target/loongarch: Implement xvld xvst

This patch includes:
- XVLD[X], XVST[X];
- XVLDREPL.{B/H/W/D};
- XVSTELM.{B/H/W/D}.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-56-gaosong@loongson.cn>
This commit is contained in:
Song Gao 2023-09-14 10:26:43 +08:00
parent 513e88a24d
commit 4a26512f01
No known key found for this signature in database
GPG Key ID: 40A2FFF239263EDF
3 changed files with 190 additions and 56 deletions

View File

@ -1753,6 +1753,16 @@ static void output_vvr_x(DisasContext *ctx, arg_vvr *a, const char *mnemonic)
output(ctx, mnemonic, "x%d, x%d, r%d", a->vd, a->vj, a->rk);
}
static void output_vrr_x(DisasContext *ctx, arg_vrr *a, const char *mnemonic)
{
output(ctx, mnemonic, "x%d, r%d, r%d", a->vd, a->rj, a->rk);
}
static void output_vr_ii_x(DisasContext *ctx, arg_vr_ii *a, const char *mnemonic)
{
output(ctx, mnemonic, "x%d, r%d, 0x%x, 0x%x", a->vd, a->rj, a->imm, a->imm2);
}
INSN_LASX(xvadd_b, vvv)
INSN_LASX(xvadd_h, vvv)
INSN_LASX(xvadd_w, vvv)
@ -2595,3 +2605,17 @@ INSN_LASX(xvextrins_d, vv_i)
INSN_LASX(xvextrins_w, vv_i)
INSN_LASX(xvextrins_h, vv_i)
INSN_LASX(xvextrins_b, vv_i)
INSN_LASX(xvld, vr_i)
INSN_LASX(xvst, vr_i)
INSN_LASX(xvldx, vrr)
INSN_LASX(xvstx, vrr)
INSN_LASX(xvldrepl_d, vr_i)
INSN_LASX(xvldrepl_w, vr_i)
INSN_LASX(xvldrepl_h, vr_i)
INSN_LASX(xvldrepl_b, vr_i)
INSN_LASX(xvstelm_d, vr_ii)
INSN_LASX(xvstelm_w, vr_ii)
INSN_LASX(xvstelm_h, vr_ii)
INSN_LASX(xvstelm_b, vr_ii)

View File

@ -5368,63 +5368,155 @@ static bool trans_vstx(DisasContext *ctx, arg_vrr *a)
return true;
}
#define VLDREPL(NAME, MO) \
static bool trans_## NAME (DisasContext *ctx, arg_vr_i *a) \
{ \
TCGv addr; \
TCGv_i64 val; \
\
if (!avail_LSX(ctx)) { \
return false; \
} \
\
if (!check_vec(ctx, 16)) { \
return true; \
} \
\
addr = gpr_src(ctx, a->rj, EXT_NONE); \
val = tcg_temp_new_i64(); \
\
addr = make_address_i(ctx, addr, a->imm); \
\
tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, MO); \
tcg_gen_gvec_dup_i64(MO, vec_full_offset(a->vd), 16, ctx->vl/8, val); \
\
return true; \
static bool do_vldrepl_vl(DisasContext *ctx, arg_vr_i *a,
uint32_t oprsz, MemOp mop)
{
TCGv addr;
TCGv_i64 val;
if (!check_vec(ctx, oprsz)) {
return true;
}
addr = gpr_src(ctx, a->rj, EXT_NONE);
val = tcg_temp_new_i64();
addr = make_address_i(ctx, addr, a->imm);
tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, mop);
tcg_gen_gvec_dup_i64(mop, vec_full_offset(a->vd), oprsz, ctx->vl / 8, val);
return true;
}
VLDREPL(vldrepl_b, MO_8)
VLDREPL(vldrepl_h, MO_16)
VLDREPL(vldrepl_w, MO_32)
VLDREPL(vldrepl_d, MO_64)
#define VSTELM(NAME, MO, E) \
static bool trans_## NAME (DisasContext *ctx, arg_vr_ii *a) \
{ \
TCGv addr; \
TCGv_i64 val; \
\
if (!avail_LSX(ctx)) { \
return false; \
} \
\
if (!check_vec(ctx, 16)) { \
return true; \
} \
\
addr = gpr_src(ctx, a->rj, EXT_NONE); \
val = tcg_temp_new_i64(); \
\
addr = make_address_i(ctx, addr, a->imm); \
\
tcg_gen_ld_i64(val, cpu_env, \
offsetof(CPULoongArchState, fpr[a->vd].vreg.E(a->imm2))); \
tcg_gen_qemu_st_i64(val, addr, ctx->mem_idx, MO); \
\
return true; \
static bool do_vldrepl(DisasContext *ctx, arg_vr_i *a, MemOp mop)
{
return do_vldrepl_vl(ctx, a, 16, mop);
}
VSTELM(vstelm_b, MO_8, B)
VSTELM(vstelm_h, MO_16, H)
VSTELM(vstelm_w, MO_32, W)
VSTELM(vstelm_d, MO_64, D)
static bool do_xvldrepl(DisasContext *ctx, arg_vr_i *a, MemOp mop)
{
return do_vldrepl_vl(ctx, a, 32, mop);
}
TRANS(vldrepl_b, LSX, do_vldrepl, MO_8)
TRANS(vldrepl_h, LSX, do_vldrepl, MO_16)
TRANS(vldrepl_w, LSX, do_vldrepl, MO_32)
TRANS(vldrepl_d, LSX, do_vldrepl, MO_64)
TRANS(xvldrepl_b, LASX, do_xvldrepl, MO_8)
TRANS(xvldrepl_h, LASX, do_xvldrepl, MO_16)
TRANS(xvldrepl_w, LASX, do_xvldrepl, MO_32)
TRANS(xvldrepl_d, LASX, do_xvldrepl, MO_64)
static bool do_vstelm_vl(DisasContext *ctx,
arg_vr_ii *a, uint32_t oprsz, MemOp mop)
{
TCGv addr;
TCGv_i64 val;
if (!check_vec(ctx, oprsz)) {
return true;
}
addr = gpr_src(ctx, a->rj, EXT_NONE);
val = tcg_temp_new_i64();
addr = make_address_i(ctx, addr, a->imm);
tcg_gen_ld_i64(val, cpu_env, vec_reg_offset(a->vd, a->imm2, mop));
tcg_gen_qemu_st_i64(val, addr, ctx->mem_idx, mop);
return true;
}
static bool do_vstelm(DisasContext *ctx, arg_vr_ii *a, MemOp mop)
{
return do_vstelm_vl(ctx, a, 16, mop);
}
static bool do_xvstelm(DisasContext *ctx, arg_vr_ii *a, MemOp mop)
{
return do_vstelm_vl(ctx, a, 32, mop);
}
TRANS(vstelm_b, LSX, do_vstelm, MO_8)
TRANS(vstelm_h, LSX, do_vstelm, MO_16)
TRANS(vstelm_w, LSX, do_vstelm, MO_32)
TRANS(vstelm_d, LSX, do_vstelm, MO_64)
TRANS(xvstelm_b, LASX, do_xvstelm, MO_8)
TRANS(xvstelm_h, LASX, do_xvstelm, MO_16)
TRANS(xvstelm_w, LASX, do_xvstelm, MO_32)
TRANS(xvstelm_d, LASX, do_xvstelm, MO_64)
static bool gen_lasx_memory(DisasContext *ctx, arg_vr_i *a,
void (*func)(DisasContext *, int, TCGv))
{
TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
TCGv temp = NULL;
if (!check_vec(ctx, 32)) {
return true;
}
if (a->imm) {
temp = tcg_temp_new();
tcg_gen_addi_tl(temp, addr, a->imm);
addr = temp;
}
func(ctx, a->vd, addr);
return true;
}
static void gen_xvld(DisasContext *ctx, int vreg, TCGv addr)
{
int i;
TCGv temp = tcg_temp_new();
TCGv dest = tcg_temp_new();
tcg_gen_qemu_ld_i64(dest, addr, ctx->mem_idx, MO_TEUQ);
set_vreg64(dest, vreg, 0);
for (i = 1; i < 4; i++) {
tcg_gen_addi_tl(temp, addr, 8 * i);
tcg_gen_qemu_ld_i64(dest, temp, ctx->mem_idx, MO_TEUQ);
set_vreg64(dest, vreg, i);
}
}
static void gen_xvst(DisasContext * ctx, int vreg, TCGv addr)
{
int i;
TCGv temp = tcg_temp_new();
TCGv dest = tcg_temp_new();
get_vreg64(dest, vreg, 0);
tcg_gen_qemu_st_i64(dest, addr, ctx->mem_idx, MO_TEUQ);
for (i = 1; i < 4; i++) {
tcg_gen_addi_tl(temp, addr, 8 * i);
get_vreg64(dest, vreg, i);
tcg_gen_qemu_st_i64(dest, temp, ctx->mem_idx, MO_TEUQ);
}
}
TRANS(xvld, LASX, gen_lasx_memory, gen_xvld)
TRANS(xvst, LASX, gen_lasx_memory, gen_xvst)
static bool gen_lasx_memoryx(DisasContext *ctx, arg_vrr *a,
void (*func)(DisasContext*, int, TCGv))
{
TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
TCGv addr = tcg_temp_new();
if (!check_vec(ctx, 32)) {
return true;
}
tcg_gen_add_tl(addr, src1, src2);
func(ctx, a->vd, addr);
return true;
}
TRANS(xvldx, LASX, gen_lasx_memoryx, gen_xvld)
TRANS(xvstx, LASX, gen_lasx_memoryx, gen_xvst)

View File

@ -550,6 +550,10 @@ dbcl 0000 00000010 10101 ............... @i15
@vr_i8i2 .... ........ imm2:2 ........ rj:5 vd:5 &vr_ii imm=%i8s2
@vr_i8i3 .... ....... imm2:3 ........ rj:5 vd:5 &vr_ii imm=%i8s1
@vr_i8i4 .... ...... imm2:4 imm:s8 rj:5 vd:5 &vr_ii
@vr_i8i2x .... ........ imm2:2 ........ rj:5 vd:5 &vr_ii imm=%i8s3
@vr_i8i3x .... ....... imm2:3 ........ rj:5 vd:5 &vr_ii imm=%i8s2
@vr_i8i4x .... ...... imm2:4 ........ rj:5 vd:5 &vr_ii imm=%i8s1
@vr_i8i5x .... ..... imm2:5 imm:s8 rj:5 vd:5 &vr_ii
@vrr .... ........ ..... rk:5 rj:5 vd:5 &vrr
@v_i13 .... ........ .. imm:13 vd:5 &v_i
@ -2060,3 +2064,17 @@ xvextrins_d 0111 01111000 00 ........ ..... ..... @vv_ui8
xvextrins_w 0111 01111000 01 ........ ..... ..... @vv_ui8
xvextrins_h 0111 01111000 10 ........ ..... ..... @vv_ui8
xvextrins_b 0111 01111000 11 ........ ..... ..... @vv_ui8
xvld 0010 110010 ............ ..... ..... @vr_i12
xvst 0010 110011 ............ ..... ..... @vr_i12
xvldx 0011 10000100 10000 ..... ..... ..... @vrr
xvstx 0011 10000100 11000 ..... ..... ..... @vrr
xvldrepl_d 0011 00100001 0 ......... ..... ..... @vr_i9
xvldrepl_w 0011 00100010 .......... ..... ..... @vr_i10
xvldrepl_h 0011 0010010 ........... ..... ..... @vr_i11
xvldrepl_b 0011 001010 ............ ..... ..... @vr_i12
xvstelm_d 0011 00110001 .. ........ ..... ..... @vr_i8i2x
xvstelm_w 0011 0011001 ... ........ ..... ..... @vr_i8i3x
xvstelm_h 0011 001101 .... ........ ..... ..... @vr_i8i4x
xvstelm_b 0011 00111 ..... ........ ..... ..... @vr_i8i5x