*/
#include "../tcg-ldst.c.inc"
+#include <asm/hwcap.h>
+
+bool use_lsx_instructions;
#ifdef CONFIG_DEBUG_TCG
static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
"s5",
"s6",
"s7",
- "s8"
+ "s8",
+ "vr0",
+ "vr1",
+ "vr2",
+ "vr3",
+ "vr4",
+ "vr5",
+ "vr6",
+ "vr7",
+ "vr8",
+ "vr9",
+ "vr10",
+ "vr11",
+ "vr12",
+ "vr13",
+ "vr14",
+ "vr15",
+ "vr16",
+ "vr17",
+ "vr18",
+ "vr19",
+ "vr20",
+ "vr21",
+ "vr22",
+ "vr23",
+ "vr24",
+ "vr25",
+ "vr26",
+ "vr27",
+ "vr28",
+ "vr29",
+ "vr30",
+ "vr31",
};
#endif
TCG_REG_A2,
TCG_REG_A1,
TCG_REG_A0,
+
+ /* Vector registers */
+ TCG_REG_V0, TCG_REG_V1, TCG_REG_V2, TCG_REG_V3,
+ TCG_REG_V4, TCG_REG_V5, TCG_REG_V6, TCG_REG_V7,
+ TCG_REG_V8, TCG_REG_V9, TCG_REG_V10, TCG_REG_V11,
+ TCG_REG_V12, TCG_REG_V13, TCG_REG_V14, TCG_REG_V15,
+ TCG_REG_V16, TCG_REG_V17, TCG_REG_V18, TCG_REG_V19,
+ TCG_REG_V20, TCG_REG_V21, TCG_REG_V22, TCG_REG_V23,
+ /* V24 - V31 are caller-saved, and skipped. */
};
static const int tcg_target_call_iarg_regs[] = {
#define TCG_CT_CONST_U12 0x800
#define TCG_CT_CONST_C12 0x1000
#define TCG_CT_CONST_WSZ 0x2000
+#define TCG_CT_CONST_VCMP 0x4000
+#define TCG_CT_CONST_VADD 0x8000
-#define ALL_GENERAL_REGS MAKE_64BIT_MASK(0, 32)
-/*
- * For softmmu, we need to avoid conflicts with the first 5
- * argument registers to call the helper. Some of these are
- * also used for the tlb lookup.
- */
-#ifdef CONFIG_SOFTMMU
-#define SOFTMMU_RESERVE_REGS MAKE_64BIT_MASK(TCG_REG_A0, 5)
-#else
-#define SOFTMMU_RESERVE_REGS 0
-#endif
-
+#define ALL_GENERAL_REGS MAKE_64BIT_MASK(0, 32)
+#define ALL_VECTOR_REGS MAKE_64BIT_MASK(32, 32)
static inline tcg_target_long sextreg(tcg_target_long val, int pos, int len)
{
}
/* test if a constant matches the constraint */
-static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
+static bool tcg_target_const_match(int64_t val, TCGType type, int ct, int vece)
{
if (ct & TCG_CT_CONST) {
return true;
if ((ct & TCG_CT_CONST_WSZ) && val == (type == TCG_TYPE_I32 ? 32 : 64)) {
return true;
}
+ int64_t vec_val = sextract64(val, 0, 8 << vece);
+ if ((ct & TCG_CT_CONST_VCMP) && -0x10 <= vec_val && vec_val <= 0x1f) {
+ return true;
+ }
+ if ((ct & TCG_CT_CONST_VADD) && -0x1f <= vec_val && vec_val <= 0x1f) {
+ return true;
+ }
return false;
}
* Load/store helpers for SoftMMU, and qemu_ld/st implementations
*/
-#if defined(CONFIG_SOFTMMU)
-/*
- * helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
- * MemOpIdx oi, uintptr_t ra)
- */
-static void * const qemu_ld_helpers[4] = {
- [MO_8] = helper_ret_ldub_mmu,
- [MO_16] = helper_le_lduw_mmu,
- [MO_32] = helper_le_ldul_mmu,
- [MO_64] = helper_le_ldq_mmu,
-};
-
-/*
- * helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
- * uintxx_t val, MemOpIdx oi,
- * uintptr_t ra)
- */
-static void * const qemu_st_helpers[4] = {
- [MO_8] = helper_ret_stb_mmu,
- [MO_16] = helper_le_stw_mmu,
- [MO_32] = helper_le_stl_mmu,
- [MO_64] = helper_le_stq_mmu,
-};
-
-/* We expect to use a 12-bit negative offset from ENV. */
-QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0);
-QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11));
-
static bool tcg_out_goto(TCGContext *s, const tcg_insn_unit *target)
{
tcg_out_opc_b(s, 0);
return reloc_br_sd10k16(s->code_ptr - 1, target);
}
-/*
- * Emits common code for TLB addend lookup, that eventually loads the
- * addend in TCG_REG_TMP2.
- */
-static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, MemOpIdx oi,
- tcg_insn_unit **label_ptr, bool is_load)
-{
- MemOp opc = get_memop(oi);
- unsigned s_bits = opc & MO_SIZE;
- unsigned a_bits = get_alignment_bits(opc);
- tcg_target_long compare_mask;
- int mem_index = get_mmuidx(oi);
- int fast_ofs = TLB_MASK_TABLE_OFS(mem_index);
- int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask);
- int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table);
-
- tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs);
- tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs);
-
- tcg_out_opc_srli_d(s, TCG_REG_TMP2, addrl,
- TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
- tcg_out_opc_and(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0);
- tcg_out_opc_add_d(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1);
-
- /* Load the tlb comparator and the addend. */
- tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP0, TCG_REG_TMP2,
- is_load ? offsetof(CPUTLBEntry, addr_read)
- : offsetof(CPUTLBEntry, addr_write));
- tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2,
- offsetof(CPUTLBEntry, addend));
-
- /* We don't support unaligned accesses. */
- if (a_bits < s_bits) {
- a_bits = s_bits;
- }
- /* Clear the non-page, non-alignment bits from the address. */
- compare_mask = (tcg_target_long)TARGET_PAGE_MASK | ((1 << a_bits) - 1);
- tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_TMP1, compare_mask);
- tcg_out_opc_and(s, TCG_REG_TMP1, TCG_REG_TMP1, addrl);
-
- /* Compare masked address with the TLB entry. */
- label_ptr[0] = s->code_ptr;
- tcg_out_opc_bne(s, TCG_REG_TMP0, TCG_REG_TMP1, 0);
-
- /* TLB Hit - addend in TCG_REG_TMP2, ready for use. */
-}
-
-static void add_qemu_ldst_label(TCGContext *s, int is_ld, MemOpIdx oi,
- TCGType type,
- TCGReg datalo, TCGReg addrlo,
- void *raddr, tcg_insn_unit **label_ptr)
-{
- TCGLabelQemuLdst *label = new_ldst_label(s);
-
- label->is_ld = is_ld;
- label->oi = oi;
- label->type = type;
- label->datalo_reg = datalo;
- label->datahi_reg = 0; /* unused */
- label->addrlo_reg = addrlo;
- label->addrhi_reg = 0; /* unused */
- label->raddr = tcg_splitwx_to_rx(raddr);
- label->label_ptr[0] = label_ptr[0];
-}
+static const TCGLdstHelperParam ldst_helper_param = {
+ .ntmp = 1, .tmp = { TCG_REG_TMP0 }
+};
static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
- MemOpIdx oi = l->oi;
- MemOp opc = get_memop(oi);
- MemOp size = opc & MO_SIZE;
+ MemOp opc = get_memop(l->oi);
/* resolve label address */
if (!reloc_br_sk16(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) {
return false;
}
- /* call load helper */
- tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A0, TCG_AREG0);
- tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A1, l->addrlo_reg);
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A2, oi);
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A3, (tcg_target_long)l->raddr);
-
- tcg_out_call_int(s, qemu_ld_helpers[size], false);
-
- tcg_out_movext(s, l->type, l->datalo_reg,
- TCG_TYPE_REG, opc & MO_SSIZE, TCG_REG_A0);
+ tcg_out_ld_helper_args(s, l, &ldst_helper_param);
+ tcg_out_call_int(s, qemu_ld_helpers[opc & MO_SIZE], false);
+ tcg_out_ld_helper_ret(s, l, false, &ldst_helper_param);
return tcg_out_goto(s, l->raddr);
}
static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
- MemOpIdx oi = l->oi;
- MemOp opc = get_memop(oi);
- MemOp size = opc & MO_SIZE;
+ MemOp opc = get_memop(l->oi);
/* resolve label address */
if (!reloc_br_sk16(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) {
return false;
}
- /* call store helper */
- tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A0, TCG_AREG0);
- tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A1, l->addrlo_reg);
- tcg_out_movext(s, size == MO_64 ? TCG_TYPE_I32 : TCG_TYPE_I32, TCG_REG_A2,
- l->type, size, l->datalo_reg);
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A3, oi);
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_A4, (tcg_target_long)l->raddr);
+ tcg_out_st_helper_args(s, l, &ldst_helper_param);
+ tcg_out_call_int(s, qemu_st_helpers[opc & MO_SIZE], false);
+ return tcg_out_goto(s, l->raddr);
+}
- tcg_out_call_int(s, qemu_st_helpers[size], false);
+typedef struct {
+ TCGReg base;
+ TCGReg index;
+ TCGAtomAlign aa;
+} HostAddress;
- return tcg_out_goto(s, l->raddr);
+bool tcg_target_has_memory_bswap(MemOp memop)
+{
+ return false;
}
-#else
+
+/* We expect to use a 12-bit negative offset from ENV. */
+#define MIN_TLB_MASK_TABLE_OFS -(1 << 11)
/*
- * Alignment helpers for user-mode emulation
+ * For softmmu, perform the TLB load and compare.
+ * For useronly, perform any required alignment tests.
+ * In both cases, return a TCGLabelQemuLdst structure if the slow path
+ * is required and fill in @h with the host address for the fast path.
*/
-
-static void tcg_out_test_alignment(TCGContext *s, bool is_ld, TCGReg addr_reg,
- unsigned a_bits)
+static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
+ TCGReg addr_reg, MemOpIdx oi,
+ bool is_ld)
{
- TCGLabelQemuLdst *l = new_ldst_label(s);
+ TCGType addr_type = s->addr_type;
+ TCGLabelQemuLdst *ldst = NULL;
+ MemOp opc = get_memop(oi);
+ MemOp a_bits;
- l->is_ld = is_ld;
- l->addrlo_reg = addr_reg;
+ h->aa = atom_and_align_for_opc(s, opc, MO_ATOM_IFALIGN, false);
+ a_bits = h->aa.align;
- /*
- * Without micro-architecture details, we don't know which of bstrpick or
- * andi is faster, so use bstrpick as it's not constrained by imm field
- * width. (Not to say alignments >= 2^12 are going to happen any time
- * soon, though)
- */
- tcg_out_opc_bstrpick_d(s, TCG_REG_TMP1, addr_reg, 0, a_bits - 1);
+#ifdef CONFIG_SOFTMMU
+ unsigned s_bits = opc & MO_SIZE;
+ int mem_index = get_mmuidx(oi);
+ int fast_ofs = tlb_mask_table_ofs(s, mem_index);
+ int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask);
+ int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table);
- l->label_ptr[0] = s->code_ptr;
- tcg_out_opc_bne(s, TCG_REG_TMP1, TCG_REG_ZERO, 0);
+ ldst = new_ldst_label(s);
+ ldst->is_ld = is_ld;
+ ldst->oi = oi;
+ ldst->addrlo_reg = addr_reg;
- l->raddr = tcg_splitwx_to_rx(s->code_ptr);
-}
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs);
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs);
-static bool tcg_out_fail_alignment(TCGContext *s, TCGLabelQemuLdst *l)
-{
- /* resolve label address */
- if (!reloc_br_sk16(l->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) {
- return false;
+ tcg_out_opc_srli_d(s, TCG_REG_TMP2, addr_reg,
+ s->page_bits - CPU_TLB_ENTRY_BITS);
+ tcg_out_opc_and(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0);
+ tcg_out_opc_add_d(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1);
+
+ /* Load the tlb comparator and the addend. */
+ QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
+ tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2,
+ is_ld ? offsetof(CPUTLBEntry, addr_read)
+ : offsetof(CPUTLBEntry, addr_write));
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2,
+ offsetof(CPUTLBEntry, addend));
+
+ /*
+ * For aligned accesses, we check the first byte and include the alignment
+ * bits within the address. For unaligned access, we check that we don't
+ * cross pages using the address of the last byte of the access.
+ */
+ if (a_bits < s_bits) {
+ unsigned a_mask = (1u << a_bits) - 1;
+ unsigned s_mask = (1u << s_bits) - 1;
+ tcg_out_addi(s, addr_type, TCG_REG_TMP1, addr_reg, s_mask - a_mask);
+ } else {
+ tcg_out_mov(s, addr_type, TCG_REG_TMP1, addr_reg);
}
+ tcg_out_opc_bstrins_d(s, TCG_REG_TMP1, TCG_REG_ZERO,
+ a_bits, s->page_bits - 1);
- tcg_out_mov(s, TCG_TYPE_TL, TCG_REG_A1, l->addrlo_reg);
- tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_A0, TCG_AREG0);
+ /* Compare masked address with the TLB entry. */
+ ldst->label_ptr[0] = s->code_ptr;
+ tcg_out_opc_bne(s, TCG_REG_TMP0, TCG_REG_TMP1, 0);
- /* tail call, with the return address back inline. */
- tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_RA, (uintptr_t)l->raddr);
- tcg_out_call_int(s, (const void *)(l->is_ld ? helper_unaligned_ld
- : helper_unaligned_st), true);
- return true;
-}
+ h->index = TCG_REG_TMP2;
+#else
+ if (a_bits) {
+ ldst = new_ldst_label(s);
-static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
-{
- return tcg_out_fail_alignment(s, l);
-}
+ ldst->is_ld = is_ld;
+ ldst->oi = oi;
+ ldst->addrlo_reg = addr_reg;
-static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
-{
- return tcg_out_fail_alignment(s, l);
-}
+ /*
+ * Without micro-architecture details, we don't know which of
+ * bstrpick or andi is faster, so use bstrpick as it's not
+ * constrained by imm field width. Not to say alignments >= 2^12
+ * are going to happen any time soon.
+ */
+ tcg_out_opc_bstrpick_d(s, TCG_REG_TMP1, addr_reg, 0, a_bits - 1);
-#endif /* CONFIG_SOFTMMU */
+ ldst->label_ptr[0] = s->code_ptr;
+ tcg_out_opc_bne(s, TCG_REG_TMP1, TCG_REG_ZERO, 0);
+ }
-/*
- * `ext32u` the address register into the temp register given,
- * if target is 32-bit, no-op otherwise.
- *
- * Returns the address register ready for use with TLB addend.
- */
-static TCGReg tcg_out_zext_addr_if_32_bit(TCGContext *s,
- TCGReg addr, TCGReg tmp)
-{
- if (TARGET_LONG_BITS == 32) {
- tcg_out_ext32u(s, tmp, addr);
- return tmp;
+ h->index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO;
+#endif
+
+ if (addr_type == TCG_TYPE_I32) {
+ h->base = TCG_REG_TMP0;
+ tcg_out_ext32u(s, h->base, addr_reg);
+ } else {
+ h->base = addr_reg;
}
- return addr;
-}
-typedef struct {
- TCGReg base;
- TCGReg index;
-} HostAddress;
+ return ldst;
+}
static void tcg_out_qemu_ld_indexed(TCGContext *s, MemOp opc, TCGType type,
TCGReg rd, HostAddress h)
static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
MemOpIdx oi, TCGType data_type)
{
- MemOp opc = get_memop(oi);
+ TCGLabelQemuLdst *ldst;
HostAddress h;
-#ifdef CONFIG_SOFTMMU
- tcg_insn_unit *label_ptr[1];
+ ldst = prepare_host_addr(s, &h, addr_reg, oi, true);
+ tcg_out_qemu_ld_indexed(s, get_memop(oi), data_type, data_reg, h);
- tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 1);
- h.index = TCG_REG_TMP2;
-#else
- unsigned a_bits = get_alignment_bits(opc);
- if (a_bits) {
- tcg_out_test_alignment(s, true, addr_reg, a_bits);
+ if (ldst) {
+ ldst->type = data_type;
+ ldst->datalo_reg = data_reg;
+ ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
}
- h.index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO;
-#endif
-
- h.base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0);
- tcg_out_qemu_ld_indexed(s, opc, data_type, data_reg, h);
-
-#ifdef CONFIG_SOFTMMU
- add_qemu_ldst_label(s, true, oi, data_type, data_reg, addr_reg,
- s->code_ptr, label_ptr);
-#endif
}
static void tcg_out_qemu_st_indexed(TCGContext *s, MemOp opc,
static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
MemOpIdx oi, TCGType data_type)
{
- MemOp opc = get_memop(oi);
+ TCGLabelQemuLdst *ldst;
HostAddress h;
-#ifdef CONFIG_SOFTMMU
- tcg_insn_unit *label_ptr[1];
+ ldst = prepare_host_addr(s, &h, addr_reg, oi, false);
+ tcg_out_qemu_st_indexed(s, get_memop(oi), data_reg, h);
- tcg_out_tlb_load(s, addr_reg, oi, label_ptr, 0);
- h.index = TCG_REG_TMP2;
-#else
- unsigned a_bits = get_alignment_bits(opc);
- if (a_bits) {
- tcg_out_test_alignment(s, false, addr_reg, a_bits);
+ if (ldst) {
+ ldst->type = data_type;
+ ldst->datalo_reg = data_reg;
+ ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
}
- h.index = USE_GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_ZERO;
-#endif
+}
+
+static void tcg_out_qemu_ldst_i128(TCGContext *s, TCGReg data_lo, TCGReg data_hi,
+ TCGReg addr_reg, MemOpIdx oi, bool is_ld)
+{
+ TCGLabelQemuLdst *ldst;
+ HostAddress h;
- h.base = tcg_out_zext_addr_if_32_bit(s, addr_reg, TCG_REG_TMP0);
- tcg_out_qemu_st_indexed(s, opc, data_reg, h);
+ ldst = prepare_host_addr(s, &h, addr_reg, oi, is_ld);
-#ifdef CONFIG_SOFTMMU
- add_qemu_ldst_label(s, false, oi, data_type, data_reg, addr_reg,
- s->code_ptr, label_ptr);
-#endif
+ if (h.aa.atom == MO_128) {
+ /*
+ * Use VLDX/VSTX when 128-bit atomicity is required.
+ * If address is aligned to 16-bytes, the 128-bit load/store is atomic.
+ */
+ if (is_ld) {
+ tcg_out_opc_vldx(s, TCG_VEC_TMP0, h.base, h.index);
+ tcg_out_opc_vpickve2gr_d(s, data_lo, TCG_VEC_TMP0, 0);
+ tcg_out_opc_vpickve2gr_d(s, data_hi, TCG_VEC_TMP0, 1);
+ } else {
+ tcg_out_opc_vinsgr2vr_d(s, TCG_VEC_TMP0, data_lo, 0);
+ tcg_out_opc_vinsgr2vr_d(s, TCG_VEC_TMP0, data_hi, 1);
+ tcg_out_opc_vstx(s, TCG_VEC_TMP0, h.base, h.index);
+ }
+ } else {
+ /* Otherwise use a pair of LD/ST. */
+ tcg_out_opc_add_d(s, TCG_REG_TMP0, h.base, h.index);
+ if (is_ld) {
+ tcg_out_opc_ld_d(s, data_lo, TCG_REG_TMP0, 0);
+ tcg_out_opc_ld_d(s, data_hi, TCG_REG_TMP0, 8);
+ } else {
+ tcg_out_opc_st_d(s, data_lo, TCG_REG_TMP0, 0);
+ tcg_out_opc_st_d(s, data_hi, TCG_REG_TMP0, 8);
+ }
+ }
+
+ if (ldst) {
+ ldst->type = TCG_TYPE_I128;
+ ldst->datalo_reg = data_lo;
+ ldst->datahi_reg = data_hi;
+ ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
+ }
}
/*
TCGArg a0 = args[0];
TCGArg a1 = args[1];
TCGArg a2 = args[2];
+ TCGArg a3 = args[3];
int c2 = const_args[2];
switch (opc) {
tcg_out_ldst(s, OPC_ST_D, a0, a1, a2);
break;
- case INDEX_op_qemu_ld_i32:
+ case INDEX_op_qemu_ld_a32_i32:
+ case INDEX_op_qemu_ld_a64_i32:
tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I32);
break;
- case INDEX_op_qemu_ld_i64:
+ case INDEX_op_qemu_ld_a32_i64:
+ case INDEX_op_qemu_ld_a64_i64:
tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I64);
break;
- case INDEX_op_qemu_st_i32:
+ case INDEX_op_qemu_ld_a32_i128:
+ case INDEX_op_qemu_ld_a64_i128:
+ tcg_out_qemu_ldst_i128(s, a0, a1, a2, a3, true);
+ break;
+ case INDEX_op_qemu_st_a32_i32:
+ case INDEX_op_qemu_st_a64_i32:
tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I32);
break;
- case INDEX_op_qemu_st_i64:
+ case INDEX_op_qemu_st_a32_i64:
+ case INDEX_op_qemu_st_a64_i64:
tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I64);
break;
+ case INDEX_op_qemu_st_a32_i128:
+ case INDEX_op_qemu_st_a64_i128:
+ tcg_out_qemu_ldst_i128(s, a0, a1, a2, a3, false);
+ break;
case INDEX_op_mov_i32: /* Always emitted via tcg_out_mov. */
case INDEX_op_mov_i64:
}
}
+static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
+ TCGReg rd, TCGReg rs)
+{
+ switch (vece) {
+ case MO_8:
+ tcg_out_opc_vreplgr2vr_b(s, rd, rs);
+ break;
+ case MO_16:
+ tcg_out_opc_vreplgr2vr_h(s, rd, rs);
+ break;
+ case MO_32:
+ tcg_out_opc_vreplgr2vr_w(s, rd, rs);
+ break;
+ case MO_64:
+ tcg_out_opc_vreplgr2vr_d(s, rd, rs);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ return true;
+}
+
+static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
+ TCGReg r, TCGReg base, intptr_t offset)
+{
+ /* Handle imm overflow and division (vldrepl.d imm is divided by 8) */
+ if (offset < -0x800 || offset > 0x7ff || \
+ (offset & ((1 << vece) - 1)) != 0) {
+ tcg_out_addi(s, TCG_TYPE_I64, TCG_REG_TMP0, base, offset);
+ base = TCG_REG_TMP0;
+ offset = 0;
+ }
+ offset >>= vece;
+
+ switch (vece) {
+ case MO_8:
+ tcg_out_opc_vldrepl_b(s, r, base, offset);
+ break;
+ case MO_16:
+ tcg_out_opc_vldrepl_h(s, r, base, offset);
+ break;
+ case MO_32:
+ tcg_out_opc_vldrepl_w(s, r, base, offset);
+ break;
+ case MO_64:
+ tcg_out_opc_vldrepl_d(s, r, base, offset);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ return true;
+}
+
+static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
+ TCGReg rd, int64_t v64)
+{
+ /* Try vldi if imm can fit */
+ int64_t value = sextract64(v64, 0, 8 << vece);
+ if (-0x200 <= value && value <= 0x1FF) {
+ uint32_t imm = (vece << 10) | ((uint32_t)v64 & 0x3FF);
+ tcg_out_opc_vldi(s, rd, imm);
+ return;
+ }
+
+ /* TODO: vldi patterns when imm 12 is set */
+
+ /* Fallback to vreplgr2vr */
+ tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP0, value);
+ switch (vece) {
+ case MO_8:
+ tcg_out_opc_vreplgr2vr_b(s, rd, TCG_REG_TMP0);
+ break;
+ case MO_16:
+ tcg_out_opc_vreplgr2vr_h(s, rd, TCG_REG_TMP0);
+ break;
+ case MO_32:
+ tcg_out_opc_vreplgr2vr_w(s, rd, TCG_REG_TMP0);
+ break;
+ case MO_64:
+ tcg_out_opc_vreplgr2vr_d(s, rd, TCG_REG_TMP0);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+static void tcg_out_addsub_vec(TCGContext *s, unsigned vece, const TCGArg a0,
+ const TCGArg a1, const TCGArg a2,
+ bool a2_is_const, bool is_add)
+{
+ static const LoongArchInsn add_vec_insn[4] = {
+ OPC_VADD_B, OPC_VADD_H, OPC_VADD_W, OPC_VADD_D
+ };
+ static const LoongArchInsn add_vec_imm_insn[4] = {
+ OPC_VADDI_BU, OPC_VADDI_HU, OPC_VADDI_WU, OPC_VADDI_DU
+ };
+ static const LoongArchInsn sub_vec_insn[4] = {
+ OPC_VSUB_B, OPC_VSUB_H, OPC_VSUB_W, OPC_VSUB_D
+ };
+ static const LoongArchInsn sub_vec_imm_insn[4] = {
+ OPC_VSUBI_BU, OPC_VSUBI_HU, OPC_VSUBI_WU, OPC_VSUBI_DU
+ };
+
+ if (a2_is_const) {
+ int64_t value = sextract64(a2, 0, 8 << vece);
+ if (!is_add) {
+ value = -value;
+ }
+
+ /* Try vaddi/vsubi */
+ if (0 <= value && value <= 0x1f) {
+ tcg_out32(s, encode_vdvjuk5_insn(add_vec_imm_insn[vece], a0, \
+ a1, value));
+ return;
+ } else if (-0x1f <= value && value < 0) {
+ tcg_out32(s, encode_vdvjuk5_insn(sub_vec_imm_insn[vece], a0, \
+ a1, -value));
+ return;
+ }
+
+ /* constraint TCG_CT_CONST_VADD ensures unreachable */
+ g_assert_not_reached();
+ }
+
+ if (is_add) {
+ tcg_out32(s, encode_vdvjvk_insn(add_vec_insn[vece], a0, a1, a2));
+ } else {
+ tcg_out32(s, encode_vdvjvk_insn(sub_vec_insn[vece], a0, a1, a2));
+ }
+}
+
+static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
+ unsigned vecl, unsigned vece,
+ const TCGArg args[TCG_MAX_OP_ARGS],
+ const int const_args[TCG_MAX_OP_ARGS])
+{
+ TCGType type = vecl + TCG_TYPE_V64;
+ TCGArg a0, a1, a2, a3;
+ TCGReg temp = TCG_REG_TMP0;
+ TCGReg temp_vec = TCG_VEC_TMP0;
+
+ static const LoongArchInsn cmp_vec_insn[16][4] = {
+ [TCG_COND_EQ] = {OPC_VSEQ_B, OPC_VSEQ_H, OPC_VSEQ_W, OPC_VSEQ_D},
+ [TCG_COND_LE] = {OPC_VSLE_B, OPC_VSLE_H, OPC_VSLE_W, OPC_VSLE_D},
+ [TCG_COND_LEU] = {OPC_VSLE_BU, OPC_VSLE_HU, OPC_VSLE_WU, OPC_VSLE_DU},
+ [TCG_COND_LT] = {OPC_VSLT_B, OPC_VSLT_H, OPC_VSLT_W, OPC_VSLT_D},
+ [TCG_COND_LTU] = {OPC_VSLT_BU, OPC_VSLT_HU, OPC_VSLT_WU, OPC_VSLT_DU},
+ };
+ static const LoongArchInsn cmp_vec_imm_insn[16][4] = {
+ [TCG_COND_EQ] = {OPC_VSEQI_B, OPC_VSEQI_H, OPC_VSEQI_W, OPC_VSEQI_D},
+ [TCG_COND_LE] = {OPC_VSLEI_B, OPC_VSLEI_H, OPC_VSLEI_W, OPC_VSLEI_D},
+ [TCG_COND_LEU] = {OPC_VSLEI_BU, OPC_VSLEI_HU, OPC_VSLEI_WU, OPC_VSLEI_DU},
+ [TCG_COND_LT] = {OPC_VSLTI_B, OPC_VSLTI_H, OPC_VSLTI_W, OPC_VSLTI_D},
+ [TCG_COND_LTU] = {OPC_VSLTI_BU, OPC_VSLTI_HU, OPC_VSLTI_WU, OPC_VSLTI_DU},
+ };
+ LoongArchInsn insn;
+ static const LoongArchInsn neg_vec_insn[4] = {
+ OPC_VNEG_B, OPC_VNEG_H, OPC_VNEG_W, OPC_VNEG_D
+ };
+ static const LoongArchInsn mul_vec_insn[4] = {
+ OPC_VMUL_B, OPC_VMUL_H, OPC_VMUL_W, OPC_VMUL_D
+ };
+ static const LoongArchInsn smin_vec_insn[4] = {
+ OPC_VMIN_B, OPC_VMIN_H, OPC_VMIN_W, OPC_VMIN_D
+ };
+ static const LoongArchInsn umin_vec_insn[4] = {
+ OPC_VMIN_BU, OPC_VMIN_HU, OPC_VMIN_WU, OPC_VMIN_DU
+ };
+ static const LoongArchInsn smax_vec_insn[4] = {
+ OPC_VMAX_B, OPC_VMAX_H, OPC_VMAX_W, OPC_VMAX_D
+ };
+ static const LoongArchInsn umax_vec_insn[4] = {
+ OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
+ };
+ static const LoongArchInsn ssadd_vec_insn[4] = {
+ OPC_VSADD_B, OPC_VSADD_H, OPC_VSADD_W, OPC_VSADD_D
+ };
+ static const LoongArchInsn usadd_vec_insn[4] = {
+ OPC_VSADD_BU, OPC_VSADD_HU, OPC_VSADD_WU, OPC_VSADD_DU
+ };
+ static const LoongArchInsn sssub_vec_insn[4] = {
+ OPC_VSSUB_B, OPC_VSSUB_H, OPC_VSSUB_W, OPC_VSSUB_D
+ };
+ static const LoongArchInsn ussub_vec_insn[4] = {
+ OPC_VSSUB_BU, OPC_VSSUB_HU, OPC_VSSUB_WU, OPC_VSSUB_DU
+ };
+ static const LoongArchInsn shlv_vec_insn[4] = {
+ OPC_VSLL_B, OPC_VSLL_H, OPC_VSLL_W, OPC_VSLL_D
+ };
+ static const LoongArchInsn shrv_vec_insn[4] = {
+ OPC_VSRL_B, OPC_VSRL_H, OPC_VSRL_W, OPC_VSRL_D
+ };
+ static const LoongArchInsn sarv_vec_insn[4] = {
+ OPC_VSRA_B, OPC_VSRA_H, OPC_VSRA_W, OPC_VSRA_D
+ };
+ static const LoongArchInsn shli_vec_insn[4] = {
+ OPC_VSLLI_B, OPC_VSLLI_H, OPC_VSLLI_W, OPC_VSLLI_D
+ };
+ static const LoongArchInsn shri_vec_insn[4] = {
+ OPC_VSRLI_B, OPC_VSRLI_H, OPC_VSRLI_W, OPC_VSRLI_D
+ };
+ static const LoongArchInsn sari_vec_insn[4] = {
+ OPC_VSRAI_B, OPC_VSRAI_H, OPC_VSRAI_W, OPC_VSRAI_D
+ };
+ static const LoongArchInsn rotrv_vec_insn[4] = {
+ OPC_VROTR_B, OPC_VROTR_H, OPC_VROTR_W, OPC_VROTR_D
+ };
+
+ a0 = args[0];
+ a1 = args[1];
+ a2 = args[2];
+ a3 = args[3];
+
+ /* Currently only supports V128 */
+ tcg_debug_assert(type == TCG_TYPE_V128);
+
+ switch (opc) {
+ case INDEX_op_st_vec:
+ /* Try to fit vst imm */
+ if (-0x800 <= a2 && a2 <= 0x7ff) {
+ tcg_out_opc_vst(s, a0, a1, a2);
+ } else {
+ tcg_out_movi(s, TCG_TYPE_I64, temp, a2);
+ tcg_out_opc_vstx(s, a0, a1, temp);
+ }
+ break;
+ case INDEX_op_ld_vec:
+ /* Try to fit vld imm */
+ if (-0x800 <= a2 && a2 <= 0x7ff) {
+ tcg_out_opc_vld(s, a0, a1, a2);
+ } else {
+ tcg_out_movi(s, TCG_TYPE_I64, temp, a2);
+ tcg_out_opc_vldx(s, a0, a1, temp);
+ }
+ break;
+ case INDEX_op_and_vec:
+ tcg_out_opc_vand_v(s, a0, a1, a2);
+ break;
+ case INDEX_op_andc_vec:
+ /*
+ * vandn vd, vj, vk: vd = vk & ~vj
+ * andc_vec vd, vj, vk: vd = vj & ~vk
+ * vk and vk are swapped
+ */
+ tcg_out_opc_vandn_v(s, a0, a2, a1);
+ break;
+ case INDEX_op_or_vec:
+ tcg_out_opc_vor_v(s, a0, a1, a2);
+ break;
+ case INDEX_op_orc_vec:
+ tcg_out_opc_vorn_v(s, a0, a1, a2);
+ break;
+ case INDEX_op_xor_vec:
+ tcg_out_opc_vxor_v(s, a0, a1, a2);
+ break;
+ case INDEX_op_nor_vec:
+ tcg_out_opc_vnor_v(s, a0, a1, a2);
+ break;
+ case INDEX_op_not_vec:
+ tcg_out_opc_vnor_v(s, a0, a1, a1);
+ break;
+ case INDEX_op_cmp_vec:
+ TCGCond cond = args[3];
+ if (const_args[2]) {
+ /*
+ * cmp_vec dest, src, value
+ * Try vseqi/vslei/vslti
+ */
+ int64_t value = sextract64(a2, 0, 8 << vece);
+ if ((cond == TCG_COND_EQ || cond == TCG_COND_LE || \
+ cond == TCG_COND_LT) && (-0x10 <= value && value <= 0x0f)) {
+ tcg_out32(s, encode_vdvjsk5_insn(cmp_vec_imm_insn[cond][vece], \
+ a0, a1, value));
+ break;
+ } else if ((cond == TCG_COND_LEU || cond == TCG_COND_LTU) &&
+ (0x00 <= value && value <= 0x1f)) {
+ tcg_out32(s, encode_vdvjuk5_insn(cmp_vec_imm_insn[cond][vece], \
+ a0, a1, value));
+ break;
+ }
+
+ /*
+ * Fallback to:
+ * dupi_vec temp, a2
+ * cmp_vec a0, a1, temp, cond
+ */
+ tcg_out_dupi_vec(s, type, vece, temp_vec, a2);
+ a2 = temp_vec;
+ }
+
+ insn = cmp_vec_insn[cond][vece];
+ if (insn == 0) {
+ TCGArg t;
+ t = a1, a1 = a2, a2 = t;
+ cond = tcg_swap_cond(cond);
+ insn = cmp_vec_insn[cond][vece];
+ tcg_debug_assert(insn != 0);
+ }
+ tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
+ break;
+ case INDEX_op_add_vec:
+ tcg_out_addsub_vec(s, vece, a0, a1, a2, const_args[2], true);
+ break;
+ case INDEX_op_sub_vec:
+ tcg_out_addsub_vec(s, vece, a0, a1, a2, const_args[2], false);
+ break;
+ case INDEX_op_neg_vec:
+ tcg_out32(s, encode_vdvj_insn(neg_vec_insn[vece], a0, a1));
+ break;
+ case INDEX_op_mul_vec:
+ tcg_out32(s, encode_vdvjvk_insn(mul_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_smin_vec:
+ tcg_out32(s, encode_vdvjvk_insn(smin_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_smax_vec:
+ tcg_out32(s, encode_vdvjvk_insn(smax_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_umin_vec:
+ tcg_out32(s, encode_vdvjvk_insn(umin_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_umax_vec:
+ tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_ssadd_vec:
+ tcg_out32(s, encode_vdvjvk_insn(ssadd_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_usadd_vec:
+ tcg_out32(s, encode_vdvjvk_insn(usadd_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_sssub_vec:
+ tcg_out32(s, encode_vdvjvk_insn(sssub_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_ussub_vec:
+ tcg_out32(s, encode_vdvjvk_insn(ussub_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_shlv_vec:
+ tcg_out32(s, encode_vdvjvk_insn(shlv_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_shrv_vec:
+ tcg_out32(s, encode_vdvjvk_insn(shrv_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_sarv_vec:
+ tcg_out32(s, encode_vdvjvk_insn(sarv_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_shli_vec:
+ tcg_out32(s, encode_vdvjuk3_insn(shli_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_shri_vec:
+ tcg_out32(s, encode_vdvjuk3_insn(shri_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_sari_vec:
+ tcg_out32(s, encode_vdvjuk3_insn(sari_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_rotrv_vec:
+ tcg_out32(s, encode_vdvjvk_insn(rotrv_vec_insn[vece], a0, a1, a2));
+ break;
+ case INDEX_op_rotlv_vec:
+ /* rotlv_vec a1, a2 = rotrv_vec a1, -a2 */
+ tcg_out32(s, encode_vdvj_insn(neg_vec_insn[vece], temp_vec, a2));
+ tcg_out32(s, encode_vdvjvk_insn(rotrv_vec_insn[vece], a0, a1,
+ temp_vec));
+ break;
+ case INDEX_op_rotli_vec:
+ /* rotli_vec a1, a2 = rotri_vec a1, -a2 */
+ a2 = extract32(-a2, 0, 3 + vece);
+ switch (vece) {
+ case MO_8:
+ tcg_out_opc_vrotri_b(s, a0, a1, a2);
+ break;
+ case MO_16:
+ tcg_out_opc_vrotri_h(s, a0, a1, a2);
+ break;
+ case MO_32:
+ tcg_out_opc_vrotri_w(s, a0, a1, a2);
+ break;
+ case MO_64:
+ tcg_out_opc_vrotri_d(s, a0, a1, a2);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ break;
+ case INDEX_op_bitsel_vec:
+ /* vbitsel vd, vj, vk, va = bitsel_vec vd, va, vk, vj */
+ tcg_out_opc_vbitsel_v(s, a0, a3, a2, a1);
+ break;
+ case INDEX_op_dupm_vec:
+ tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
+{
+ switch (opc) {
+ case INDEX_op_ld_vec:
+ case INDEX_op_st_vec:
+ case INDEX_op_dup_vec:
+ case INDEX_op_dupm_vec:
+ case INDEX_op_cmp_vec:
+ case INDEX_op_add_vec:
+ case INDEX_op_sub_vec:
+ case INDEX_op_and_vec:
+ case INDEX_op_andc_vec:
+ case INDEX_op_or_vec:
+ case INDEX_op_orc_vec:
+ case INDEX_op_xor_vec:
+ case INDEX_op_nor_vec:
+ case INDEX_op_not_vec:
+ case INDEX_op_neg_vec:
+ case INDEX_op_mul_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_umin_vec:
+ case INDEX_op_umax_vec:
+ case INDEX_op_ssadd_vec:
+ case INDEX_op_usadd_vec:
+ case INDEX_op_sssub_vec:
+ case INDEX_op_ussub_vec:
+ case INDEX_op_shlv_vec:
+ case INDEX_op_shrv_vec:
+ case INDEX_op_sarv_vec:
+ case INDEX_op_bitsel_vec:
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
+ TCGArg a0, ...)
+{
+ g_assert_not_reached();
+}
+
static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
{
switch (op) {
case INDEX_op_st32_i64:
case INDEX_op_st_i32:
case INDEX_op_st_i64:
+ case INDEX_op_qemu_st_a32_i32:
+ case INDEX_op_qemu_st_a64_i32:
+ case INDEX_op_qemu_st_a32_i64:
+ case INDEX_op_qemu_st_a64_i64:
return C_O0_I2(rZ, r);
+ case INDEX_op_qemu_ld_a32_i128:
+ case INDEX_op_qemu_ld_a64_i128:
+ return C_O2_I1(r, r, r);
+
+ case INDEX_op_qemu_st_a32_i128:
+ case INDEX_op_qemu_st_a64_i128:
+ return C_O0_I3(r, r, r);
+
case INDEX_op_brcond_i32:
case INDEX_op_brcond_i64:
return C_O0_I2(rZ, rZ);
- case INDEX_op_qemu_st_i32:
- case INDEX_op_qemu_st_i64:
- return C_O0_I2(LZ, L);
-
case INDEX_op_ext8s_i32:
case INDEX_op_ext8s_i64:
case INDEX_op_ext8u_i32:
case INDEX_op_ld32u_i64:
case INDEX_op_ld_i32:
case INDEX_op_ld_i64:
+ case INDEX_op_qemu_ld_a32_i32:
+ case INDEX_op_qemu_ld_a64_i32:
+ case INDEX_op_qemu_ld_a32_i64:
+ case INDEX_op_qemu_ld_a64_i64:
return C_O1_I1(r, r);
- case INDEX_op_qemu_ld_i32:
- case INDEX_op_qemu_ld_i64:
- return C_O1_I1(r, L);
-
case INDEX_op_andc_i32:
case INDEX_op_andc_i64:
case INDEX_op_orc_i32:
case INDEX_op_movcond_i64:
return C_O1_I4(r, rZ, rJ, rZ, rZ);
+ case INDEX_op_ld_vec:
+ case INDEX_op_dupm_vec:
+ case INDEX_op_dup_vec:
+ return C_O1_I1(w, r);
+
+ case INDEX_op_st_vec:
+ return C_O0_I2(w, r);
+
+ case INDEX_op_cmp_vec:
+ return C_O1_I2(w, w, wM);
+
+ case INDEX_op_add_vec:
+ case INDEX_op_sub_vec:
+ return C_O1_I2(w, w, wA);
+
+ case INDEX_op_and_vec:
+ case INDEX_op_andc_vec:
+ case INDEX_op_or_vec:
+ case INDEX_op_orc_vec:
+ case INDEX_op_xor_vec:
+ case INDEX_op_nor_vec:
+ case INDEX_op_mul_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_umin_vec:
+ case INDEX_op_umax_vec:
+ case INDEX_op_ssadd_vec:
+ case INDEX_op_usadd_vec:
+ case INDEX_op_sssub_vec:
+ case INDEX_op_ussub_vec:
+ case INDEX_op_shlv_vec:
+ case INDEX_op_shrv_vec:
+ case INDEX_op_sarv_vec:
+ case INDEX_op_rotrv_vec:
+ case INDEX_op_rotlv_vec:
+ return C_O1_I2(w, w, w);
+
+ case INDEX_op_not_vec:
+ case INDEX_op_neg_vec:
+ case INDEX_op_shli_vec:
+ case INDEX_op_shri_vec:
+ case INDEX_op_sari_vec:
+ case INDEX_op_rotli_vec:
+ return C_O1_I1(w, w);
+
+ case INDEX_op_bitsel_vec:
+ return C_O1_I3(w, w, w, w);
+
default:
g_assert_not_reached();
}
tcg_out_opc_jirl(s, TCG_REG_ZERO, TCG_REG_RA, 0);
}
+static void tcg_out_tb_start(TCGContext *s)
+{
+ /* nothing to do */
+}
+
static void tcg_target_init(TCGContext *s)
{
+ unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+
+ /* Server and desktop class cpus have UAL; embedded cpus do not. */
+ if (!(hwcap & HWCAP_LOONGARCH_UAL)) {
+ error_report("TCG: unaligned access support required; exiting");
+ exit(EXIT_FAILURE);
+ }
+
+ if (hwcap & HWCAP_LOONGARCH_LSX) {
+ use_lsx_instructions = 1;
+ }
+
tcg_target_available_regs[TCG_TYPE_I32] = ALL_GENERAL_REGS;
tcg_target_available_regs[TCG_TYPE_I64] = ALL_GENERAL_REGS;
tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_S8);
tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_S9);
+ if (use_lsx_instructions) {
+ tcg_target_available_regs[TCG_TYPE_V128] = ALL_VECTOR_REGS;
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V24);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V25);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V26);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V27);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V28);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V29);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V30);
+ tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V31);
+ }
+
s->reserved_regs = 0;
tcg_regset_set_reg(s->reserved_regs, TCG_REG_ZERO);
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP0);
tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP);
tcg_regset_set_reg(s->reserved_regs, TCG_REG_TP);
tcg_regset_set_reg(s->reserved_regs, TCG_REG_RESERVED);
+ tcg_regset_set_reg(s->reserved_regs, TCG_VEC_TMP0);
}
typedef struct {