#include "cpu.h"
#include "exec/tb-context.h"
#include "qemu/bitops.h"
+#include "qemu/queue.h"
#include "tcg-mo.h"
#include "tcg-target.h"
#else
#define MAX_OPC_PARAM_PER_ARG 1
#endif
-#define MAX_OPC_PARAM_IARGS 5
+#define MAX_OPC_PARAM_IARGS 6
#define MAX_OPC_PARAM_OARGS 1
#define MAX_OPC_PARAM_ARGS (MAX_OPC_PARAM_IARGS + MAX_OPC_PARAM_OARGS)
* and up to 4 + N parameters on 64-bit archs
* (N = number of input arguments + output arguments). */
#define MAX_OPC_PARAM (4 + (MAX_OPC_PARAM_PER_ARG * MAX_OPC_PARAM_ARGS))
-#define OPC_BUF_SIZE 640
-#define OPC_MAX_SIZE (OPC_BUF_SIZE - MAX_OP_PER_INSTR)
#define CPU_TEMP_BUF_NLONGS 128
# error "Missing unsigned widening multiply"
#endif
+#if !defined(TCG_TARGET_HAS_v64) \
+ && !defined(TCG_TARGET_HAS_v128) \
+ && !defined(TCG_TARGET_HAS_v256)
+#define TCG_TARGET_MAYBE_vec 0
+#define TCG_TARGET_HAS_neg_vec 0
+#define TCG_TARGET_HAS_not_vec 0
+#define TCG_TARGET_HAS_andc_vec 0
+#define TCG_TARGET_HAS_orc_vec 0
+#define TCG_TARGET_HAS_shi_vec 0
+#define TCG_TARGET_HAS_shs_vec 0
+#define TCG_TARGET_HAS_shv_vec 0
+#define TCG_TARGET_HAS_mul_vec 0
+#else
+#define TCG_TARGET_MAYBE_vec 1
+#endif
+#ifndef TCG_TARGET_HAS_v64
+#define TCG_TARGET_HAS_v64 0
+#endif
+#ifndef TCG_TARGET_HAS_v128
+#define TCG_TARGET_HAS_v128 0
+#endif
+#ifndef TCG_TARGET_HAS_v256
+#define TCG_TARGET_HAS_v256 0
+#endif
+
#ifndef TARGET_INSN_START_EXTRA_WORDS
# define TARGET_INSN_START_WORDS 1
#else
typedef enum TCGType {
TCG_TYPE_I32,
TCG_TYPE_I64,
+
+ TCG_TYPE_V64,
+ TCG_TYPE_V128,
+ TCG_TYPE_V256,
+
TCG_TYPE_COUNT, /* number of different types */
/* An alias for the size of the host register. */
* TCGv_i32 : 32 bit integer type
* TCGv_i64 : 64 bit integer type
* TCGv_ptr : a host pointer type
+ * TCGv_vec : a host vector type; the exact size is not exposed
+ to the CPU front-end code.
* TCGv : an integer type the same size as target_ulong
(an alias for either TCGv_i32 or TCGv_i64)
The compiler's type checking will complain if you mix them
integers, but keeping them in pointer types like this means that the
compiler will complain if you accidentally pass a TCGv_i32 to a
function which takes a TCGv_i64, and so on. Only the internals of
- TCG need to care about the actual contents of the types, and they always
- box and unbox via the MAKE_TCGV_* and GET_TCGV_* functions.
- Converting to and from intptr_t rather than int reduces the number
- of sign-extension instructions that get implied on 64-bit hosts. */
+ TCG need to care about the actual contents of the types. */
typedef struct TCGv_i32_d *TCGv_i32;
typedef struct TCGv_i64_d *TCGv_i64;
typedef struct TCGv_ptr_d *TCGv_ptr;
+typedef struct TCGv_vec_d *TCGv_vec;
typedef TCGv_ptr TCGv_env;
#if TARGET_LONG_BITS == 32
#define TCGv TCGv_i32
#error Unhandled TARGET_LONG_BITS value
#endif
-static inline TCGv_i32 QEMU_ARTIFICIAL MAKE_TCGV_I32(intptr_t i)
-{
- return (TCGv_i32)i;
-}
-
-static inline TCGv_i64 QEMU_ARTIFICIAL MAKE_TCGV_I64(intptr_t i)
-{
- return (TCGv_i64)i;
-}
-
-static inline TCGv_ptr QEMU_ARTIFICIAL MAKE_TCGV_PTR(intptr_t i)
-{
- return (TCGv_ptr)i;
-}
-
-static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_I32(TCGv_i32 t)
-{
- return (intptr_t)t;
-}
-
-static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_I64(TCGv_i64 t)
-{
- return (intptr_t)t;
-}
-
-static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_PTR(TCGv_ptr t)
-{
- return (intptr_t)t;
-}
-
-#if TCG_TARGET_REG_BITS == 32
-#define TCGV_LOW(t) MAKE_TCGV_I32(GET_TCGV_I64(t))
-#define TCGV_HIGH(t) MAKE_TCGV_I32(GET_TCGV_I64(t) + 1)
-#endif
-
-#define TCGV_EQUAL_I32(a, b) (GET_TCGV_I32(a) == GET_TCGV_I32(b))
-#define TCGV_EQUAL_I64(a, b) (GET_TCGV_I64(a) == GET_TCGV_I64(b))
-#define TCGV_EQUAL_PTR(a, b) (GET_TCGV_PTR(a) == GET_TCGV_PTR(b))
-
-/* Dummy definition to avoid compiler warnings. */
-#define TCGV_UNUSED_I32(x) x = MAKE_TCGV_I32(-1)
-#define TCGV_UNUSED_I64(x) x = MAKE_TCGV_I64(-1)
-#define TCGV_UNUSED_PTR(x) x = MAKE_TCGV_PTR(-1)
-
-#define TCGV_IS_UNUSED_I32(x) (GET_TCGV_I32(x) == -1)
-#define TCGV_IS_UNUSED_I64(x) (GET_TCGV_I64(x) == -1)
-#define TCGV_IS_UNUSED_PTR(x) (GET_TCGV_PTR(x) == -1)
-
/* call flags */
/* Helper does not read globals (either directly or through an exception). It
implies TCG_CALL_NO_WRITE_GLOBALS. */
#define TCG_CALL_NO_RWG_SE (TCG_CALL_NO_RWG | TCG_CALL_NO_SE)
#define TCG_CALL_NO_WG_SE (TCG_CALL_NO_WG | TCG_CALL_NO_SE)
-/* used to align parameters */
-#define TCG_CALL_DUMMY_ARG ((TCGArg)(-1))
+/* Used to align parameters. See the comment before tcgv_i32_temp. */
+#define TCG_CALL_DUMMY_ARG ((TCGArg)0)
/* Conditions. Note that these are laid out for easy manipulation by
the functions below:
return c & 2 ? (TCGCond)(c ^ 6) : c;
}
+/* Create a "signed" version of an "unsigned" comparison. */
+static inline TCGCond tcg_signed_cond(TCGCond c)
+{
+ return c & 4 ? (TCGCond)(c ^ 6) : c;
+}
+
/* Must a comparison be considered unsigned? */
static inline bool is_unsigned_cond(TCGCond c)
{
typedef struct TCGOp {
TCGOpcode opc : 8; /* 8 */
- /* The number of out and in parameter for a call. */
- unsigned calli : 4; /* 12 */
- unsigned callo : 2; /* 14 */
- unsigned : 2; /* 16 */
-
- /* Index of the prev/next op, or 0 for the end of the list. */
- unsigned prev : 16; /* 32 */
- unsigned next : 16; /* 48 */
+ /* Parameters for this opcode. See below. */
+ unsigned param1 : 4; /* 12 */
+ unsigned param2 : 4; /* 16 */
/* Lifetime data of the operands. */
- unsigned life : 16; /* 64 */
+ unsigned life : 16; /* 32 */
+
+ /* Next and previous opcodes. */
+ QTAILQ_ENTRY(TCGOp) link;
/* Arguments for the opcode. */
TCGArg args[MAX_OPC_PARAM];
} TCGOp;
-/* Make sure that we don't expand the structure without noticing. */
-QEMU_BUILD_BUG_ON(sizeof(TCGOp) != 8 + sizeof(TCGArg) * MAX_OPC_PARAM);
+#define TCGOP_CALLI(X) (X)->param1
+#define TCGOP_CALLO(X) (X)->param2
+
+#define TCGOP_VECL(X) (X)->param1
+#define TCGOP_VECE(X) (X)->param2
/* Make sure operands fit in the bitfields above. */
QEMU_BUILD_BUG_ON(NB_OPS > (1 << 8));
-QEMU_BUILD_BUG_ON(OPC_BUF_SIZE > (1 << 16));
+
+typedef struct TCGProfile {
+ int64_t tb_count1;
+ int64_t tb_count;
+ int64_t op_count; /* total insn count */
+ int op_count_max; /* max insn per TB */
+ int64_t temp_count;
+ int temp_count_max;
+ int64_t del_op_count;
+ int64_t code_in_len;
+ int64_t code_out_len;
+ int64_t search_out_len;
+ int64_t interm_time;
+ int64_t code_time;
+ int64_t la_time;
+ int64_t opt_time;
+ int64_t restore_count;
+ int64_t restore_time;
+ int64_t table_op_count[NB_OPS];
+} TCGProfile;
struct TCGContext {
uint8_t *pool_cur, *pool_end;
uintptr_t *tb_jmp_target_addr; /* tb->jmp_target_arg if !direct_jump */
TCGRegSet reserved_regs;
+ uint32_t tb_cflags; /* cflags of the current TB */
intptr_t current_frame_offset;
intptr_t frame_start;
intptr_t frame_end;
tcg_insn_unit *code_ptr;
#ifdef CONFIG_PROFILER
- /* profiling info */
- int64_t tb_count1;
- int64_t tb_count;
- int64_t op_count; /* total insn count */
- int op_count_max; /* max insn per TB */
- int64_t temp_count;
- int temp_count_max;
- int64_t del_op_count;
- int64_t code_in_len;
- int64_t code_out_len;
- int64_t search_out_len;
- int64_t interm_time;
- int64_t code_time;
- int64_t la_time;
- int64_t opt_time;
- int64_t restore_count;
- int64_t restore_time;
+ TCGProfile prof;
#endif
#ifdef CONFIG_DEBUG_TCG
int goto_tb_issue_mask;
#endif
- int gen_next_op_idx;
-
/* Code generation. Note that we specifically do not use tcg_insn_unit
here, because there's too much arithmetic throughout that relies
on addition and subtraction working on bytes. Rely on the GCC
/* Threshold to flush the translated code buffer. */
void *code_gen_highwater;
- TBContext tb_ctx;
-
/* Track which vCPU triggers events */
CPUState *cpu; /* *_trans */
- TCGv_env tcg_env; /* *_exec */
/* These structures are private to tcg-target.inc.c. */
#ifdef TCG_TARGET_NEED_LDST_LABELS
struct TCGLabelPoolData *pool_labels;
#endif
+ TCGLabel *exitreq_label;
+
TCGTempSet free_temps[TCG_TYPE_COUNT * 2];
TCGTemp temps[TCG_MAX_TEMPS]; /* globals first, temps after */
+ QTAILQ_HEAD(TCGOpHead, TCGOp) ops, free_ops;
+
/* Tells which temporary holds a given register.
It does not take into account fixed registers */
TCGTemp *reg_to_temp[TCG_TARGET_NB_REGS];
- TCGOp gen_op_buf[OPC_BUF_SIZE];
-
uint16_t gen_insn_end_off[TCG_MAX_INSNS];
target_ulong gen_insn_data[TCG_MAX_INSNS][TARGET_INSN_START_WORDS];
};
-extern TCGContext tcg_ctx;
-extern bool parallel_cpus;
+extern TCGContext tcg_init_ctx;
+extern __thread TCGContext *tcg_ctx;
+extern TCGv_env cpu_env;
static inline size_t temp_idx(TCGTemp *ts)
{
- ptrdiff_t n = ts - tcg_ctx.temps;
- tcg_debug_assert(n >= 0 && n < tcg_ctx.nb_temps);
+ ptrdiff_t n = ts - tcg_ctx->temps;
+ tcg_debug_assert(n >= 0 && n < tcg_ctx->nb_temps);
return n;
}
static inline TCGArg temp_arg(TCGTemp *ts)
{
- return temp_idx(ts);
+ return (uintptr_t)ts;
}
static inline TCGTemp *arg_temp(TCGArg a)
{
- return a == TCG_CALL_DUMMY_ARG ? NULL : &tcg_ctx.temps[a];
+ return (TCGTemp *)(uintptr_t)a;
}
-static inline size_t arg_index(TCGArg a)
+/* Using the offset of a temporary, relative to TCGContext, rather than
+ its index means that we don't use 0. That leaves offset 0 free for
+ a NULL representation without having to leave index 0 unused. */
+static inline TCGTemp *tcgv_i32_temp(TCGv_i32 v)
{
- return a;
+ uintptr_t o = (uintptr_t)v;
+ TCGTemp *t = (void *)tcg_ctx + o;
+ tcg_debug_assert(offsetof(TCGContext, temps[temp_idx(t)]) == o);
+ return t;
+}
+
+static inline TCGTemp *tcgv_i64_temp(TCGv_i64 v)
+{
+ return tcgv_i32_temp((TCGv_i32)v);
}
-static inline TCGArg tcgv_i32_arg(TCGv_i32 t)
+static inline TCGTemp *tcgv_ptr_temp(TCGv_ptr v)
{
- return (intptr_t)t;
+ return tcgv_i32_temp((TCGv_i32)v);
}
-static inline TCGArg tcgv_i64_arg(TCGv_i64 t)
+static inline TCGTemp *tcgv_vec_temp(TCGv_vec v)
{
- return (intptr_t)t;
+ return tcgv_i32_temp((TCGv_i32)v);
}
-static inline TCGArg tcgv_ptr_arg(TCGv_ptr t)
+static inline TCGArg tcgv_i32_arg(TCGv_i32 v)
{
- return (intptr_t)t;
+ return temp_arg(tcgv_i32_temp(v));
}
-static inline TCGTemp *tcgv_i32_temp(TCGv_i32 t)
+static inline TCGArg tcgv_i64_arg(TCGv_i64 v)
{
- return arg_temp(tcgv_i32_arg(t));
+ return temp_arg(tcgv_i64_temp(v));
}
-static inline TCGTemp *tcgv_i64_temp(TCGv_i64 t)
+static inline TCGArg tcgv_ptr_arg(TCGv_ptr v)
{
- return arg_temp(tcgv_i64_arg(t));
+ return temp_arg(tcgv_ptr_temp(v));
}
-static inline TCGTemp *tcgv_ptr_temp(TCGv_ptr t)
+static inline TCGArg tcgv_vec_arg(TCGv_vec v)
{
- return arg_temp(tcgv_ptr_arg(t));
+ return temp_arg(tcgv_vec_temp(v));
}
static inline TCGv_i32 temp_tcgv_i32(TCGTemp *t)
{
- return (TCGv_i32)temp_idx(t);
+ (void)temp_idx(t); /* trigger embedded assert */
+ return (TCGv_i32)((void *)t - (void *)tcg_ctx);
}
static inline TCGv_i64 temp_tcgv_i64(TCGTemp *t)
{
- return (TCGv_i64)temp_idx(t);
+ return (TCGv_i64)temp_tcgv_i32(t);
}
static inline TCGv_ptr temp_tcgv_ptr(TCGTemp *t)
{
- return (TCGv_ptr)temp_idx(t);
+ return (TCGv_ptr)temp_tcgv_i32(t);
+}
+
+static inline TCGv_vec temp_tcgv_vec(TCGTemp *t)
+{
+ return (TCGv_vec)temp_tcgv_i32(t);
+}
+
+#if TCG_TARGET_REG_BITS == 32
+static inline TCGv_i32 TCGV_LOW(TCGv_i64 t)
+{
+ return temp_tcgv_i32(tcgv_i64_temp(t));
+}
+
+static inline TCGv_i32 TCGV_HIGH(TCGv_i64 t)
+{
+ return temp_tcgv_i32(tcgv_i64_temp(t) + 1);
}
+#endif
-static inline void tcg_set_insn_param(int op_idx, int arg, TCGArg v)
+static inline void tcg_set_insn_param(TCGOp *op, int arg, TCGArg v)
{
- tcg_ctx.gen_op_buf[op_idx].args[arg] = v;
+ op->args[arg] = v;
}
-/* The number of opcodes emitted so far. */
-static inline int tcg_op_buf_count(void)
+static inline void tcg_set_insn_start_param(TCGOp *op, int arg, target_ulong v)
{
- return tcg_ctx.gen_next_op_idx;
+#if TARGET_LONG_BITS <= TCG_TARGET_REG_BITS
+ tcg_set_insn_param(op, arg, v);
+#else
+ tcg_set_insn_param(op, arg * 2, v);
+ tcg_set_insn_param(op, arg * 2 + 1, v >> 32);
+#endif
+}
+
+/* The last op that was emitted. */
+static inline TCGOp *tcg_last_op(void)
+{
+ return QTAILQ_LAST(&tcg_ctx->ops, TCGOpHead);
}
/* Test for whether to terminate the TB for using too many opcodes. */
static inline bool tcg_op_buf_full(void)
{
- return tcg_op_buf_count() >= OPC_MAX_SIZE;
+ return false;
}
/* pool based memory allocation */
-/* tb_lock must be held for tcg_malloc_internal. */
+/* user-mode: tb_lock must be held for tcg_malloc_internal. */
void *tcg_malloc_internal(TCGContext *s, int size);
void tcg_pool_reset(TCGContext *s);
TranslationBlock *tcg_tb_alloc(TCGContext *s);
-/* Called with tb_lock held. */
+void tcg_region_init(void);
+void tcg_region_reset_all(void);
+
+size_t tcg_code_size(void);
+size_t tcg_code_capacity(void);
+
+/* user-mode: Called with tb_lock held. */
static inline void *tcg_malloc(int size)
{
- TCGContext *s = &tcg_ctx;
+ TCGContext *s = tcg_ctx;
uint8_t *ptr, *ptr_end;
/* ??? This is a weak placeholder for minimum malloc alignment. */
ptr = s->pool_cur;
ptr_end = ptr + size;
if (unlikely(ptr_end > s->pool_end)) {
- return tcg_malloc_internal(&tcg_ctx, size);
+ return tcg_malloc_internal(tcg_ctx, size);
} else {
s->pool_cur = ptr_end;
return ptr;
}
void tcg_context_init(TCGContext *s);
+void tcg_register_thread(void);
void tcg_prologue_init(TCGContext *s);
void tcg_func_start(TCGContext *s);
TCGTemp *tcg_global_mem_new_internal(TCGType, TCGv_ptr,
intptr_t, const char *);
-TCGv_i32 tcg_global_reg_new_i32(TCGReg reg, const char *name);
-TCGv_i64 tcg_global_reg_new_i64(TCGReg reg, const char *name);
-
TCGv_i32 tcg_temp_new_internal_i32(int temp_local);
TCGv_i64 tcg_temp_new_internal_i64(int temp_local);
+TCGv_vec tcg_temp_new_vec(TCGType type);
+TCGv_vec tcg_temp_new_vec_matching(TCGv_vec match);
void tcg_temp_free_i32(TCGv_i32 arg);
void tcg_temp_free_i64(TCGv_i64 arg);
+void tcg_temp_free_vec(TCGv_vec arg);
static inline TCGv_i32 tcg_global_mem_new_i32(TCGv_ptr reg, intptr_t offset,
const char *name)
/* Instruction is optional and not implemented by the host, or insn
is generic and should not be implemened by the host. */
TCG_OPF_NOT_PRESENT = 0x10,
+ /* Instruction operands are vectors. */
+ TCG_OPF_VECTOR = 0x20,
};
typedef struct TCGOpDef {
} while (0)
#if UINTPTR_MAX == UINT32_MAX
-#define TCGV_NAT_TO_PTR(n) MAKE_TCGV_PTR(GET_TCGV_I32(n))
-#define TCGV_PTR_TO_NAT(n) MAKE_TCGV_I32(GET_TCGV_PTR(n))
+static inline TCGv_ptr TCGV_NAT_TO_PTR(TCGv_i32 n) { return (TCGv_ptr)n; }
+static inline TCGv_i32 TCGV_PTR_TO_NAT(TCGv_ptr n) { return (TCGv_i32)n; }
#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i32((intptr_t)(V)))
-#define tcg_global_reg_new_ptr(R, N) \
- TCGV_NAT_TO_PTR(tcg_global_reg_new_i32((R), (N)))
#define tcg_global_mem_new_ptr(R, O, N) \
TCGV_NAT_TO_PTR(tcg_global_mem_new_i32((R), (O), (N)))
#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i32())
#define tcg_temp_free_ptr(T) tcg_temp_free_i32(TCGV_PTR_TO_NAT(T))
#else
-#define TCGV_NAT_TO_PTR(n) MAKE_TCGV_PTR(GET_TCGV_I64(n))
-#define TCGV_PTR_TO_NAT(n) MAKE_TCGV_I64(GET_TCGV_PTR(n))
+static inline TCGv_ptr TCGV_NAT_TO_PTR(TCGv_i64 n) { return (TCGv_ptr)n; }
+static inline TCGv_i64 TCGV_PTR_TO_NAT(TCGv_ptr n) { return (TCGv_i64)n; }
#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i64((intptr_t)(V)))
-#define tcg_global_reg_new_ptr(R, N) \
- TCGV_NAT_TO_PTR(tcg_global_reg_new_i64((R), (N)))
#define tcg_global_mem_new_ptr(R, O, N) \
TCGV_NAT_TO_PTR(tcg_global_mem_new_i64((R), (O), (N)))
#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i64())
void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args);
+TCGOp *tcg_emit_op(TCGOpcode opc);
void tcg_op_remove(TCGContext *s, TCGOp *op);
TCGOp *tcg_op_insert_before(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
TCGv_i64 tcg_const_i64(int64_t val);
TCGv_i32 tcg_const_local_i32(int32_t val);
TCGv_i64 tcg_const_local_i64(int64_t val);
+TCGv_vec tcg_const_zeros_vec(TCGType);
+TCGv_vec tcg_const_ones_vec(TCGType);
+TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec);
+TCGv_vec tcg_const_ones_vec_matching(TCGv_vec);
TCGLabel *gen_new_label(void);
uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr);
#else
# define tcg_qemu_tb_exec(env, tb_ptr) \
- ((uintptr_t (*)(void *, void *))tcg_ctx.code_gen_prologue)(env, tb_ptr)
+ ((uintptr_t (*)(void *, void *))tcg_ctx->code_gen_prologue)(env, tb_ptr)
#endif
void tcg_register_jit(void *buf, size_t buf_size);
+#if TCG_TARGET_MAYBE_vec
+/* Return zero if the tuple (opc, type, vece) is unsupportable;
+ return > 0 if it is directly supportable;
+ return < 0 if we must call tcg_expand_vec_op. */
+int tcg_can_emit_vec_op(TCGOpcode, TCGType, unsigned);
+#else
+static inline int tcg_can_emit_vec_op(TCGOpcode o, TCGType t, unsigned ve)
+{
+ return 0;
+}
+#endif
+
+/* Expand the tuple (opc, type, vece) on the given arguments. */
+void tcg_expand_vec_op(TCGOpcode, TCGType, unsigned, TCGArg, ...);
+
+/* Replicate a constant C accoring to the log2 of the element size. */
+uint64_t dup_const(unsigned vece, uint64_t c);
+
+#define dup_const(VECE, C) \
+ (__builtin_constant_p(VECE) \
+ ? ( (VECE) == MO_8 ? 0x0101010101010101ull * (uint8_t)(C) \
+ : (VECE) == MO_16 ? 0x0001000100010001ull * (uint16_t)(C) \
+ : (VECE) == MO_32 ? 0x0000000100000001ull * (uint32_t)(C) \
+ : dup_const(VECE, C)) \
+ : dup_const(VECE, C))
+
+
/*
* Memory helpers that will be used by TCG generated code.
*/