target-i386: Rename XMM_[BWLSDQ] helpers to ZMM_*

They are helpers for the ZMMReg fields, so name them accordingly.

This is just a global search+replace, no other changes are being
introduced.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

8 files changed, 300 insertions, 300 deletions

diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 372814c5f9..d7a7d012c2 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -753,24 +753,24 @@ typedef struct BNDCSReg {
 } BNDCSReg;
 
 #ifdef HOST_WORDS_BIGENDIAN
-#define XMM_B(n) _b[63 - (n)]
-#define XMM_W(n) _w[31 - (n)]
-#define XMM_L(n) _l[15 - (n)]
-#define XMM_S(n) _s[15 - (n)]
-#define XMM_Q(n) _q[7 - (n)]
-#define XMM_D(n) _d[7 - (n)]
+#define ZMM_B(n) _b[63 - (n)]
+#define ZMM_W(n) _w[31 - (n)]
+#define ZMM_L(n) _l[15 - (n)]
+#define ZMM_S(n) _s[15 - (n)]
+#define ZMM_Q(n) _q[7 - (n)]
+#define ZMM_D(n) _d[7 - (n)]
 
 #define MMX_B(n) _b[7 - (n)]
 #define MMX_W(n) _w[3 - (n)]
 #define MMX_L(n) _l[1 - (n)]
 #define MMX_S(n) _s[1 - (n)]
 #else
-#define XMM_B(n) _b[n]
-#define XMM_W(n) _w[n]
-#define XMM_L(n) _l[n]
-#define XMM_S(n) _s[n]
-#define XMM_Q(n) _q[n]
-#define XMM_D(n) _d[n]
+#define ZMM_B(n) _b[n]
+#define ZMM_W(n) _w[n]
+#define ZMM_L(n) _l[n]
+#define ZMM_S(n) _s[n]
+#define ZMM_Q(n) _q[n]
+#define ZMM_D(n) _d[n]
 
 #define MMX_B(n) _b[n]
 #define MMX_W(n) _w[n]
diff --git a/target-i386/fpu_helper.c b/target-i386/fpu_helper.c
index d421a475ff..31afa4475d 100644
--- a/target-i386/fpu_helper.c
+++ b/target-i386/fpu_helper.c
@@ -1169,8 +1169,8 @@ static void do_fxsave(CPUX86State *env, target_ulong ptr, int data64,
             || (env->hflags & HF_CPL_MASK)
             || !(env->hflags & HF_LMA_MASK)) {
             for (i = 0; i < nb_xmm_regs; i++) {
-                cpu_stq_data_ra(env, addr, env->xmm_regs[i].XMM_Q(0), retaddr);
-                cpu_stq_data_ra(env, addr + 8, env->xmm_regs[i].XMM_Q(1), retaddr);
+                cpu_stq_data_ra(env, addr, env->xmm_regs[i].ZMM_Q(0), retaddr);
+                cpu_stq_data_ra(env, addr + 8, env->xmm_regs[i].ZMM_Q(1), retaddr);
                 addr += 16;
             }
         }
@@ -1226,8 +1226,8 @@ static void do_fxrstor(CPUX86State *env, target_ulong ptr, int data64,
             || (env->hflags & HF_CPL_MASK)
             || !(env->hflags & HF_LMA_MASK)) {
             for (i = 0; i < nb_xmm_regs; i++) {
-                env->xmm_regs[i].XMM_Q(0) = cpu_ldq_data_ra(env, addr, retaddr);
-                env->xmm_regs[i].XMM_Q(1) = cpu_ldq_data_ra(env, addr + 8, retaddr);
+                env->xmm_regs[i].ZMM_Q(0) = cpu_ldq_data_ra(env, addr, retaddr);
+                env->xmm_regs[i].ZMM_Q(1) = cpu_ldq_data_ra(env, addr + 8, retaddr);
                 addr += 16;
             }
         }
diff --git a/target-i386/gdbstub.c b/target-i386/gdbstub.c
index ff99cfb007..6a9bf3c4a0 100644
--- a/target-i386/gdbstub.c
+++ b/target-i386/gdbstub.c
@@ -61,8 +61,8 @@ int x86_cpu_gdb_read_register(CPUState *cs, uint8_t *mem_buf, int n)
         n -= IDX_XMM_REGS;
         if (n < CPU_NB_REGS32 ||
             (TARGET_LONG_BITS == 64 && env->hflags & HF_CS64_MASK)) {
-            stq_p(mem_buf, env->xmm_regs[n].XMM_Q(0));
-            stq_p(mem_buf + 8, env->xmm_regs[n].XMM_Q(1));
+            stq_p(mem_buf, env->xmm_regs[n].ZMM_Q(0));
+            stq_p(mem_buf + 8, env->xmm_regs[n].ZMM_Q(1));
             return 16;
         }
     } else {
@@ -170,8 +170,8 @@ int x86_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
         n -= IDX_XMM_REGS;
         if (n < CPU_NB_REGS32 ||
             (TARGET_LONG_BITS == 64 && env->hflags & HF_CS64_MASK)) {
-            env->xmm_regs[n].XMM_Q(0) = ldq_p(mem_buf);
-            env->xmm_regs[n].XMM_Q(1) = ldq_p(mem_buf + 8);
+            env->xmm_regs[n].ZMM_Q(0) = ldq_p(mem_buf);
+            env->xmm_regs[n].ZMM_Q(1) = ldq_p(mem_buf + 8);
             return 16;
         }
     } else {
diff --git a/target-i386/helper.c b/target-i386/helper.c
index 6b10019e70..24f58117ab 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -535,10 +535,10 @@ void x86_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf,
         for(i=0;i<nb;i++) {
             cpu_fprintf(f, "XMM%02d=%08x%08x%08x%08x",
                         i,
-                        env->xmm_regs[i].XMM_L(3),
-                        env->xmm_regs[i].XMM_L(2),
-                        env->xmm_regs[i].XMM_L(1),
-                        env->xmm_regs[i].XMM_L(0));
+                        env->xmm_regs[i].ZMM_L(3),
+                        env->xmm_regs[i].ZMM_L(2),
+                        env->xmm_regs[i].ZMM_L(1),
+                        env->xmm_regs[i].ZMM_L(0));
             if ((i & 1) == 1)
                 cpu_fprintf(f, "\n");
             else
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index ab65a6ebe5..0551a5c27e 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1237,8 +1237,8 @@ static int kvm_put_fpu(X86CPU *cpu)
     }
     memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
     for (i = 0; i < CPU_NB_REGS; i++) {
-        stq_p(&fpu.xmm[i][0], env->xmm_regs[i].XMM_Q(0));
-        stq_p(&fpu.xmm[i][8], env->xmm_regs[i].XMM_Q(1));
+        stq_p(&fpu.xmm[i][0], env->xmm_regs[i].ZMM_Q(0));
+        stq_p(&fpu.xmm[i][8], env->xmm_regs[i].ZMM_Q(1));
     }
     fpu.mxcsr = env->mxcsr;
 
@@ -1299,14 +1299,14 @@ static int kvm_put_xsave(X86CPU *cpu)
     ymmh = (uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
     zmmh = (uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
     for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
-        stq_p(xmm,     env->xmm_regs[i].XMM_Q(0));
-        stq_p(xmm+8,   env->xmm_regs[i].XMM_Q(1));
-        stq_p(ymmh,    env->xmm_regs[i].XMM_Q(2));
-        stq_p(ymmh+8,  env->xmm_regs[i].XMM_Q(3));
-        stq_p(zmmh,    env->xmm_regs[i].XMM_Q(4));
-        stq_p(zmmh+8,  env->xmm_regs[i].XMM_Q(5));
-        stq_p(zmmh+16, env->xmm_regs[i].XMM_Q(6));
-        stq_p(zmmh+24, env->xmm_regs[i].XMM_Q(7));
+        stq_p(xmm,     env->xmm_regs[i].ZMM_Q(0));
+        stq_p(xmm+8,   env->xmm_regs[i].ZMM_Q(1));
+        stq_p(ymmh,    env->xmm_regs[i].ZMM_Q(2));
+        stq_p(ymmh+8,  env->xmm_regs[i].ZMM_Q(3));
+        stq_p(zmmh,    env->xmm_regs[i].ZMM_Q(4));
+        stq_p(zmmh+8,  env->xmm_regs[i].ZMM_Q(5));
+        stq_p(zmmh+16, env->xmm_regs[i].ZMM_Q(6));
+        stq_p(zmmh+24, env->xmm_regs[i].ZMM_Q(7));
     }
 
 #ifdef TARGET_X86_64
@@ -1665,8 +1665,8 @@ static int kvm_get_fpu(X86CPU *cpu)
     }
     memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
     for (i = 0; i < CPU_NB_REGS; i++) {
-        env->xmm_regs[i].XMM_Q(0) = ldq_p(&fpu.xmm[i][0]);
-        env->xmm_regs[i].XMM_Q(1) = ldq_p(&fpu.xmm[i][8]);
+        env->xmm_regs[i].ZMM_Q(0) = ldq_p(&fpu.xmm[i][0]);
+        env->xmm_regs[i].ZMM_Q(1) = ldq_p(&fpu.xmm[i][8]);
     }
     env->mxcsr = fpu.mxcsr;
 
@@ -1717,14 +1717,14 @@ static int kvm_get_xsave(X86CPU *cpu)
     ymmh = (const uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
     zmmh = (const uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
     for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
-        env->xmm_regs[i].XMM_Q(0) = ldq_p(xmm);
-        env->xmm_regs[i].XMM_Q(1) = ldq_p(xmm+8);
-        env->xmm_regs[i].XMM_Q(2) = ldq_p(ymmh);
-        env->xmm_regs[i].XMM_Q(3) = ldq_p(ymmh+8);
-        env->xmm_regs[i].XMM_Q(4) = ldq_p(zmmh);
-        env->xmm_regs[i].XMM_Q(5) = ldq_p(zmmh+8);
-        env->xmm_regs[i].XMM_Q(6) = ldq_p(zmmh+16);
-        env->xmm_regs[i].XMM_Q(7) = ldq_p(zmmh+24);
+        env->xmm_regs[i].ZMM_Q(0) = ldq_p(xmm);
+        env->xmm_regs[i].ZMM_Q(1) = ldq_p(xmm+8);
+        env->xmm_regs[i].ZMM_Q(2) = ldq_p(ymmh);
+        env->xmm_regs[i].ZMM_Q(3) = ldq_p(ymmh+8);
+        env->xmm_regs[i].ZMM_Q(4) = ldq_p(zmmh);
+        env->xmm_regs[i].ZMM_Q(5) = ldq_p(zmmh+8);
+        env->xmm_regs[i].ZMM_Q(6) = ldq_p(zmmh+16);
+        env->xmm_regs[i].ZMM_Q(7) = ldq_p(zmmh+24);
     }
 
 #ifdef TARGET_X86_64
diff --git a/target-i386/machine.c b/target-i386/machine.c
index 6ea29a41af..4d802882f5 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -36,8 +36,8 @@ static const VMStateDescription vmstate_xmm_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(0), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(1), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(0), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(1), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -52,8 +52,8 @@ static const VMStateDescription vmstate_ymmh_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(2), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(3), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(2), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(3), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -67,10 +67,10 @@ static const VMStateDescription vmstate_zmmh_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(4), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(5), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(6), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(7), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(4), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(5), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(6), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(7), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -85,14 +85,14 @@ static const VMStateDescription vmstate_hi16_zmm_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(0), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(1), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(2), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(3), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(4), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(5), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(6), ZMMReg),
-        VMSTATE_UINT64(XMM_Q(7), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(0), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(1), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(2), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(3), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(4), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(5), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(6), ZMMReg),
+        VMSTATE_UINT64(ZMM_Q(7), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -787,7 +787,7 @@ static bool avx512_needed(void *opaque)
     }
 
     for (i = 0; i < CPU_NB_REGS; i++) {
-#define ENV_XMM(reg, field) (env->xmm_regs[reg].XMM_Q(field))
+#define ENV_XMM(reg, field) (env->xmm_regs[reg].ZMM_Q(field))
         if (ENV_XMM(i, 4) || ENV_XMM(i, 6) ||
             ENV_XMM(i, 5) || ENV_XMM(i, 7)) {
             return true;
diff --git a/target-i386/ops_sse.h b/target-i386/ops_sse.h
index b0820e731a..7a98f53864 100644
--- a/target-i386/ops_sse.h
+++ b/target-i386/ops_sse.h
@@ -31,10 +31,10 @@
 #else
 #define Reg ZMMReg
 #define XMM_ONLY(...) __VA_ARGS__
-#define B(n) XMM_B(n)
-#define W(n) XMM_W(n)
-#define L(n) XMM_L(n)
-#define Q(n) XMM_Q(n)
+#define B(n) ZMM_B(n)
+#define W(n) ZMM_W(n)
+#define L(n) ZMM_L(n)
+#define Q(n) ZMM_Q(n)
 #define SUFFIX _xmm
 #endif
 
@@ -582,26 +582,26 @@ void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order)
 #define SSE_HELPER_S(name, F)                                           \
     void helper_ ## name ## ps(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));                  \
-        d->XMM_S(1) = F(32, d->XMM_S(1), s->XMM_S(1));                  \
-        d->XMM_S(2) = F(32, d->XMM_S(2), s->XMM_S(2));                  \
-        d->XMM_S(3) = F(32, d->XMM_S(3), s->XMM_S(3));                  \
+        d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
+        d->ZMM_S(1) = F(32, d->ZMM_S(1), s->ZMM_S(1));                  \
+        d->ZMM_S(2) = F(32, d->ZMM_S(2), s->ZMM_S(2));                  \
+        d->ZMM_S(3) = F(32, d->ZMM_S(3), s->ZMM_S(3));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));                  \
+        d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## pd(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));                  \
-        d->XMM_D(1) = F(64, d->XMM_D(1), s->XMM_D(1));                  \
+        d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
+        d->ZMM_D(1) = F(64, d->ZMM_D(1), s->ZMM_D(1));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));                  \
+        d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
     }
 
 #define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status)
@@ -633,216 +633,216 @@ void helper_cvtps2pd(CPUX86State *env, Reg *d, Reg *s)
 {
     float32 s0, s1;
 
-    s0 = s->XMM_S(0);
-    s1 = s->XMM_S(1);
-    d->XMM_D(0) = float32_to_float64(s0, &env->sse_status);
-    d->XMM_D(1) = float32_to_float64(s1, &env->sse_status);
+    s0 = s->ZMM_S(0);
+    s1 = s->ZMM_S(1);
+    d->ZMM_D(0) = float32_to_float64(s0, &env->sse_status);
+    d->ZMM_D(1) = float32_to_float64(s1, &env->sse_status);
 }
 
 void helper_cvtpd2ps(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->XMM_S(0) = float64_to_float32(s->XMM_D(0), &env->sse_status);
-    d->XMM_S(1) = float64_to_float32(s->XMM_D(1), &env->sse_status);
+    d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
+    d->ZMM_S(1) = float64_to_float32(s->ZMM_D(1), &env->sse_status);
     d->Q(1) = 0;
 }
 
 void helper_cvtss2sd(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->XMM_D(0) = float32_to_float64(s->XMM_S(0), &env->sse_status);
+    d->ZMM_D(0) = float32_to_float64(s->ZMM_S(0), &env->sse_status);
 }
 
 void helper_cvtsd2ss(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->XMM_S(0) = float64_to_float32(s->XMM_D(0), &env->sse_status);
+    d->ZMM_S(0) = float64_to_float32(s->ZMM_D(0), &env->sse_status);
 }
 
 /* integer to float */
 void helper_cvtdq2ps(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->XMM_S(0) = int32_to_float32(s->XMM_L(0), &env->sse_status);
-    d->XMM_S(1) = int32_to_float32(s->XMM_L(1), &env->sse_status);
-    d->XMM_S(2) = int32_to_float32(s->XMM_L(2), &env->sse_status);
-    d->XMM_S(3) = int32_to_float32(s->XMM_L(3), &env->sse_status);
+    d->ZMM_S(0) = int32_to_float32(s->ZMM_L(0), &env->sse_status);
+    d->ZMM_S(1) = int32_to_float32(s->ZMM_L(1), &env->sse_status);
+    d->ZMM_S(2) = int32_to_float32(s->ZMM_L(2), &env->sse_status);
+    d->ZMM_S(3) = int32_to_float32(s->ZMM_L(3), &env->sse_status);
 }
 
 void helper_cvtdq2pd(CPUX86State *env, Reg *d, Reg *s)
 {
     int32_t l0, l1;
 
-    l0 = (int32_t)s->XMM_L(0);
-    l1 = (int32_t)s->XMM_L(1);
-    d->XMM_D(0) = int32_to_float64(l0, &env->sse_status);
-    d->XMM_D(1) = int32_to_float64(l1, &env->sse_status);
+    l0 = (int32_t)s->ZMM_L(0);
+    l1 = (int32_t)s->ZMM_L(1);
+    d->ZMM_D(0) = int32_to_float64(l0, &env->sse_status);
+    d->ZMM_D(1) = int32_to_float64(l1, &env->sse_status);
 }
 
 void helper_cvtpi2ps(CPUX86State *env, ZMMReg *d, MMXReg *s)
 {
-    d->XMM_S(0) = int32_to_float32(s->MMX_L(0), &env->sse_status);
-    d->XMM_S(1) = int32_to_float32(s->MMX_L(1), &env->sse_status);
+    d->ZMM_S(0) = int32_to_float32(s->MMX_L(0), &env->sse_status);
+    d->ZMM_S(1) = int32_to_float32(s->MMX_L(1), &env->sse_status);
 }
 
 void helper_cvtpi2pd(CPUX86State *env, ZMMReg *d, MMXReg *s)
 {
-    d->XMM_D(0) = int32_to_float64(s->MMX_L(0), &env->sse_status);
-    d->XMM_D(1) = int32_to_float64(s->MMX_L(1), &env->sse_status);
+    d->ZMM_D(0) = int32_to_float64(s->MMX_L(0), &env->sse_status);
+    d->ZMM_D(1) = int32_to_float64(s->MMX_L(1), &env->sse_status);
 }
 
 void helper_cvtsi2ss(CPUX86State *env, ZMMReg *d, uint32_t val)
 {
-    d->XMM_S(0) = int32_to_float32(val, &env->sse_status);
+    d->ZMM_S(0) = int32_to_float32(val, &env->sse_status);
 }
 
 void helper_cvtsi2sd(CPUX86State *env, ZMMReg *d, uint32_t val)
 {
-    d->XMM_D(0) = int32_to_float64(val, &env->sse_status);
+    d->ZMM_D(0) = int32_to_float64(val, &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
 void helper_cvtsq2ss(CPUX86State *env, ZMMReg *d, uint64_t val)
 {
-    d->XMM_S(0) = int64_to_float32(val, &env->sse_status);
+    d->ZMM_S(0) = int64_to_float32(val, &env->sse_status);
 }
 
 void helper_cvtsq2sd(CPUX86State *env, ZMMReg *d, uint64_t val)
 {
-    d->XMM_D(0) = int64_to_float64(val, &env->sse_status);
+    d->ZMM_D(0) = int64_to_float64(val, &env->sse_status);
 }
 #endif
 
 /* float to integer */
 void helper_cvtps2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_L(0) = float32_to_int32(s->XMM_S(0), &env->sse_status);
-    d->XMM_L(1) = float32_to_int32(s->XMM_S(1), &env->sse_status);
-    d->XMM_L(2) = float32_to_int32(s->XMM_S(2), &env->sse_status);
-    d->XMM_L(3) = float32_to_int32(s->XMM_S(3), &env->sse_status);
+    d->ZMM_L(0) = float32_to_int32(s->ZMM_S(0), &env->sse_status);
+    d->ZMM_L(1) = float32_to_int32(s->ZMM_S(1), &env->sse_status);
+    d->ZMM_L(2) = float32_to_int32(s->ZMM_S(2), &env->sse_status);
+    d->ZMM_L(3) = float32_to_int32(s->ZMM_S(3), &env->sse_status);
 }
 
 void helper_cvtpd2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_L(0) = float64_to_int32(s->XMM_D(0), &env->sse_status);
-    d->XMM_L(1) = float64_to_int32(s->XMM_D(1), &env->sse_status);
-    d->XMM_Q(1) = 0;
+    d->ZMM_L(0) = float64_to_int32(s->ZMM_D(0), &env->sse_status);
+    d->ZMM_L(1) = float64_to_int32(s->ZMM_D(1), &env->sse_status);
+    d->ZMM_Q(1) = 0;
 }
 
 void helper_cvtps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
-    d->MMX_L(0) = float32_to_int32(s->XMM_S(0), &env->sse_status);
-    d->MMX_L(1) = float32_to_int32(s->XMM_S(1), &env->sse_status);
+    d->MMX_L(0) = float32_to_int32(s->ZMM_S(0), &env->sse_status);
+    d->MMX_L(1) = float32_to_int32(s->ZMM_S(1), &env->sse_status);
 }
 
 void helper_cvtpd2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
-    d->MMX_L(0) = float64_to_int32(s->XMM_D(0), &env->sse_status);
-    d->MMX_L(1) = float64_to_int32(s->XMM_D(1), &env->sse_status);
+    d->MMX_L(0) = float64_to_int32(s->ZMM_D(0), &env->sse_status);
+    d->MMX_L(1) = float64_to_int32(s->ZMM_D(1), &env->sse_status);
 }
 
 int32_t helper_cvtss2si(CPUX86State *env, ZMMReg *s)
 {
-    return float32_to_int32(s->XMM_S(0), &env->sse_status);
+    return float32_to_int32(s->ZMM_S(0), &env->sse_status);
 }
 
 int32_t helper_cvtsd2si(CPUX86State *env, ZMMReg *s)
 {
-    return float64_to_int32(s->XMM_D(0), &env->sse_status);
+    return float64_to_int32(s->ZMM_D(0), &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
 int64_t helper_cvtss2sq(CPUX86State *env, ZMMReg *s)
 {
-    return float32_to_int64(s->XMM_S(0), &env->sse_status);
+    return float32_to_int64(s->ZMM_S(0), &env->sse_status);
 }
 
 int64_t helper_cvtsd2sq(CPUX86State *env, ZMMReg *s)
 {
-    return float64_to_int64(s->XMM_D(0), &env->sse_status);
+    return float64_to_int64(s->ZMM_D(0), &env->sse_status);
 }
 #endif
 
 /* float to integer truncated */
 void helper_cvttps2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_L(0) = float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
-    d->XMM_L(1) = float32_to_int32_round_to_zero(s->XMM_S(1), &env->sse_status);
-    d->XMM_L(2) = float32_to_int32_round_to_zero(s->XMM_S(2), &env->sse_status);
-    d->XMM_L(3) = float32_to_int32_round_to_zero(s->XMM_S(3), &env->sse_status);
+    d->ZMM_L(0) = float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
+    d->ZMM_L(1) = float32_to_int32_round_to_zero(s->ZMM_S(1), &env->sse_status);
+    d->ZMM_L(2) = float32_to_int32_round_to_zero(s->ZMM_S(2), &env->sse_status);
+    d->ZMM_L(3) = float32_to_int32_round_to_zero(s->ZMM_S(3), &env->sse_status);
 }
 
 void helper_cvttpd2dq(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_L(0) = float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
-    d->XMM_L(1) = float64_to_int32_round_to_zero(s->XMM_D(1), &env->sse_status);
-    d->XMM_Q(1) = 0;
+    d->ZMM_L(0) = float64_to_int32_round_to_zero(s->ZMM_D(0), &env->sse_status);
+    d->ZMM_L(1) = float64_to_int32_round_to_zero(s->ZMM_D(1), &env->sse_status);
+    d->ZMM_Q(1) = 0;
 }
 
 void helper_cvttps2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
-    d->MMX_L(0) = float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
-    d->MMX_L(1) = float32_to_int32_round_to_zero(s->XMM_S(1), &env->sse_status);
+    d->MMX_L(0) = float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
+    d->MMX_L(1) = float32_to_int32_round_to_zero(s->ZMM_S(1), &env->sse_status);
 }
 
 void helper_cvttpd2pi(CPUX86State *env, MMXReg *d, ZMMReg *s)
 {
-    d->MMX_L(0) = float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
-    d->MMX_L(1) = float64_to_int32_round_to_zero(s->XMM_D(1), &env->sse_status);
+    d->MMX_L(0) = float64_to_int32_round_to_zero(s->ZMM_D(0), &env->sse_status);
+    d->MMX_L(1) = float64_to_int32_round_to_zero(s->ZMM_D(1), &env->sse_status);
 }
 
 int32_t helper_cvttss2si(CPUX86State *env, ZMMReg *s)
 {
-    return float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
+    return float32_to_int32_round_to_zero(s->ZMM_S(0), &env->sse_status);
 }
 
 int32_t helper_cvttsd2si(CPUX86State *env, ZMMReg *s)
 {
-    return float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
+    return float64_to_int32_round_to_zero(s->ZMM_D(0), &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
 int64_t helper_cvttss2sq(CPUX86State *env, ZMMReg *s)
 {
-    return float32_to_int64_round_to_zero(s->XMM_S(0), &env->sse_status);
+    return float32_to_int64_round_to_zero(s->ZMM_S(0), &env->sse_status);
 }
 
 int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
 {
-    return float64_to_int64_round_to_zero(s->XMM_D(0), &env->sse_status);
+    return float64_to_int64_round_to_zero(s->ZMM_D(0), &env->sse_status);
 }
 #endif
 
 void helper_rsqrtps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_S(0) = float32_div(float32_one,
-                              float32_sqrt(s->XMM_S(0), &env->sse_status),
+    d->ZMM_S(0) = float32_div(float32_one,
+                              float32_sqrt(s->ZMM_S(0), &env->sse_status),
                               &env->sse_status);
-    d->XMM_S(1) = float32_div(float32_one,
-                              float32_sqrt(s->XMM_S(1), &env->sse_status),
+    d->ZMM_S(1) = float32_div(float32_one,
+                              float32_sqrt(s->ZMM_S(1), &env->sse_status),
                               &env->sse_status);
-    d->XMM_S(2) = float32_div(float32_one,
-                              float32_sqrt(s->XMM_S(2), &env->sse_status),
+    d->ZMM_S(2) = float32_div(float32_one,
+                              float32_sqrt(s->ZMM_S(2), &env->sse_status),
                               &env->sse_status);
-    d->XMM_S(3) = float32_div(float32_one,
-                              float32_sqrt(s->XMM_S(3), &env->sse_status),
+    d->ZMM_S(3) = float32_div(float32_one,
+                              float32_sqrt(s->ZMM_S(3), &env->sse_status),
                               &env->sse_status);
 }
 
 void helper_rsqrtss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_S(0) = float32_div(float32_one,
-                              float32_sqrt(s->XMM_S(0), &env->sse_status),
+    d->ZMM_S(0) = float32_div(float32_one,
+                              float32_sqrt(s->ZMM_S(0), &env->sse_status),
                               &env->sse_status);
 }
 
 void helper_rcpps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_S(0) = float32_div(float32_one, s->XMM_S(0), &env->sse_status);
-    d->XMM_S(1) = float32_div(float32_one, s->XMM_S(1), &env->sse_status);
-    d->XMM_S(2) = float32_div(float32_one, s->XMM_S(2), &env->sse_status);
-    d->XMM_S(3) = float32_div(float32_one, s->XMM_S(3), &env->sse_status);
+    d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
+    d->ZMM_S(1) = float32_div(float32_one, s->ZMM_S(1), &env->sse_status);
+    d->ZMM_S(2) = float32_div(float32_one, s->ZMM_S(2), &env->sse_status);
+    d->ZMM_S(3) = float32_div(float32_one, s->ZMM_S(3), &env->sse_status);
 }
 
 void helper_rcpss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_S(0) = float32_div(float32_one, s->XMM_S(0), &env->sse_status);
+    d->ZMM_S(0) = float32_div(float32_one, s->ZMM_S(0), &env->sse_status);
 }
 
 static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
@@ -859,12 +859,12 @@ static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
 
 void helper_extrq_r(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_Q(0) = helper_extrq(d->XMM_Q(0), s->XMM_B(1), s->XMM_B(0));
+    d->ZMM_Q(0) = helper_extrq(d->ZMM_Q(0), s->ZMM_B(1), s->ZMM_B(0));
 }
 
 void helper_extrq_i(CPUX86State *env, ZMMReg *d, int index, int length)
 {
-    d->XMM_Q(0) = helper_extrq(d->XMM_Q(0), index, length);
+    d->ZMM_Q(0) = helper_extrq(d->ZMM_Q(0), index, length);
 }
 
 static inline uint64_t helper_insertq(uint64_t src, int shift, int len)
@@ -881,22 +881,22 @@ static inline uint64_t helper_insertq(uint64_t src, int shift, int len)
 
 void helper_insertq_r(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_Q(0) = helper_insertq(s->XMM_Q(0), s->XMM_B(9), s->XMM_B(8));
+    d->ZMM_Q(0) = helper_insertq(s->ZMM_Q(0), s->ZMM_B(9), s->ZMM_B(8));
 }
 
 void helper_insertq_i(CPUX86State *env, ZMMReg *d, int index, int length)
 {
-    d->XMM_Q(0) = helper_insertq(d->XMM_Q(0), index, length);
+    d->ZMM_Q(0) = helper_insertq(d->ZMM_Q(0), index, length);
 }
 
 void helper_haddps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     ZMMReg r;
 
-    r.XMM_S(0) = float32_add(d->XMM_S(0), d->XMM_S(1), &env->sse_status);
-    r.XMM_S(1) = float32_add(d->XMM_S(2), d->XMM_S(3), &env->sse_status);
-    r.XMM_S(2) = float32_add(s->XMM_S(0), s->XMM_S(1), &env->sse_status);
-    r.XMM_S(3) = float32_add(s->XMM_S(2), s->XMM_S(3), &env->sse_status);
+    r.ZMM_S(0) = float32_add(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
+    r.ZMM_S(1) = float32_add(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
+    r.ZMM_S(2) = float32_add(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
+    r.ZMM_S(3) = float32_add(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
     *d = r;
 }
 
@@ -904,8 +904,8 @@ void helper_haddpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     ZMMReg r;
 
-    r.XMM_D(0) = float64_add(d->XMM_D(0), d->XMM_D(1), &env->sse_status);
-    r.XMM_D(1) = float64_add(s->XMM_D(0), s->XMM_D(1), &env->sse_status);
+    r.ZMM_D(0) = float64_add(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
+    r.ZMM_D(1) = float64_add(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
     *d = r;
 }
 
@@ -913,10 +913,10 @@ void helper_hsubps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     ZMMReg r;
 
-    r.XMM_S(0) = float32_sub(d->XMM_S(0), d->XMM_S(1), &env->sse_status);
-    r.XMM_S(1) = float32_sub(d->XMM_S(2), d->XMM_S(3), &env->sse_status);
-    r.XMM_S(2) = float32_sub(s->XMM_S(0), s->XMM_S(1), &env->sse_status);
-    r.XMM_S(3) = float32_sub(s->XMM_S(2), s->XMM_S(3), &env->sse_status);
+    r.ZMM_S(0) = float32_sub(d->ZMM_S(0), d->ZMM_S(1), &env->sse_status);
+    r.ZMM_S(1) = float32_sub(d->ZMM_S(2), d->ZMM_S(3), &env->sse_status);
+    r.ZMM_S(2) = float32_sub(s->ZMM_S(0), s->ZMM_S(1), &env->sse_status);
+    r.ZMM_S(3) = float32_sub(s->ZMM_S(2), s->ZMM_S(3), &env->sse_status);
     *d = r;
 }
 
@@ -924,49 +924,49 @@ void helper_hsubpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     ZMMReg r;
 
-    r.XMM_D(0) = float64_sub(d->XMM_D(0), d->XMM_D(1), &env->sse_status);
-    r.XMM_D(1) = float64_sub(s->XMM_D(0), s->XMM_D(1), &env->sse_status);
+    r.ZMM_D(0) = float64_sub(d->ZMM_D(0), d->ZMM_D(1), &env->sse_status);
+    r.ZMM_D(1) = float64_sub(s->ZMM_D(0), s->ZMM_D(1), &env->sse_status);
     *d = r;
 }
 
 void helper_addsubps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_S(0) = float32_sub(d->XMM_S(0), s->XMM_S(0), &env->sse_status);
-    d->XMM_S(1) = float32_add(d->XMM_S(1), s->XMM_S(1), &env->sse_status);
-    d->XMM_S(2) = float32_sub(d->XMM_S(2), s->XMM_S(2), &env->sse_status);
-    d->XMM_S(3) = float32_add(d->XMM_S(3), s->XMM_S(3), &env->sse_status);
+    d->ZMM_S(0) = float32_sub(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status);
+    d->ZMM_S(1) = float32_add(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status);
+    d->ZMM_S(2) = float32_sub(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status);
+    d->ZMM_S(3) = float32_add(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status);
 }
 
 void helper_addsubpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    d->XMM_D(0) = float64_sub(d->XMM_D(0), s->XMM_D(0), &env->sse_status);
-    d->XMM_D(1) = float64_add(d->XMM_D(1), s->XMM_D(1), &env->sse_status);
+    d->ZMM_D(0) = float64_sub(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status);
+    d->ZMM_D(1) = float64_add(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status);
 }
 
 /* XXX: unordered */
 #define SSE_HELPER_CMP(name, F)                                         \
     void helper_ ## name ## ps(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0));                  \
-        d->XMM_L(1) = F(32, d->XMM_S(1), s->XMM_S(1));                  \
-        d->XMM_L(2) = F(32, d->XMM_S(2), s->XMM_S(2));                  \
-        d->XMM_L(3) = F(32, d->XMM_S(3), s->XMM_S(3));                  \
+        d->ZMM_L(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
+        d->ZMM_L(1) = F(32, d->ZMM_S(1), s->ZMM_S(1));                  \
+        d->ZMM_L(2) = F(32, d->ZMM_S(2), s->ZMM_S(2));                  \
+        d->ZMM_L(3) = F(32, d->ZMM_S(3), s->ZMM_S(3));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0));                  \
+        d->ZMM_L(0) = F(32, d->ZMM_S(0), s->ZMM_S(0));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## pd(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0));                  \
-        d->XMM_Q(1) = F(64, d->XMM_D(1), s->XMM_D(1));                  \
+        d->ZMM_Q(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
+        d->ZMM_Q(1) = F(64, d->ZMM_D(1), s->ZMM_D(1));                  \
     }                                                                   \
                                                                         \
     void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)        \
     {                                                                   \
-        d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0));                  \
+        d->ZMM_Q(0) = F(64, d->ZMM_D(0), s->ZMM_D(0));                  \
     }
 
 #define FPU_CMPEQ(size, a, b)                                           \
@@ -1002,8 +1002,8 @@ void helper_ucomiss(CPUX86State *env, Reg *d, Reg *s)
     int ret;
     float32 s0, s1;
 
-    s0 = d->XMM_S(0);
-    s1 = s->XMM_S(0);
+    s0 = d->ZMM_S(0);
+    s1 = s->ZMM_S(0);
     ret = float32_compare_quiet(s0, s1, &env->sse_status);
     CC_SRC = comis_eflags[ret + 1];
 }
@@ -1013,8 +1013,8 @@ void helper_comiss(CPUX86State *env, Reg *d, Reg *s)
     int ret;
     float32 s0, s1;
 
-    s0 = d->XMM_S(0);
-    s1 = s->XMM_S(0);
+    s0 = d->ZMM_S(0);
+    s1 = s->ZMM_S(0);
     ret = float32_compare(s0, s1, &env->sse_status);
     CC_SRC = comis_eflags[ret + 1];
 }
@@ -1024,8 +1024,8 @@ void helper_ucomisd(CPUX86State *env, Reg *d, Reg *s)
     int ret;
     float64 d0, d1;
 
-    d0 = d->XMM_D(0);
-    d1 = s->XMM_D(0);
+    d0 = d->ZMM_D(0);
+    d1 = s->ZMM_D(0);
     ret = float64_compare_quiet(d0, d1, &env->sse_status);
     CC_SRC = comis_eflags[ret + 1];
 }
@@ -1035,8 +1035,8 @@ void helper_comisd(CPUX86State *env, Reg *d, Reg *s)
     int ret;
     float64 d0, d1;
 
-    d0 = d->XMM_D(0);
-    d1 = s->XMM_D(0);
+    d0 = d->ZMM_D(0);
+    d1 = s->ZMM_D(0);
     ret = float64_compare(d0, d1, &env->sse_status);
     CC_SRC = comis_eflags[ret + 1];
 }
@@ -1045,10 +1045,10 @@ uint32_t helper_movmskps(CPUX86State *env, Reg *s)
 {
     int b0, b1, b2, b3;
 
-    b0 = s->XMM_L(0) >> 31;
-    b1 = s->XMM_L(1) >> 31;
-    b2 = s->XMM_L(2) >> 31;
-    b3 = s->XMM_L(3) >> 31;
+    b0 = s->ZMM_L(0) >> 31;
+    b1 = s->ZMM_L(1) >> 31;
+    b2 = s->ZMM_L(2) >> 31;
+    b3 = s->ZMM_L(3) >> 31;
     return b0 | (b1 << 1) | (b2 << 2) | (b3 << 3);
 }
 
@@ -1056,8 +1056,8 @@ uint32_t helper_movmskpd(CPUX86State *env, Reg *s)
 {
     int b0, b1;
 
-    b0 = s->XMM_L(1) >> 31;
-    b1 = s->XMM_L(3) >> 31;
+    b0 = s->ZMM_L(1) >> 31;
+    b1 = s->ZMM_L(3) >> 31;
     return b0 | (b1 << 1);
 }
 
@@ -1736,10 +1736,10 @@ void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->XMM_S(0) = float32_round_to_int(s->XMM_S(0), &env->sse_status);
-    d->XMM_S(1) = float32_round_to_int(s->XMM_S(1), &env->sse_status);
-    d->XMM_S(2) = float32_round_to_int(s->XMM_S(2), &env->sse_status);
-    d->XMM_S(3) = float32_round_to_int(s->XMM_S(3), &env->sse_status);
+    d->ZMM_S(0) = float32_round_to_int(s->ZMM_S(0), &env->sse_status);
+    d->ZMM_S(1) = float32_round_to_int(s->ZMM_S(1), &env->sse_status);
+    d->ZMM_S(2) = float32_round_to_int(s->ZMM_S(2), &env->sse_status);
+    d->ZMM_S(3) = float32_round_to_int(s->ZMM_S(3), &env->sse_status);
 
 #if 0 /* TODO */
     if (mode & (1 << 3)) {
@@ -1774,8 +1774,8 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->XMM_D(0) = float64_round_to_int(s->XMM_D(0), &env->sse_status);
-    d->XMM_D(1) = float64_round_to_int(s->XMM_D(1), &env->sse_status);
+    d->ZMM_D(0) = float64_round_to_int(s->ZMM_D(0), &env->sse_status);
+    d->ZMM_D(1) = float64_round_to_int(s->ZMM_D(1), &env->sse_status);
 
 #if 0 /* TODO */
     if (mode & (1 << 3)) {
@@ -1810,7 +1810,7 @@ void glue(helper_roundss, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->XMM_S(0) = float32_round_to_int(s->XMM_S(0), &env->sse_status);
+    d->ZMM_S(0) = float32_round_to_int(s->ZMM_S(0), &env->sse_status);
 
 #if 0 /* TODO */
     if (mode & (1 << 3)) {
@@ -1845,7 +1845,7 @@ void glue(helper_roundsd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
         }
     }
 
-    d->XMM_D(0) = float64_round_to_int(s->XMM_D(0), &env->sse_status);
+    d->ZMM_D(0) = float64_round_to_int(s->ZMM_D(0), &env->sse_status);
 
 #if 0 /* TODO */
     if (mode & (1 << 3)) {
@@ -1868,32 +1868,32 @@ void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
 
     if (mask & (1 << 4)) {
         iresult = float32_add(iresult,
-                              float32_mul(d->XMM_S(0), s->XMM_S(0),
+                              float32_mul(d->ZMM_S(0), s->ZMM_S(0),
                                           &env->sse_status),
                               &env->sse_status);
     }
     if (mask & (1 << 5)) {
         iresult = float32_add(iresult,
-                              float32_mul(d->XMM_S(1), s->XMM_S(1),
+                              float32_mul(d->ZMM_S(1), s->ZMM_S(1),
                                           &env->sse_status),
                               &env->sse_status);
     }
     if (mask & (1 << 6)) {
         iresult = float32_add(iresult,
-                              float32_mul(d->XMM_S(2), s->XMM_S(2),
+                              float32_mul(d->ZMM_S(2), s->ZMM_S(2),
                                           &env->sse_status),
                               &env->sse_status);
     }
     if (mask & (1 << 7)) {
         iresult = float32_add(iresult,
-                              float32_mul(d->XMM_S(3), s->XMM_S(3),
+                              float32_mul(d->ZMM_S(3), s->ZMM_S(3),
                                           &env->sse_status),
                               &env->sse_status);
     }
-    d->XMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
-    d->XMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
-    d->XMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
-    d->XMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
+    d->ZMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
+    d->ZMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
+    d->ZMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
+    d->ZMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
 }
 
 void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
@@ -1902,18 +1902,18 @@ void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
 
     if (mask & (1 << 4)) {
         iresult = float64_add(iresult,
-                              float64_mul(d->XMM_D(0), s->XMM_D(0),
+                              float64_mul(d->ZMM_D(0), s->ZMM_D(0),
                                           &env->sse_status),
                               &env->sse_status);
     }
     if (mask & (1 << 5)) {
         iresult = float64_add(iresult,
-                              float64_mul(d->XMM_D(1), s->XMM_D(1),
+                              float64_mul(d->ZMM_D(1), s->ZMM_D(1),
                                           &env->sse_status),
                               &env->sse_status);
     }
-    d->XMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
-    d->XMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
+    d->ZMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
+    d->ZMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
 }
 
 void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
diff --git a/target-i386/translate.c b/target-i386/translate.c
index 68dd9a075e..8ce0fcc0bd 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -2602,28 +2602,28 @@ static inline void gen_ldo_env_A0(DisasContext *s, int offset)
 {
     int mem_index = s->mem_index;
     tcg_gen_qemu_ld_i64(cpu_tmp1_i64, cpu_A0, mem_index, MO_LEQ);
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_Q(0)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(0)));
     tcg_gen_addi_tl(cpu_tmp0, cpu_A0, 8);
     tcg_gen_qemu_ld_i64(cpu_tmp1_i64, cpu_tmp0, mem_index, MO_LEQ);
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_Q(1)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(1)));
 }
 
 static inline void gen_sto_env_A0(DisasContext *s, int offset)
 {
     int mem_index = s->mem_index;
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_Q(0)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(0)));
     tcg_gen_qemu_st_i64(cpu_tmp1_i64, cpu_A0, mem_index, MO_LEQ);
     tcg_gen_addi_tl(cpu_tmp0, cpu_A0, 8);
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_Q(1)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(1)));
     tcg_gen_qemu_st_i64(cpu_tmp1_i64, cpu_tmp0, mem_index, MO_LEQ);
 }
 
 static inline void gen_op_movo(int d_offset, int s_offset)
 {
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(ZMMReg, XMM_Q(0)));
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(ZMMReg, XMM_Q(0)));
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(ZMMReg, XMM_Q(1)));
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(ZMMReg, XMM_Q(1)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(ZMMReg, ZMM_Q(0)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(ZMMReg, ZMM_Q(0)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(ZMMReg, ZMM_Q(1)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(ZMMReg, ZMM_Q(1)));
 }
 
 static inline void gen_op_movq(int d_offset, int s_offset)
@@ -3074,10 +3074,10 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             gen_lea_modrm(env, s, modrm);
             if (b1 & 1) {
                 gen_stq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 tcg_gen_ld32u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
-                    xmm_regs[reg].XMM_L(0)));
+                    xmm_regs[reg].ZMM_L(0)));
                 gen_op_st_v(s, MO_32, cpu_T[0], cpu_A0);
             }
             break;
@@ -3144,29 +3144,29 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_op_ld_v(s, MO_32, cpu_T[0], cpu_A0);
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)));
                 tcg_gen_movi_tl(cpu_T[0], 0);
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(1)));
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(2)));
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(3)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(1)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(2)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(3)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_L(0)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_L(0)));
             }
             break;
         case 0x310: /* movsd xmm, ea */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_ldq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
                 tcg_gen_movi_tl(cpu_T[0], 0);
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(2)));
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(3)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(2)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(3)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)));
             }
             break;
         case 0x012: /* movlps */
@@ -3174,12 +3174,12 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_ldq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 /* movhlps */
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_Q(1)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(1)));
             }
             break;
         case 0x212: /* movsldup */
@@ -3188,40 +3188,40 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                 gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_L(0)));
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(2)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_L(2)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_L(0)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(2)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_L(2)));
             }
-            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(1)),
-                        offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)));
-            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(3)),
-                        offsetof(CPUX86State,xmm_regs[reg].XMM_L(2)));
+            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(1)),
+                        offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)));
+            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(3)),
+                        offsetof(CPUX86State,xmm_regs[reg].ZMM_L(2)));
             break;
         case 0x312: /* movddup */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_ldq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)));
             }
-            gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(1)),
-                        offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)));
+            gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(1)),
+                        offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)));
             break;
         case 0x016: /* movhps */
         case 0x116: /* movhpd */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_ldq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(1)));
+                                           xmm_regs[reg].ZMM_Q(1)));
             } else {
                 /* movlhps */
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(1)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(1)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)));
             }
             break;
         case 0x216: /* movshdup */
@@ -3230,15 +3230,15 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                 gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(1)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_L(1)));
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(3)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_L(3)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(1)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_L(1)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(3)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_L(3)));
             }
-            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)),
-                        offsetof(CPUX86State,xmm_regs[reg].XMM_L(1)));
-            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].XMM_L(2)),
-                        offsetof(CPUX86State,xmm_regs[reg].XMM_L(3)));
+            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)),
+                        offsetof(CPUX86State,xmm_regs[reg].ZMM_L(1)));
+            gen_op_movl(offsetof(CPUX86State,xmm_regs[reg].ZMM_L(2)),
+                        offsetof(CPUX86State,xmm_regs[reg].ZMM_L(3)));
             break;
         case 0x178:
         case 0x378:
@@ -3279,13 +3279,13 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
 #ifdef TARGET_X86_64
             if (s->dflag == MO_64) {
                 tcg_gen_ld_i64(cpu_T[0], cpu_env, 
-                               offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)));
+                               offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)));
                 gen_ldst_modrm(env, s, modrm, MO_64, OR_TMP0, 1);
             } else
 #endif
             {
                 tcg_gen_ld32u_tl(cpu_T[0], cpu_env, 
-                                 offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)));
+                                 offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)));
                 gen_ldst_modrm(env, s, modrm, MO_32, OR_TMP0, 1);
             }
             break;
@@ -3293,13 +3293,13 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_ldq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)));
             }
-            gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(1)));
+            gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(1)));
             break;
         case 0x7f: /* movq ea, mm */
             if (mod != 3) {
@@ -3329,23 +3329,23 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
         case 0x211: /* movss ea, xmm */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
-                tcg_gen_ld32u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)));
+                tcg_gen_ld32u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)));
                 gen_op_st_v(s, MO_32, cpu_T[0], cpu_A0);
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movl(offsetof(CPUX86State,xmm_regs[rm].XMM_L(0)),
-                            offsetof(CPUX86State,xmm_regs[reg].XMM_L(0)));
+                gen_op_movl(offsetof(CPUX86State,xmm_regs[rm].ZMM_L(0)),
+                            offsetof(CPUX86State,xmm_regs[reg].ZMM_L(0)));
             }
             break;
         case 0x311: /* movsd ea, xmm */
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_stq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)));
             }
             break;
         case 0x013: /* movlps */
@@ -3353,7 +3353,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_stq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 goto illegal_op;
             }
@@ -3363,7 +3363,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_stq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(1)));
+                                           xmm_regs[reg].ZMM_Q(1)));
             } else {
                 goto illegal_op;
             }
@@ -3380,9 +3380,9 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             val = cpu_ldub_code(env, s->pc++);
             if (is_xmm) {
                 tcg_gen_movi_tl(cpu_T[0], val);
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.XMM_L(0)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.ZMM_L(0)));
                 tcg_gen_movi_tl(cpu_T[0], 0);
-                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.XMM_L(1)));
+                tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.ZMM_L(1)));
                 op1_offset = offsetof(CPUX86State,xmm_t0);
             } else {
                 tcg_gen_movi_tl(cpu_T[0], val);
@@ -3503,10 +3503,10 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 if ((b >> 8) & 1) {
-                    gen_ldq_env_A0(s, offsetof(CPUX86State, xmm_t0.XMM_Q(0)));
+                    gen_ldq_env_A0(s, offsetof(CPUX86State, xmm_t0.ZMM_Q(0)));
                 } else {
                     gen_op_ld_v(s, MO_32, cpu_T[0], cpu_A0);
-                    tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.XMM_L(0)));
+                    tcg_gen_st32_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,xmm_t0.ZMM_L(0)));
                 }
                 op2_offset = offsetof(CPUX86State,xmm_t0);
             } else {
@@ -3538,7 +3538,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (b1) {
                 val &= 7;
                 tcg_gen_st16_tl(cpu_T[0], cpu_env,
-                                offsetof(CPUX86State,xmm_regs[reg].XMM_W(val)));
+                                offsetof(CPUX86State,xmm_regs[reg].ZMM_W(val)));
             } else {
                 val &= 3;
                 tcg_gen_st16_tl(cpu_T[0], cpu_env,
@@ -3555,7 +3555,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                 val &= 7;
                 rm = (modrm & 7) | REX_B(s);
                 tcg_gen_ld16u_tl(cpu_T[0], cpu_env,
-                                 offsetof(CPUX86State,xmm_regs[rm].XMM_W(val)));
+                                 offsetof(CPUX86State,xmm_regs[rm].ZMM_W(val)));
             } else {
                 val &= 3;
                 rm = (modrm & 7);
@@ -3569,26 +3569,26 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
             if (mod != 3) {
                 gen_lea_modrm(env, s, modrm);
                 gen_stq_env_A0(s, offsetof(CPUX86State,
-                                           xmm_regs[reg].XMM_Q(0)));
+                                           xmm_regs[reg].ZMM_Q(0)));
             } else {
                 rm = (modrm & 7) | REX_B(s);
-                gen_op_movq(offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)),
-                            offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)));
-                gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[rm].XMM_Q(1)));
+                gen_op_movq(offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)),
+                            offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)));
+                gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(1)));
             }
             break;
         case 0x2d6: /* movq2dq */
             gen_helper_enter_mmx(cpu_env);
             rm = (modrm & 7);
-            gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(0)),
+            gen_op_movq(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(0)),
                         offsetof(CPUX86State,fpregs[rm].mmx));
-            gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[reg].XMM_Q(1)));
+            gen_op_movq_env_0(offsetof(CPUX86State,xmm_regs[reg].ZMM_Q(1)));
             break;
         case 0x3d6: /* movdq2q */
             gen_helper_enter_mmx(cpu_env);
             rm = (modrm & 7) | REX_B(s);
             gen_op_movq(offsetof(CPUX86State,fpregs[reg & 7].mmx),
-                        offsetof(CPUX86State,xmm_regs[rm].XMM_Q(0)));
+                        offsetof(CPUX86State,xmm_regs[rm].ZMM_Q(0)));
             break;
         case 0xd7: /* pmovmskb */
         case 0x1d7:
@@ -3640,20 +3640,20 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     case 0x23: case 0x33: /* pmovsxwd, pmovzxwd */
                     case 0x25: case 0x35: /* pmovsxdq, pmovzxdq */
                         gen_ldq_env_A0(s, op2_offset +
-                                        offsetof(ZMMReg, XMM_Q(0)));
+                                        offsetof(ZMMReg, ZMM_Q(0)));
                         break;
                     case 0x21: case 0x31: /* pmovsxbd, pmovzxbd */
                     case 0x24: case 0x34: /* pmovsxwq, pmovzxwq */
                         tcg_gen_qemu_ld_i32(cpu_tmp2_i32, cpu_A0,
                                             s->mem_index, MO_LEUL);
                         tcg_gen_st_i32(cpu_tmp2_i32, cpu_env, op2_offset +
-                                        offsetof(ZMMReg, XMM_L(0)));
+                                        offsetof(ZMMReg, ZMM_L(0)));
                         break;
                     case 0x22: case 0x32: /* pmovsxbq, pmovzxbq */
                         tcg_gen_qemu_ld_tl(cpu_tmp0, cpu_A0,
                                            s->mem_index, MO_LEUW);
                         tcg_gen_st16_tl(cpu_tmp0, cpu_env, op2_offset +
-                                        offsetof(ZMMReg, XMM_W(0)));
+                                        offsetof(ZMMReg, ZMM_W(0)));
                         break;
                     case 0x2a:            /* movntqda */
                         gen_ldo_env_A0(s, op1_offset);
@@ -4078,7 +4078,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                 switch (b) {
                 case 0x14: /* pextrb */
                     tcg_gen_ld8u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
-                                            xmm_regs[reg].XMM_B(val & 15)));
+                                            xmm_regs[reg].ZMM_B(val & 15)));
                     if (mod == 3) {
                         gen_op_mov_reg_v(ot, rm, cpu_T[0]);
                     } else {
@@ -4088,7 +4088,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     break;
                 case 0x15: /* pextrw */
                     tcg_gen_ld16u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
-                                            xmm_regs[reg].XMM_W(val & 7)));
+                                            xmm_regs[reg].ZMM_W(val & 7)));
                     if (mod == 3) {
                         gen_op_mov_reg_v(ot, rm, cpu_T[0]);
                     } else {
@@ -4100,7 +4100,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     if (ot == MO_32) { /* pextrd */
                         tcg_gen_ld_i32(cpu_tmp2_i32, cpu_env,
                                         offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(val & 3)));
+                                                xmm_regs[reg].ZMM_L(val & 3)));
                         if (mod == 3) {
                             tcg_gen_extu_i32_tl(cpu_regs[rm], cpu_tmp2_i32);
                         } else {
@@ -4111,7 +4111,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
 #ifdef TARGET_X86_64
                         tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env,
                                         offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_Q(val & 1)));
+                                                xmm_regs[reg].ZMM_Q(val & 1)));
                         if (mod == 3) {
                             tcg_gen_mov_i64(cpu_regs[rm], cpu_tmp1_i64);
                         } else {
@@ -4125,7 +4125,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     break;
                 case 0x17: /* extractps */
                     tcg_gen_ld32u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
-                                            xmm_regs[reg].XMM_L(val & 3)));
+                                            xmm_regs[reg].ZMM_L(val & 3)));
                     if (mod == 3) {
                         gen_op_mov_reg_v(ot, rm, cpu_T[0]);
                     } else {
@@ -4141,36 +4141,36 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                                            s->mem_index, MO_UB);
                     }
                     tcg_gen_st8_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
-                                            xmm_regs[reg].XMM_B(val & 15)));
+                                            xmm_regs[reg].ZMM_B(val & 15)));
                     break;
                 case 0x21: /* insertps */
                     if (mod == 3) {
                         tcg_gen_ld_i32(cpu_tmp2_i32, cpu_env,
                                         offsetof(CPUX86State,xmm_regs[rm]
-                                                .XMM_L((val >> 6) & 3)));
+                                                .ZMM_L((val >> 6) & 3)));
                     } else {
                         tcg_gen_qemu_ld_i32(cpu_tmp2_i32, cpu_A0,
                                             s->mem_index, MO_LEUL);
                     }
                     tcg_gen_st_i32(cpu_tmp2_i32, cpu_env,
                                     offsetof(CPUX86State,xmm_regs[reg]
-                                            .XMM_L((val >> 4) & 3)));
+                                            .ZMM_L((val >> 4) & 3)));
                     if ((val >> 0) & 1)
                         tcg_gen_st_i32(tcg_const_i32(0 /*float32_zero*/),
                                         cpu_env, offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(0)));
+                                                xmm_regs[reg].ZMM_L(0)));
                     if ((val >> 1) & 1)
                         tcg_gen_st_i32(tcg_const_i32(0 /*float32_zero*/),
                                         cpu_env, offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(1)));
+                                                xmm_regs[reg].ZMM_L(1)));
                     if ((val >> 2) & 1)
                         tcg_gen_st_i32(tcg_const_i32(0 /*float32_zero*/),
                                         cpu_env, offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(2)));
+                                                xmm_regs[reg].ZMM_L(2)));
                     if ((val >> 3) & 1)
                         tcg_gen_st_i32(tcg_const_i32(0 /*float32_zero*/),
                                         cpu_env, offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(3)));
+                                                xmm_regs[reg].ZMM_L(3)));
                     break;
                 case 0x22:
                     if (ot == MO_32) { /* pinsrd */
@@ -4182,7 +4182,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                         }
                         tcg_gen_st_i32(cpu_tmp2_i32, cpu_env,
                                         offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_L(val & 3)));
+                                                xmm_regs[reg].ZMM_L(val & 3)));
                     } else { /* pinsrq */
 #ifdef TARGET_X86_64
                         if (mod == 3) {
@@ -4193,7 +4193,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                         }
                         tcg_gen_st_i64(cpu_tmp1_i64, cpu_env,
                                         offsetof(CPUX86State,
-                                                xmm_regs[reg].XMM_Q(val & 1)));
+                                                xmm_regs[reg].ZMM_Q(val & 1)));
 #else
                         goto illegal_op;
 #endif
@@ -4318,11 +4318,11 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                     /* 32 bit access */
                     gen_op_ld_v(s, MO_32, cpu_T[0], cpu_A0);
                     tcg_gen_st32_tl(cpu_T[0], cpu_env,
-                                    offsetof(CPUX86State,xmm_t0.XMM_L(0)));
+                                    offsetof(CPUX86State,xmm_t0.ZMM_L(0)));
                     break;
                 case 3:
                     /* 64 bit access */
-                    gen_ldq_env_A0(s, offsetof(CPUX86State, xmm_t0.XMM_D(0)));
+                    gen_ldq_env_A0(s, offsetof(CPUX86State, xmm_t0.ZMM_D(0)));
                     break;
                 default:
                     /* 128 bit access */