*/
#include "qemu/osdep.h"
-#include "cpu.h"
-#include "exec/exec-all.h"
-#include "tcg/tcg-op.h"
-#include "tcg/tcg-op-gvec.h"
-#include "tcg/tcg-gvec-desc.h"
-#include "qemu/log.h"
-#include "arm_ldst.h"
#include "translate.h"
-#include "internals.h"
-#include "exec/helper-proto.h"
-#include "exec/helper-gen.h"
-#include "exec/log.h"
#include "translate-a64.h"
#include "fpu/softfloat.h"
}
vsz = vec_full_reg_size(s);
- tmode = tcg_const_i32(arm_rmode_to_sf(mode));
status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
-
- gen_helper_set_rmode(tmode, tmode, status);
+ tmode = gen_set_rmode(mode, status);
tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
vec_full_reg_offset(s, a->rn),
pred_full_reg_offset(s, a->pg),
status, vsz, vsz, 0, fn);
- gen_helper_set_rmode(tmode, tmode, status);
+ gen_restore_rmode(tmode, status);
return true;
}
void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
int len, int rn, int imm)
{
- int len_align = QEMU_ALIGN_DOWN(len, 8);
- int len_remain = len % 8;
- int nparts = len / 8 + ctpop8(len_remain);
+ int len_align = QEMU_ALIGN_DOWN(len, 16);
+ int len_remain = len % 16;
+ int nparts = len / 16 + ctpop8(len_remain);
int midx = get_mem_index(s);
TCGv_i64 dirty_addr, clean_addr, t0, t1;
+ TCGv_i128 t16;
dirty_addr = tcg_temp_new_i64();
tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm);
- clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len);
+ clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8);
/*
* Note that unpredicated load/store of vector/predicate registers
int i;
t0 = tcg_temp_new_i64();
- for (i = 0; i < len_align; i += 8) {
- tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ);
+ t1 = tcg_temp_new_i64();
+ t16 = tcg_temp_new_i128();
+
+ for (i = 0; i < len_align; i += 16) {
+ tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
+ MO_LE | MO_128 | MO_ATOM_NONE);
+ tcg_gen_extr_i128_i64(t0, t1, t16);
tcg_gen_st_i64(t0, base, vofs + i);
- tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ tcg_gen_st_i64(t1, base, vofs + i + 8);
+ tcg_gen_addi_i64(clean_addr, clean_addr, 16);
}
} else {
TCGLabel *loop = gen_new_label();
- TCGv_ptr tp, i = tcg_const_ptr(0);
+ TCGv_ptr tp, i = tcg_temp_new_ptr();
+ tcg_gen_movi_ptr(i, 0);
gen_set_label(loop);
- t0 = tcg_temp_new_i64();
- tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ);
- tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ t16 = tcg_temp_new_i128();
+ tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
+ MO_LE | MO_128 | MO_ATOM_NONE);
+ tcg_gen_addi_i64(clean_addr, clean_addr, 16);
tp = tcg_temp_new_ptr();
tcg_gen_add_ptr(tp, base, i);
- tcg_gen_addi_ptr(i, i, 8);
+ tcg_gen_addi_ptr(i, i, 16);
+
+ t0 = tcg_temp_new_i64();
+ t1 = tcg_temp_new_i64();
+ tcg_gen_extr_i128_i64(t0, t1, t16);
+
tcg_gen_st_i64(t0, tp, vofs);
+ tcg_gen_st_i64(t1, tp, vofs + 8);
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
}
* Predicate register loads can be any multiple of 2.
* Note that we still store the entire 64-bit unit into cpu_env.
*/
+ if (len_remain >= 8) {
+ t0 = tcg_temp_new_i64();
+ tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+ tcg_gen_st_i64(t0, base, vofs + len_align);
+ len_remain -= 8;
+ len_align += 8;
+ if (len_remain) {
+ tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ }
+ }
if (len_remain) {
t0 = tcg_temp_new_i64();
switch (len_remain) {
case 4:
case 8:
tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
- MO_LE | ctz32(len_remain));
+ MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
break;
case 6:
t1 = tcg_temp_new_i64();
- tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL);
+ tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
tcg_gen_addi_i64(clean_addr, clean_addr, 4);
- tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW);
+ tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
tcg_gen_deposit_i64(t0, t0, t1, 32, 32);
break;
void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
int len, int rn, int imm)
{
- int len_align = QEMU_ALIGN_DOWN(len, 8);
- int len_remain = len % 8;
- int nparts = len / 8 + ctpop8(len_remain);
+ int len_align = QEMU_ALIGN_DOWN(len, 16);
+ int len_remain = len % 16;
+ int nparts = len / 16 + ctpop8(len_remain);
int midx = get_mem_index(s);
- TCGv_i64 dirty_addr, clean_addr, t0;
+ TCGv_i64 dirty_addr, clean_addr, t0, t1;
+ TCGv_i128 t16;
dirty_addr = tcg_temp_new_i64();
tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm);
- clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len);
+ clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8);
/* Note that unpredicated load/store of vector/predicate registers
* are defined as a stream of bytes, which equates to little-endian
int i;
t0 = tcg_temp_new_i64();
+ t1 = tcg_temp_new_i64();
+ t16 = tcg_temp_new_i128();
for (i = 0; i < len_align; i += 8) {
tcg_gen_ld_i64(t0, base, vofs + i);
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ);
- tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ tcg_gen_ld_i64(t1, base, vofs + i + 8);
+ tcg_gen_concat_i64_i128(t16, t0, t1);
+ tcg_gen_qemu_st_i128(t16, clean_addr, midx,
+ MO_LE | MO_128 | MO_ATOM_NONE);
+ tcg_gen_addi_i64(clean_addr, clean_addr, 16);
}
} else {
TCGLabel *loop = gen_new_label();
- TCGv_ptr tp, i = tcg_const_ptr(0);
+ TCGv_ptr tp, i = tcg_temp_new_ptr();
+ tcg_gen_movi_ptr(i, 0);
gen_set_label(loop);
t0 = tcg_temp_new_i64();
+ t1 = tcg_temp_new_i64();
tp = tcg_temp_new_ptr();
tcg_gen_add_ptr(tp, base, i);
tcg_gen_ld_i64(t0, tp, vofs);
- tcg_gen_addi_ptr(i, i, 8);
+ tcg_gen_ld_i64(t1, tp, vofs + 8);
+ tcg_gen_addi_ptr(i, i, 16);
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ);
- tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ t16 = tcg_temp_new_i128();
+ tcg_gen_concat_i64_i128(t16, t0, t1);
+
+ tcg_gen_qemu_st_i128(t16, clean_addr, midx, MO_LEUQ);
+ tcg_gen_addi_i64(clean_addr, clean_addr, 16);
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
}
/* Predicate register stores can be any multiple of 2. */
+ if (len_remain >= 8) {
+ t0 = tcg_temp_new_i64();
+ tcg_gen_ld_i64(t0, base, vofs + len_align);
+ tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+ len_remain -= 8;
+ len_align += 8;
+ if (len_remain) {
+ tcg_gen_addi_i64(clean_addr, clean_addr, 8);
+ }
+ }
if (len_remain) {
t0 = tcg_temp_new_i64();
tcg_gen_ld_i64(t0, base, vofs + len_align);
case 4:
case 8:
tcg_gen_qemu_st_i64(t0, clean_addr, midx,
- MO_LE | ctz32(len_remain));
+ MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
break;
case 6:
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL);
+ tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
tcg_gen_addi_i64(clean_addr, clean_addr, 4);
tcg_gen_shri_i64(t0, t0, 32);
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW);
+ tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
break;
default:
unsigned msz = dtype_msz(a->dtype);
TCGLabel *over;
TCGv_i64 temp, clean_addr;
+ MemOp memop;
if (!dc_isar_feature(aa64_sve, s)) {
return false;
/* Load the data. */
temp = tcg_temp_new_i64();
tcg_gen_addi_i64(temp, cpu_reg_sp(s, a->rn), a->imm << msz);
- clean_addr = gen_mte_check1(s, temp, false, true, msz);
- tcg_gen_qemu_ld_i64(temp, clean_addr, get_mem_index(s),
- finalize_memop(s, dtype_mop[a->dtype]));
+ memop = finalize_memop(s, dtype_mop[a->dtype]);
+ clean_addr = gen_mte_check1(s, temp, false, true, memop);
+ tcg_gen_qemu_ld_i64(temp, clean_addr, get_mem_index(s), memop);
/* Broadcast to *all* elements. */
tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd),