6 files changed, 45 insertions, 149 deletions

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 10e8dcf..ad78b8b 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -1324,41 +1324,8 @@ static void ext_and_shift_reg(TCGv_i64 tcg_out, TCGv_i64 tcg_in,
     int extsize = extract32(option, 0, 2);
     bool is_signed = extract32(option, 2, 1);
 
-    if (is_signed) {
-        switch (extsize) {
-        case 0:
-            tcg_gen_ext8s_i64(tcg_out, tcg_in);
-            break;
-        case 1:
-            tcg_gen_ext16s_i64(tcg_out, tcg_in);
-            break;
-        case 2:
-            tcg_gen_ext32s_i64(tcg_out, tcg_in);
-            break;
-        case 3:
-            tcg_gen_mov_i64(tcg_out, tcg_in);
-            break;
-        }
-    } else {
-        switch (extsize) {
-        case 0:
-            tcg_gen_ext8u_i64(tcg_out, tcg_in);
-            break;
-        case 1:
-            tcg_gen_ext16u_i64(tcg_out, tcg_in);
-            break;
-        case 2:
-            tcg_gen_ext32u_i64(tcg_out, tcg_in);
-            break;
-        case 3:
-            tcg_gen_mov_i64(tcg_out, tcg_in);
-            break;
-        }
-    }
-
-    if (shift) {
-        tcg_gen_shli_i64(tcg_out, tcg_out, shift);
-    }
+    tcg_gen_ext_i64(tcg_out, tcg_in, extsize | (is_signed ? MO_SIGN : 0));
+    tcg_gen_shli_i64(tcg_out, tcg_out, shift);
 }
 
 static inline void gen_check_sp_alignment(DisasContext *s)
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 4f6f9fa..587d886 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -701,33 +701,11 @@ static inline void gen_op_movl_T0_Dshift(DisasContext *s, MemOp ot)
 
 static TCGv gen_ext_tl(TCGv dst, TCGv src, MemOp size, bool sign)
 {
-    switch (size) {
-    case MO_8:
-        if (sign) {
-            tcg_gen_ext8s_tl(dst, src);
-        } else {
-            tcg_gen_ext8u_tl(dst, src);
-        }
-        return dst;
-    case MO_16:
-        if (sign) {
-            tcg_gen_ext16s_tl(dst, src);
-        } else {
-            tcg_gen_ext16u_tl(dst, src);
-        }
-        return dst;
-#ifdef TARGET_X86_64
-    case MO_32:
-        if (sign) {
-            tcg_gen_ext32s_tl(dst, src);
-        } else {
-            tcg_gen_ext32u_tl(dst, src);
-        }
-        return dst;
-#endif
-    default:
+    if (size == MO_TL) {
         return src;
     }
+    tcg_gen_ext_tl(dst, src, size | (sign ? MO_SIGN : 0));
+    return dst;
 }
 
 static void gen_extu(MemOp ot, TCGv reg)
@@ -2918,59 +2896,54 @@ static inline void gen_stq_env_A0(DisasContext *s, int offset)
 
 static inline void gen_ldo_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp atom = (s->cpuid_ext_features & CPUID_EXT_AVX
+                  ? MO_ATOM_IFALIGN : MO_ATOM_IFALIGN_PAIR);
+    MemOp mop = MO_128 | MO_LE | atom | (align ? MO_ALIGN_16 : 0);
     int mem_index = s->mem_index;
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(1)));
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_qemu_ld_i128(t, s->A0, mem_index, mop);
+    tcg_gen_st_i128(t, tcg_env, offset);
 }
 
 static inline void gen_sto_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp atom = (s->cpuid_ext_features & CPUID_EXT_AVX
+                  ? MO_ATOM_IFALIGN : MO_ATOM_IFALIGN_PAIR);
+    MemOp mop = MO_128 | MO_LE | atom | (align ? MO_ALIGN_16 : 0);
     int mem_index = s->mem_index;
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_16 : 0));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(XMMReg, XMM_Q(1)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_ld_i128(t, tcg_env, offset);
+    tcg_gen_qemu_st_i128(t, s->A0, mem_index, mop);
 }
 
 static void gen_ldy_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp mop = MO_128 | MO_LE | MO_ATOM_IFALIGN_PAIR;
     int mem_index = s->mem_index;
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_32 : 0));
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(0)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(1)));
+    TCGv_i128 t0 = tcg_temp_new_i128();
+    TCGv_i128 t1 = tcg_temp_new_i128();
 
+    tcg_gen_qemu_ld_i128(t0, s->A0, mem_index, mop | (align ? MO_ALIGN_32 : 0));
     tcg_gen_addi_tl(s->tmp0, s->A0, 16);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(2)));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
-    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_st_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(3)));
+    tcg_gen_qemu_ld_i128(t1, s->tmp0, mem_index, mop);
+
+    tcg_gen_st_i128(t0, tcg_env, offset + offsetof(YMMReg, YMM_X(0)));
+    tcg_gen_st_i128(t1, tcg_env, offset + offsetof(YMMReg, YMM_X(1)));
 }
 
 static void gen_sty_env_A0(DisasContext *s, int offset, bool align)
 {
+    MemOp mop = MO_128 | MO_LE | MO_ATOM_IFALIGN_PAIR;
     int mem_index = s->mem_index;
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(0)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->A0, mem_index,
-                        MO_LEUQ | (align ? MO_ALIGN_32 : 0));
-    tcg_gen_addi_tl(s->tmp0, s->A0, 8);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(1)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    tcg_gen_ld_i128(t, tcg_env, offset + offsetof(YMMReg, YMM_X(0)));
+    tcg_gen_qemu_st_i128(t, s->A0, mem_index, mop | (align ? MO_ALIGN_32 : 0));
     tcg_gen_addi_tl(s->tmp0, s->A0, 16);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(2)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
-    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
-    tcg_gen_ld_i64(s->tmp1_i64, tcg_env, offset + offsetof(YMMReg, YMM_Q(3)));
-    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    tcg_gen_ld_i128(t, tcg_env, offset + offsetof(YMMReg, YMM_X(1)));
+    tcg_gen_qemu_st_i128(t, s->tmp0, mem_index, mop);
 }
 
 #include "decode-new.h"
diff --git a/target/m68k/translate.c b/target/m68k/translate.c
index 4d0110d..4a0b0b2 100644
--- a/target/m68k/translate.c
+++ b/target/m68k/translate.c
@@ -520,21 +520,9 @@ static inline void gen_ext(TCGv res, TCGv val, int opsize, int sign)
 {
     switch (opsize) {
     case OS_BYTE:
-        if (sign) {
-            tcg_gen_ext8s_i32(res, val);
-        } else {
-            tcg_gen_ext8u_i32(res, val);
-        }
-        break;
     case OS_WORD:
-        if (sign) {
-            tcg_gen_ext16s_i32(res, val);
-        } else {
-            tcg_gen_ext16u_i32(res, val);
-        }
-        break;
     case OS_LONG:
-        tcg_gen_mov_i32(res, val);
+        tcg_gen_ext_i32(res, val, opsize | (sign ? MO_SIGN : 0));
         break;
     default:
         g_assert_not_reached();
@@ -1072,15 +1060,10 @@ static int gen_ea_mode_fp(CPUM68KState *env, DisasContext *s, int mode,
             tmp = tcg_temp_new();
             switch (opsize) {
             case OS_BYTE:
-                tcg_gen_ext8s_i32(tmp, reg);
-                gen_helper_exts32(tcg_env, fp, tmp);
-                break;
             case OS_WORD:
-                tcg_gen_ext16s_i32(tmp, reg);
-                gen_helper_exts32(tcg_env, fp, tmp);
-                break;
             case OS_LONG:
-                gen_helper_exts32(tcg_env, fp, reg);
+                tcg_gen_ext_i32(tmp, reg, opsize | MO_SIGN);
+                gen_helper_exts32(tcg_env, fp, tmp);
                 break;
             case OS_SINGLE:
                 gen_helper_extf32(tcg_env, fp, reg);
diff --git a/target/rx/translate.c b/target/rx/translate.c
index f886083..c6ce717 100644
--- a/target/rx/translate.c
+++ b/target/rx/translate.c
@@ -492,13 +492,11 @@ static bool trans_MOV_ra(DisasContext *ctx, arg_MOV_ra *a)
 /* mov.<bwl> rs,rd */
 static bool trans_MOV_mm(DisasContext *ctx, arg_MOV_mm *a)
 {
-    static void (* const mov[])(TCGv ret, TCGv arg) = {
-        tcg_gen_ext8s_i32, tcg_gen_ext16s_i32, tcg_gen_mov_i32,
-    };
     TCGv tmp, mem, addr;
+
     if (a->lds == 3 && a->ldd == 3) {
         /* mov.<bwl> rs,rd */
-        mov[a->sz](cpu_regs[a->rd], cpu_regs[a->rs]);
+        tcg_gen_ext_i32(cpu_regs[a->rd], cpu_regs[a->rs], a->sz | MO_SIGN);
         return true;
     }
 
@@ -570,10 +568,7 @@ static bool trans_MOVU_mr(DisasContext *ctx, arg_MOVU_mr *a)
 /* movu.<bw> rs,rd */
 static bool trans_MOVU_rr(DisasContext *ctx, arg_MOVU_rr *a)
 {
-    static void (* const ext[])(TCGv ret, TCGv arg) = {
-        tcg_gen_ext8u_i32, tcg_gen_ext16u_i32,
-    };
-    ext[a->sz](cpu_regs[a->rd], cpu_regs[a->rs]);
+    tcg_gen_ext_i32(cpu_regs[a->rd], cpu_regs[a->rs], a->sz);
     return true;
 }
 
diff --git a/target/tricore/translate.c b/target/tricore/translate.c
index dd812ec..66553d1 100644
--- a/target/tricore/translate.c
+++ b/target/tricore/translate.c
@@ -6542,28 +6542,16 @@ static void decode_rrpw_extract_insert(DisasContext *ctx)
     switch (op2) {
     case OPC2_32_RRPW_EXTR:
         if (width == 0) {
-                tcg_gen_movi_tl(cpu_gpr_d[r3], 0);
-                break;
-        }
-
-        if (pos + width <= 32) {
-            /* optimize special cases */
-            if ((pos == 0) && (width == 8)) {
-                tcg_gen_ext8s_tl(cpu_gpr_d[r3], cpu_gpr_d[r1]);
-            } else if ((pos == 0) && (width == 16)) {
-                tcg_gen_ext16s_tl(cpu_gpr_d[r3], cpu_gpr_d[r1]);
-            } else {
-                tcg_gen_shli_tl(cpu_gpr_d[r3], cpu_gpr_d[r1], 32 - pos - width);
-                tcg_gen_sari_tl(cpu_gpr_d[r3], cpu_gpr_d[r3], 32 - width);
-            }
+            tcg_gen_movi_tl(cpu_gpr_d[r3], 0);
+        } else if (pos + width <= 32) {
+            tcg_gen_sextract_tl(cpu_gpr_d[r3], cpu_gpr_d[r1], pos, width);
         }
         break;
     case OPC2_32_RRPW_EXTR_U:
         if (width == 0) {
             tcg_gen_movi_tl(cpu_gpr_d[r3], 0);
         } else {
-            tcg_gen_shri_tl(cpu_gpr_d[r3], cpu_gpr_d[r1], pos);
-            tcg_gen_andi_tl(cpu_gpr_d[r3], cpu_gpr_d[r3], ~0u >> (32-width));
+            tcg_gen_extract_tl(cpu_gpr_d[r3], cpu_gpr_d[r1], pos, width);
         }
         break;
     case OPC2_32_RRPW_IMASK:
diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c
index 54bee7d..de89940 100644
--- a/target/xtensa/translate.c
+++ b/target/xtensa/translate.c
@@ -2262,17 +2262,7 @@ static void translate_salt(DisasContext *dc, const OpcodeArg arg[],
 static void translate_sext(DisasContext *dc, const OpcodeArg arg[],
                            const uint32_t par[])
 {
-    int shift = 31 - arg[2].imm;
-
-    if (shift == 24) {
-        tcg_gen_ext8s_i32(arg[0].out, arg[1].in);
-    } else if (shift == 16) {
-        tcg_gen_ext16s_i32(arg[0].out, arg[1].in);
-    } else {
-        TCGv_i32 tmp = tcg_temp_new_i32();
-        tcg_gen_shli_i32(tmp, arg[1].in, shift);
-        tcg_gen_sari_i32(arg[0].out, tmp, shift);
-    }
+    tcg_gen_sextract_i32(arg[0].out, arg[1].in, 0, arg[2].imm + 1);
 }
 
 static uint32_t test_exceptions_simcall(DisasContext *dc,