;                              \
                                                                 \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                         \
+    len = (simd_oprsz(v) == 16) ? LSX_LEN : LASX_LEN;           \
+    for (i = 0; i < len / BIT; i++) {                           \
         Vd->E(i) = DO_OP(Vj->E(i), (TD)imm);                    \
     }                                                           \
 }
-- 
2.39.1