diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 15e325ee75..372814c5f9 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -732,7 +732,7 @@ typedef union {
     uint64_t _q[8];
     float32 _s[16];
     float64 _d[8];
-} XMMReg; /* really zmm */
+} ZMMReg;
 
 typedef union {
     uint8_t _b[8];
@@ -865,8 +865,8 @@ typedef struct CPUX86State {
     float_status mmx_status; /* for 3DNow! float ops */
     float_status sse_status;
     uint32_t mxcsr;
-    XMMReg xmm_regs[CPU_NB_REGS == 8 ? 8 : 32];
-    XMMReg xmm_t0;
+    ZMMReg xmm_regs[CPU_NB_REGS == 8 ? 8 : 32];
+    ZMMReg xmm_t0;
     MMXReg mmx_t0;
 
     uint64_t opmask_regs[NB_OPMASK_REGS];
diff --git a/target-i386/machine.c b/target-i386/machine.c
index 6126d96d7f..6ea29a41af 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -36,15 +36,15 @@ static const VMStateDescription vmstate_xmm_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(0), XMMReg),
-        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_UINT64(XMM_Q(0), ZMMReg),
+        VMSTATE_UINT64(XMM_Q(1), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
 
 #define VMSTATE_XMM_REGS(_field, _state, _start)                         \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
-                             vmstate_xmm_reg, XMMReg)
+                             vmstate_xmm_reg, ZMMReg)
 
 /* YMMH format is the same as XMM, but for bits 128-255 */
 static const VMStateDescription vmstate_ymmh_reg = {
@@ -52,32 +52,32 @@ static const VMStateDescription vmstate_ymmh_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(2), XMMReg),
-        VMSTATE_UINT64(XMM_Q(3), XMMReg),
+        VMSTATE_UINT64(XMM_Q(2), ZMMReg),
+        VMSTATE_UINT64(XMM_Q(3), ZMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
 
 #define VMSTATE_YMMH_REGS_VARS(_field, _state, _start, _v)               \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, _v,    \
-                             vmstate_ymmh_reg, XMMReg)
+                             vmstate_ymmh_reg, ZMMReg)
 
 static const VMStateDescription vmstate_zmmh_reg = {
     .name = "zmmh_reg",
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(4), XMMReg),
-        VMSTATE_UINT64(XMM_Q(5), XMMReg),
-        VMSTATE_UINT64(XMM_Q(6), XMMReg),
-        VMSTATE_UINT64(XMM_Q(7), XMMReg),
+        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_END_OF_LIST()
     }
 };
 
 #define VMSTATE_ZMMH_REGS_VARS(_field, _state, _start)                   \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
-                             vmstate_zmmh_reg, XMMReg)
+                             vmstate_zmmh_reg, ZMMReg)
 
 #ifdef TARGET_X86_64
 static const VMStateDescription vmstate_hi16_zmm_reg = {
@@ -85,21 +85,21 @@ static const VMStateDescription vmstate_hi16_zmm_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(0), XMMReg),
-        VMSTATE_UINT64(XMM_Q(1), XMMReg),
-        VMSTATE_UINT64(XMM_Q(2), XMMReg),
-        VMSTATE_UINT64(XMM_Q(3), XMMReg),
-        VMSTATE_UINT64(XMM_Q(4), XMMReg),
-        VMSTATE_UINT64(XMM_Q(5), XMMReg),
-        VMSTATE_UINT64(XMM_Q(6), XMMReg),
-        VMSTATE_UINT64(XMM_Q(7), XMMReg),
+        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_END_OF_LIST()
     }
 };
 
 #define VMSTATE_Hi16_ZMM_REGS_VARS(_field, _state, _start)               \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
-                             vmstate_hi16_zmm_reg, XMMReg)
+                             vmstate_hi16_zmm_reg, ZMMReg)
 #endif
 
 static const VMStateDescription vmstate_bnd_regs = {
diff --git a/target-i386/ops_sse.h b/target-i386/ops_sse.h
index 52ec0b07f8..b0820e731a 100644
--- a/target-i386/ops_sse.h
+++ b/target-i386/ops_sse.h
@@ -29,7 +29,7 @@
 #define Q(n) MMX_Q(n)
 #define SUFFIX _mmx
 #else
-#define Reg XMMReg
+#define Reg ZMMReg
 #define XMM_ONLY(...) __VA_ARGS__
 #define B(n) XMM_B(n)
 #define W(n) XMM_W(n)
@@ -675,42 +675,42 @@ void helper_cvtdq2pd(CPUX86State *env, Reg *d, Reg *s)
     d->XMM_D(1) = int32_to_float64(l1, &env->sse_status);
 }
 
-void helper_cvtpi2ps(CPUX86State *env, XMMReg *d, MMXReg *s)
+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);
 }
 
-void helper_cvtpi2pd(CPUX86State *env, XMMReg *d, MMXReg *s)
+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);
 }
 
-void helper_cvtsi2ss(CPUX86State *env, XMMReg *d, uint32_t val)
+void helper_cvtsi2ss(CPUX86State *env, ZMMReg *d, uint32_t val)
 {
     d->XMM_S(0) = int32_to_float32(val, &env->sse_status);
 }
 
-void helper_cvtsi2sd(CPUX86State *env, XMMReg *d, uint32_t val)
+void helper_cvtsi2sd(CPUX86State *env, ZMMReg *d, uint32_t val)
 {
     d->XMM_D(0) = int32_to_float64(val, &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
-void helper_cvtsq2ss(CPUX86State *env, XMMReg *d, uint64_t val)
+void helper_cvtsq2ss(CPUX86State *env, ZMMReg *d, uint64_t val)
 {
     d->XMM_S(0) = int64_to_float32(val, &env->sse_status);
 }
 
-void helper_cvtsq2sd(CPUX86State *env, XMMReg *d, uint64_t val)
+void helper_cvtsq2sd(CPUX86State *env, ZMMReg *d, uint64_t val)
 {
     d->XMM_D(0) = int64_to_float64(val, &env->sse_status);
 }
 #endif
 
 /* float to integer */
-void helper_cvtps2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
+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);
@@ -718,49 +718,49 @@ void helper_cvtps2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
     d->XMM_L(3) = float32_to_int32(s->XMM_S(3), &env->sse_status);
 }
 
-void helper_cvtpd2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
+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;
 }
 
-void helper_cvtps2pi(CPUX86State *env, MMXReg *d, XMMReg *s)
+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);
 }
 
-void helper_cvtpd2pi(CPUX86State *env, MMXReg *d, XMMReg *s)
+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);
 }
 
-int32_t helper_cvtss2si(CPUX86State *env, XMMReg *s)
+int32_t helper_cvtss2si(CPUX86State *env, ZMMReg *s)
 {
     return float32_to_int32(s->XMM_S(0), &env->sse_status);
 }
 
-int32_t helper_cvtsd2si(CPUX86State *env, XMMReg *s)
+int32_t helper_cvtsd2si(CPUX86State *env, ZMMReg *s)
 {
     return float64_to_int32(s->XMM_D(0), &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
-int64_t helper_cvtss2sq(CPUX86State *env, XMMReg *s)
+int64_t helper_cvtss2sq(CPUX86State *env, ZMMReg *s)
 {
     return float32_to_int64(s->XMM_S(0), &env->sse_status);
 }
 
-int64_t helper_cvtsd2sq(CPUX86State *env, XMMReg *s)
+int64_t helper_cvtsd2sq(CPUX86State *env, ZMMReg *s)
 {
     return float64_to_int64(s->XMM_D(0), &env->sse_status);
 }
 #endif
 
 /* float to integer truncated */
-void helper_cvttps2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
+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);
@@ -768,48 +768,48 @@ void helper_cvttps2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
     d->XMM_L(3) = float32_to_int32_round_to_zero(s->XMM_S(3), &env->sse_status);
 }
 
-void helper_cvttpd2dq(CPUX86State *env, XMMReg *d, XMMReg *s)
+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;
 }
 
-void helper_cvttps2pi(CPUX86State *env, MMXReg *d, XMMReg *s)
+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);
 }
 
-void helper_cvttpd2pi(CPUX86State *env, MMXReg *d, XMMReg *s)
+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);
 }
 
-int32_t helper_cvttss2si(CPUX86State *env, XMMReg *s)
+int32_t helper_cvttss2si(CPUX86State *env, ZMMReg *s)
 {
     return float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
 }
 
-int32_t helper_cvttsd2si(CPUX86State *env, XMMReg *s)
+int32_t helper_cvttsd2si(CPUX86State *env, ZMMReg *s)
 {
     return float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
 }
 
 #ifdef TARGET_X86_64
-int64_t helper_cvttss2sq(CPUX86State *env, XMMReg *s)
+int64_t helper_cvttss2sq(CPUX86State *env, ZMMReg *s)
 {
     return float32_to_int64_round_to_zero(s->XMM_S(0), &env->sse_status);
 }
 
-int64_t helper_cvttsd2sq(CPUX86State *env, XMMReg *s)
+int64_t helper_cvttsd2sq(CPUX86State *env, ZMMReg *s)
 {
     return float64_to_int64_round_to_zero(s->XMM_D(0), &env->sse_status);
 }
 #endif
 
-void helper_rsqrtps(CPUX86State *env, XMMReg *d, XMMReg *s)
+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),
@@ -825,14 +825,14 @@ void helper_rsqrtps(CPUX86State *env, XMMReg *d, XMMReg *s)
                               &env->sse_status);
 }
 
-void helper_rsqrtss(CPUX86State *env, XMMReg *d, XMMReg *s)
+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),
                               &env->sse_status);
 }
 
-void helper_rcpps(CPUX86State *env, XMMReg *d, XMMReg *s)
+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);
@@ -840,7 +840,7 @@ void helper_rcpps(CPUX86State *env, XMMReg *d, XMMReg *s)
     d->XMM_S(3) = float32_div(float32_one, s->XMM_S(3), &env->sse_status);
 }
 
-void helper_rcpss(CPUX86State *env, XMMReg *d, XMMReg *s)
+void helper_rcpss(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
     d->XMM_S(0) = float32_div(float32_one, s->XMM_S(0), &env->sse_status);
 }
@@ -857,12 +857,12 @@ static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
     return (src >> shift) & mask;
 }
 
-void helper_extrq_r(CPUX86State *env, XMMReg *d, XMMReg *s)
+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));
 }
 
-void helper_extrq_i(CPUX86State *env, XMMReg *d, int index, int length)
+void helper_extrq_i(CPUX86State *env, ZMMReg *d, int index, int length)
 {
     d->XMM_Q(0) = helper_extrq(d->XMM_Q(0), index, length);
 }
@@ -879,19 +879,19 @@ static inline uint64_t helper_insertq(uint64_t src, int shift, int len)
     return (src & ~(mask << shift)) | ((src & mask) << shift);
 }
 
-void helper_insertq_r(CPUX86State *env, XMMReg *d, XMMReg *s)
+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));
 }
 
-void helper_insertq_i(CPUX86State *env, XMMReg *d, int index, int length)
+void helper_insertq_i(CPUX86State *env, ZMMReg *d, int index, int length)
 {
     d->XMM_Q(0) = helper_insertq(d->XMM_Q(0), index, length);
 }
 
-void helper_haddps(CPUX86State *env, XMMReg *d, XMMReg *s)
+void helper_haddps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    XMMReg r;
+    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);
@@ -900,18 +900,18 @@ void helper_haddps(CPUX86State *env, XMMReg *d, XMMReg *s)
     *d = r;
 }
 
-void helper_haddpd(CPUX86State *env, XMMReg *d, XMMReg *s)
+void helper_haddpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    XMMReg r;
+    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);
     *d = r;
 }
 
-void helper_hsubps(CPUX86State *env, XMMReg *d, XMMReg *s)
+void helper_hsubps(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    XMMReg r;
+    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);
@@ -920,16 +920,16 @@ void helper_hsubps(CPUX86State *env, XMMReg *d, XMMReg *s)
     *d = r;
 }
 
-void helper_hsubpd(CPUX86State *env, XMMReg *d, XMMReg *s)
+void helper_hsubpd(CPUX86State *env, ZMMReg *d, ZMMReg *s)
 {
-    XMMReg r;
+    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);
     *d = r;
 }
 
-void helper_addsubps(CPUX86State *env, XMMReg *d, XMMReg *s)
+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);
@@ -937,7 +937,7 @@ void helper_addsubps(CPUX86State *env, XMMReg *d, XMMReg *s)
     d->XMM_S(3) = float32_add(d->XMM_S(3), s->XMM_S(3), &env->sse_status);
 }
 
-void helper_addsubpd(CPUX86State *env, XMMReg *d, XMMReg *s)
+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);
diff --git a/target-i386/ops_sse_header.h b/target-i386/ops_sse_header.h
index a68c7cc0c9..64c5857cf4 100644
--- a/target-i386/ops_sse_header.h
+++ b/target-i386/ops_sse_header.h
@@ -20,18 +20,18 @@
 #define Reg MMXReg
 #define SUFFIX _mmx
 #else
-#define Reg XMMReg
+#define Reg ZMMReg
 #define SUFFIX _xmm
 #endif
 
 #define dh_alias_Reg ptr
-#define dh_alias_XMMReg ptr
+#define dh_alias_ZMMReg ptr
 #define dh_alias_MMXReg ptr
 #define dh_ctype_Reg Reg *
-#define dh_ctype_XMMReg XMMReg *
+#define dh_ctype_ZMMReg ZMMReg *
 #define dh_ctype_MMXReg MMXReg *
 #define dh_is_signed_Reg dh_is_signed_ptr
-#define dh_is_signed_XMMReg dh_is_signed_ptr
+#define dh_is_signed_ZMMReg dh_is_signed_ptr
 #define dh_is_signed_MMXReg dh_is_signed_ptr
 
 DEF_HELPER_3(glue(psrlw, SUFFIX), void, env, Reg, Reg)
@@ -154,52 +154,52 @@ DEF_HELPER_3(cvtss2sd, void, env, Reg, Reg)
 DEF_HELPER_3(cvtsd2ss, void, env, Reg, Reg)
 DEF_HELPER_3(cvtdq2ps, void, env, Reg, Reg)
 DEF_HELPER_3(cvtdq2pd, void, env, Reg, Reg)
-DEF_HELPER_3(cvtpi2ps, void, env, XMMReg, MMXReg)
-DEF_HELPER_3(cvtpi2pd, void, env, XMMReg, MMXReg)
-DEF_HELPER_3(cvtsi2ss, void, env, XMMReg, i32)
-DEF_HELPER_3(cvtsi2sd, void, env, XMMReg, i32)
+DEF_HELPER_3(cvtpi2ps, void, env, ZMMReg, MMXReg)
+DEF_HELPER_3(cvtpi2pd, void, env, ZMMReg, MMXReg)
+DEF_HELPER_3(cvtsi2ss, void, env, ZMMReg, i32)
+DEF_HELPER_3(cvtsi2sd, void, env, ZMMReg, i32)
 
 #ifdef TARGET_X86_64
-DEF_HELPER_3(cvtsq2ss, void, env, XMMReg, i64)
-DEF_HELPER_3(cvtsq2sd, void, env, XMMReg, i64)
+DEF_HELPER_3(cvtsq2ss, void, env, ZMMReg, i64)
+DEF_HELPER_3(cvtsq2sd, void, env, ZMMReg, i64)
 #endif
 
-DEF_HELPER_3(cvtps2dq, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(cvtpd2dq, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(cvtps2pi, void, env, MMXReg, XMMReg)
-DEF_HELPER_3(cvtpd2pi, void, env, MMXReg, XMMReg)
-DEF_HELPER_2(cvtss2si, s32, env, XMMReg)
-DEF_HELPER_2(cvtsd2si, s32, env, XMMReg)
+DEF_HELPER_3(cvtps2dq, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(cvtpd2dq, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(cvtps2pi, void, env, MMXReg, ZMMReg)
+DEF_HELPER_3(cvtpd2pi, void, env, MMXReg, ZMMReg)
+DEF_HELPER_2(cvtss2si, s32, env, ZMMReg)
+DEF_HELPER_2(cvtsd2si, s32, env, ZMMReg)
 #ifdef TARGET_X86_64
-DEF_HELPER_2(cvtss2sq, s64, env, XMMReg)
-DEF_HELPER_2(cvtsd2sq, s64, env, XMMReg)
+DEF_HELPER_2(cvtss2sq, s64, env, ZMMReg)
+DEF_HELPER_2(cvtsd2sq, s64, env, ZMMReg)
 #endif
 
-DEF_HELPER_3(cvttps2dq, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(cvttpd2dq, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(cvttps2pi, void, env, MMXReg, XMMReg)
-DEF_HELPER_3(cvttpd2pi, void, env, MMXReg, XMMReg)
-DEF_HELPER_2(cvttss2si, s32, env, XMMReg)
-DEF_HELPER_2(cvttsd2si, s32, env, XMMReg)
+DEF_HELPER_3(cvttps2dq, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(cvttpd2dq, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(cvttps2pi, void, env, MMXReg, ZMMReg)
+DEF_HELPER_3(cvttpd2pi, void, env, MMXReg, ZMMReg)
+DEF_HELPER_2(cvttss2si, s32, env, ZMMReg)
+DEF_HELPER_2(cvttsd2si, s32, env, ZMMReg)
 #ifdef TARGET_X86_64
-DEF_HELPER_2(cvttss2sq, s64, env, XMMReg)
-DEF_HELPER_2(cvttsd2sq, s64, env, XMMReg)
+DEF_HELPER_2(cvttss2sq, s64, env, ZMMReg)
+DEF_HELPER_2(cvttsd2sq, s64, env, ZMMReg)
 #endif
 
-DEF_HELPER_3(rsqrtps, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(rsqrtss, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(rcpps, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(rcpss, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(extrq_r, void, env, XMMReg, XMMReg)
-DEF_HELPER_4(extrq_i, void, env, XMMReg, int, int)
-DEF_HELPER_3(insertq_r, void, env, XMMReg, XMMReg)
-DEF_HELPER_4(insertq_i, void, env, XMMReg, int, int)
-DEF_HELPER_3(haddps, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(haddpd, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(hsubps, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(hsubpd, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(addsubps, void, env, XMMReg, XMMReg)
-DEF_HELPER_3(addsubpd, void, env, XMMReg, XMMReg)
+DEF_HELPER_3(rsqrtps, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(rsqrtss, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(rcpps, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(rcpss, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(extrq_r, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_4(extrq_i, void, env, ZMMReg, int, int)
+DEF_HELPER_3(insertq_r, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_4(insertq_i, void, env, ZMMReg, int, int)
+DEF_HELPER_3(haddps, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(haddpd, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(hsubps, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(hsubpd, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(addsubps, void, env, ZMMReg, ZMMReg)
+DEF_HELPER_3(addsubpd, void, env, ZMMReg, ZMMReg)
 
 #define SSE_HELPER_CMP(name, F)                           \
     DEF_HELPER_3(name ## ps, void, env, Reg, Reg)         \
diff --git a/target-i386/translate.c b/target-i386/translate.c
index d52f5081ba..68dd9a075e 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(XMMReg, XMM_Q(0)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_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(XMMReg, XMM_Q(1)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_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(XMMReg, XMM_Q(0)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_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(XMMReg, XMM_Q(1)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, offset + offsetof(ZMMReg, XMM_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(XMMReg, XMM_Q(0)));
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(1)));
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(1)));
+    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)));
 }
 
 static inline void gen_op_movq(int d_offset, int s_offset)
@@ -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(XMMReg, XMM_Q(0)));
+                                        offsetof(ZMMReg, XMM_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(XMMReg, XMM_L(0)));
+                                        offsetof(ZMMReg, XMM_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(XMMReg, XMM_W(0)));
+                                        offsetof(ZMMReg, XMM_W(0)));
                         break;
                     case 0x2a:            /* movntqda */
                         gen_ldo_env_A0(s, op1_offset);