OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity
ecda15d137
qemu-e2k/target/arm/translate-mve.c
Peter Maydell 075e7e97e3 target/arm: Implement MVE interleaving loads/stores 
Implement the MVE interleaving load/store functions VLD2, VLD4, VST2
and VST4.  VLD2 loads 16 bytes of data from memory and writes to 2
consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes
to 4 consecutive Qregs.  The 'pattern' field in the encoding
determines the offset into memory which is accessed and also which
elements in the Qregs are written to.  (The intention is that a
sequence of four consecutive VLD4 with different pattern values
performs a complete de-interleaving load of 64 bytes into all
elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-25 10:48:50 +01:00

1877 lines
56 KiB
C
Raw Blame History

/*
* ARM translation: M-profile MVE instructions
*
* Copyright (c) 2021 Linaro, Ltd.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "tcg/tcg-op.h"
#include "tcg/tcg-op-gvec.h"
#include "exec/exec-all.h"
#include "exec/gen-icount.h"
#include "translate.h"
#include "translate-a32.h"
static inline int vidup_imm(DisasContext *s, int x)
{
return 1 << x;
}
/* Include the generated decoder */
#include "decode-mve.c.inc"
typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenLdStIlFn(TCGv_ptr, TCGv_i32, TCGv_i32);
typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenLongDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32);
typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32);
typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
/* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
static inline long mve_qreg_offset(unsigned reg)
{
return offsetof(CPUARMState, vfp.zregs[reg].d[0]);
}
static TCGv_ptr mve_qreg_ptr(unsigned reg)
{
TCGv_ptr ret = tcg_temp_new_ptr();
tcg_gen_addi_ptr(ret, cpu_env, mve_qreg_offset(reg));
return ret;
}
static bool mve_check_qreg_bank(DisasContext *s, int qmask)
{
/*
* Check whether Qregs are in range. For v8.1M only Q0..Q7
* are supported, see VFPSmallRegisterBank().
*/
return qmask < 8;
}
bool mve_eci_check(DisasContext *s)
{
/*
* This is a beatwise insn: check that ECI is valid (not a
* reserved value) and note that we are handling it.
* Return true if OK, false if we generated an exception.
*/
s->eci_handled = true;
switch (s->eci) {
case ECI_NONE:
case ECI_A0:
case ECI_A0A1:
case ECI_A0A1A2:
case ECI_A0A1A2B0:
return true;
default:
/* Reserved value: INVSTATE UsageFault */
gen_exception_insn(s, s->pc_curr, EXCP_INVSTATE, syn_uncategorized(),
default_exception_el(s));
return false;
}
}
void mve_update_eci(DisasContext *s)
{
/*
* The helper function will always update the CPUState field,
* so we only need to update the DisasContext field.
*/
if (s->eci) {
s->eci = (s->eci == ECI_A0A1A2B0) ? ECI_A0 : ECI_NONE;
}
}
void mve_update_and_store_eci(DisasContext *s)
{
/*
* For insns which don't call a helper function that will call
* mve_advance_vpt(), this version updates s->eci and also stores
* it out to the CPUState field.
*/
if (s->eci) {
mve_update_eci(s);
store_cpu_field(tcg_constant_i32(s->eci << 4), condexec_bits);
}
}
static bool mve_skip_first_beat(DisasContext *s)
{
/* Return true if PSR.ECI says we must skip the first beat of this insn */
switch (s->eci) {
case ECI_NONE:
return false;
case ECI_A0:
case ECI_A0A1:
case ECI_A0A1A2:
case ECI_A0A1A2B0:
return true;
default:
g_assert_not_reached();
}
}
static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn,
unsigned msize)
{
TCGv_i32 addr;
uint32_t offset;
TCGv_ptr qreg;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd) ||
!fn) {
return false;
}
/* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
if (a->rn == 15 || (a->rn == 13 && a->w)) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
offset = a->imm << msize;
if (!a->a) {
offset = -offset;
}
addr = load_reg(s, a->rn);
if (a->p) {
tcg_gen_addi_i32(addr, addr, offset);
}
qreg = mve_qreg_ptr(a->qd);
fn(cpu_env, qreg, addr);
tcg_temp_free_ptr(qreg);
/*
* Writeback always happens after the last beat of the insn,
* regardless of predication
*/
if (a->w) {
if (!a->p) {
tcg_gen_addi_i32(addr, addr, offset);
}
store_reg(s, a->rn, addr);
} else {
tcg_temp_free_i32(addr);
}
mve_update_eci(s);
return true;
}
static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a)
{
static MVEGenLdStFn * const ldstfns[4][2] = {
{ gen_helper_mve_vstrb, gen_helper_mve_vldrb },
{ gen_helper_mve_vstrh, gen_helper_mve_vldrh },
{ gen_helper_mve_vstrw, gen_helper_mve_vldrw },
{ NULL, NULL }
};
return do_ldst(s, a, ldstfns[a->size][a->l], a->size);
}
#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \
static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \
{ \
static MVEGenLdStFn * const ldstfns[2][2] = { \
{ gen_helper_mve_##ST, gen_helper_mve_##SLD }, \
{ NULL, gen_helper_mve_##ULD }, \
}; \
return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \
}
DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8)
DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8)
DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16)
static bool do_ldst_sg(DisasContext *s, arg_vldst_sg *a, MVEGenLdStSGFn fn)
{
TCGv_i32 addr;
TCGv_ptr qd, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn || a->rn == 15) {
/* Rn case is UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
addr = load_reg(s, a->rn);
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm, addr);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
tcg_temp_free_i32(addr);
mve_update_eci(s);
return true;
}
/*
* The naming scheme here is "vldrb_sg_sh == in-memory byte loads
* signextended to halfword elements in register". _os_ indicates that
* the offsets in Qm should be scaled by the element size.
*/
/* This macro is just to make the arrays more compact in these functions */
#define F(N) gen_helper_mve_##N
/* VLDRB/VSTRB (ie msize 1) with OS=1 is UNPREDICTABLE; we UNDEF */
static bool trans_VLDR_S_sg(DisasContext *s, arg_vldst_sg *a)
{
static MVEGenLdStSGFn * const fns[2][4][4] = { {
{ NULL, F(vldrb_sg_sh), F(vldrb_sg_sw), NULL },
{ NULL, NULL, F(vldrh_sg_sw), NULL },
{ NULL, NULL, NULL, NULL },
{ NULL, NULL, NULL, NULL }
}, {
{ NULL, NULL, NULL, NULL },
{ NULL, NULL, F(vldrh_sg_os_sw), NULL },
{ NULL, NULL, NULL, NULL },
{ NULL, NULL, NULL, NULL }
}
};
if (a->qd == a->qm) {
return false; /* UNPREDICTABLE */
}
return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]);
}
static bool trans_VLDR_U_sg(DisasContext *s, arg_vldst_sg *a)
{
static MVEGenLdStSGFn * const fns[2][4][4] = { {
{ F(vldrb_sg_ub), F(vldrb_sg_uh), F(vldrb_sg_uw), NULL },
{ NULL, F(vldrh_sg_uh), F(vldrh_sg_uw), NULL },
{ NULL, NULL, F(vldrw_sg_uw), NULL },
{ NULL, NULL, NULL, F(vldrd_sg_ud) }
}, {
{ NULL, NULL, NULL, NULL },
{ NULL, F(vldrh_sg_os_uh), F(vldrh_sg_os_uw), NULL },
{ NULL, NULL, F(vldrw_sg_os_uw), NULL },
{ NULL, NULL, NULL, F(vldrd_sg_os_ud) }
}
};
if (a->qd == a->qm) {
return false; /* UNPREDICTABLE */
}
return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]);
}
static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a)
{
static MVEGenLdStSGFn * const fns[2][4][4] = { {
{ F(vstrb_sg_ub), F(vstrb_sg_uh), F(vstrb_sg_uw), NULL },
{ NULL, F(vstrh_sg_uh), F(vstrh_sg_uw), NULL },
{ NULL, NULL, F(vstrw_sg_uw), NULL },
{ NULL, NULL, NULL, F(vstrd_sg_ud) }
}, {
{ NULL, NULL, NULL, NULL },
{ NULL, F(vstrh_sg_os_uh), F(vstrh_sg_os_uw), NULL },
{ NULL, NULL, F(vstrw_sg_os_uw), NULL },
{ NULL, NULL, NULL, F(vstrd_sg_os_ud) }
}
};
return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]);
}
#undef F
static bool do_ldst_sg_imm(DisasContext *s, arg_vldst_sg_imm *a,
MVEGenLdStSGFn *fn, unsigned msize)
{
uint32_t offset;
TCGv_ptr qd, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
offset = a->imm << msize;
if (!a->a) {
offset = -offset;
}
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm, tcg_constant_i32(offset));
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
static bool trans_VLDRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a)
{
static MVEGenLdStSGFn * const fns[] = {
gen_helper_mve_vldrw_sg_uw,
gen_helper_mve_vldrw_sg_wb_uw,
};
if (a->qd == a->qm) {
return false; /* UNPREDICTABLE */
}
return do_ldst_sg_imm(s, a, fns[a->w], MO_32);
}
static bool trans_VLDRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a)
{
static MVEGenLdStSGFn * const fns[] = {
gen_helper_mve_vldrd_sg_ud,
gen_helper_mve_vldrd_sg_wb_ud,
};
if (a->qd == a->qm) {
return false; /* UNPREDICTABLE */
}
return do_ldst_sg_imm(s, a, fns[a->w], MO_64);
}
static bool trans_VSTRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a)
{
static MVEGenLdStSGFn * const fns[] = {
gen_helper_mve_vstrw_sg_uw,
gen_helper_mve_vstrw_sg_wb_uw,
};
return do_ldst_sg_imm(s, a, fns[a->w], MO_32);
}
static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a)
{
static MVEGenLdStSGFn * const fns[] = {
gen_helper_mve_vstrd_sg_ud,
gen_helper_mve_vstrd_sg_wb_ud,
};
return do_ldst_sg_imm(s, a, fns[a->w], MO_64);
}
static bool do_vldst_il(DisasContext *s, arg_vldst_il *a, MVEGenLdStIlFn *fn,
int addrinc)
{
TCGv_i32 rn;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd) ||
!fn || (a->rn == 13 && a->w) || a->rn == 15) {
/* Variously UNPREDICTABLE or UNDEF or related-encoding */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
rn = load_reg(s, a->rn);
/*
* We pass the index of Qd, not a pointer, because the helper must
* access multiple Q registers starting at Qd and working up.
*/
fn(cpu_env, tcg_constant_i32(a->qd), rn);
if (a->w) {
tcg_gen_addi_i32(rn, rn, addrinc);
store_reg(s, a->rn, rn);
} else {
tcg_temp_free_i32(rn);
}
mve_update_and_store_eci(s);
return true;
}
/* This macro is just to make the arrays more compact in these functions */
#define F(N) gen_helper_mve_##N
static bool trans_VLD2(DisasContext *s, arg_vldst_il *a)
{
static MVEGenLdStIlFn * const fns[4][4] = {
{ F(vld20b), F(vld20h), F(vld20w), NULL, },
{ F(vld21b), F(vld21h), F(vld21w), NULL, },
{ NULL, NULL, NULL, NULL },
{ NULL, NULL, NULL, NULL },
};
if (a->qd > 6) {
return false;
}
return do_vldst_il(s, a, fns[a->pat][a->size], 32);
}
static bool trans_VLD4(DisasContext *s, arg_vldst_il *a)
{
static MVEGenLdStIlFn * const fns[4][4] = {
{ F(vld40b), F(vld40h), F(vld40w), NULL, },
{ F(vld41b), F(vld41h), F(vld41w), NULL, },
{ F(vld42b), F(vld42h), F(vld42w), NULL, },
{ F(vld43b), F(vld43h), F(vld43w), NULL, },
};
if (a->qd > 4) {
return false;
}
return do_vldst_il(s, a, fns[a->pat][a->size], 64);
}
static bool trans_VST2(DisasContext *s, arg_vldst_il *a)
{
static MVEGenLdStIlFn * const fns[4][4] = {
{ F(vst20b), F(vst20h), F(vst20w), NULL, },
{ F(vst21b), F(vst21h), F(vst21w), NULL, },
{ NULL, NULL, NULL, NULL },
{ NULL, NULL, NULL, NULL },
};
if (a->qd > 6) {
return false;
}
return do_vldst_il(s, a, fns[a->pat][a->size], 32);
}
static bool trans_VST4(DisasContext *s, arg_vldst_il *a)
{
static MVEGenLdStIlFn * const fns[4][4] = {
{ F(vst40b), F(vst40h), F(vst40w), NULL, },
{ F(vst41b), F(vst41h), F(vst41w), NULL, },
{ F(vst42b), F(vst42h), F(vst42w), NULL, },
{ F(vst43b), F(vst43h), F(vst43w), NULL, },
};
if (a->qd > 4) {
return false;
}
return do_vldst_il(s, a, fns[a->pat][a->size], 64);
}
#undef F
static bool trans_VDUP(DisasContext *s, arg_VDUP *a)
{
TCGv_ptr qd;
TCGv_i32 rt;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd)) {
return false;
}
if (a->rt == 13 || a->rt == 15) {
/* UNPREDICTABLE; we choose to UNDEF */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
rt = load_reg(s, a->rt);
tcg_gen_dup_i32(a->size, rt, rt);
gen_helper_mve_vdup(cpu_env, qd, rt);
tcg_temp_free_ptr(qd);
tcg_temp_free_i32(rt);
mve_update_eci(s);
return true;
}
static bool do_1op(DisasContext *s, arg_1op *a, MVEGenOneOpFn fn)
{
TCGv_ptr qd, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_1OP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_1op *a) \
{ \
static MVEGenOneOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_1op(s, a, fns[a->size]); \
}
DO_1OP(VCLZ, vclz)
DO_1OP(VCLS, vcls)
DO_1OP(VABS, vabs)
DO_1OP(VNEG, vneg)
DO_1OP(VQABS, vqabs)
DO_1OP(VQNEG, vqneg)
DO_1OP(VMAXA, vmaxa)
DO_1OP(VMINA, vmina)
/* Narrowing moves: only size 0 and 1 are valid */
#define DO_VMOVN(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_1op *a) \
{ \
static MVEGenOneOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
NULL, \
NULL, \
}; \
return do_1op(s, a, fns[a->size]); \
}
DO_VMOVN(VMOVNB, vmovnb)
DO_VMOVN(VMOVNT, vmovnt)
DO_VMOVN(VQMOVUNB, vqmovunb)
DO_VMOVN(VQMOVUNT, vqmovunt)
DO_VMOVN(VQMOVN_BS, vqmovnbs)
DO_VMOVN(VQMOVN_TS, vqmovnts)
DO_VMOVN(VQMOVN_BU, vqmovnbu)
DO_VMOVN(VQMOVN_TU, vqmovntu)
static bool trans_VREV16(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev16b,
NULL,
NULL,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VREV32(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev32b,
gen_helper_mve_vrev32h,
NULL,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VREV64(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev64b,
gen_helper_mve_vrev64h,
gen_helper_mve_vrev64w,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VMVN(DisasContext *s, arg_1op *a)
{
return do_1op(s, a, gen_helper_mve_vmvn);
}
static bool trans_VABS_fp(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
NULL,
gen_helper_mve_vfabsh,
gen_helper_mve_vfabss,
NULL,
};
if (!dc_isar_feature(aa32_mve_fp, s)) {
return false;
}
return do_1op(s, a, fns[a->size]);
}
static bool trans_VNEG_fp(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
NULL,
gen_helper_mve_vfnegh,
gen_helper_mve_vfnegs,
NULL,
};
if (!dc_isar_feature(aa32_mve_fp, s)) {
return false;
}
return do_1op(s, a, fns[a->size]);
}
static bool do_2op(DisasContext *s, arg_2op *a, MVEGenTwoOpFn fn)
{
TCGv_ptr qd, qn, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qn | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qn = mve_qreg_ptr(a->qn);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qn, qm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qn);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_LOGIC(INSN, HELPER) \
static bool trans_##INSN(DisasContext *s, arg_2op *a) \
{ \
return do_2op(s, a, HELPER); \
}
DO_LOGIC(VAND, gen_helper_mve_vand)
DO_LOGIC(VBIC, gen_helper_mve_vbic)
DO_LOGIC(VORR, gen_helper_mve_vorr)
DO_LOGIC(VORN, gen_helper_mve_vorn)
DO_LOGIC(VEOR, gen_helper_mve_veor)
DO_LOGIC(VPSEL, gen_helper_mve_vpsel)
#define DO_2OP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_2op *a) \
{ \
static MVEGenTwoOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_2op(s, a, fns[a->size]); \
}
DO_2OP(VADD, vadd)
DO_2OP(VSUB, vsub)
DO_2OP(VMUL, vmul)
DO_2OP(VMULH_S, vmulhs)
DO_2OP(VMULH_U, vmulhu)
DO_2OP(VRMULH_S, vrmulhs)
DO_2OP(VRMULH_U, vrmulhu)
DO_2OP(VMAX_S, vmaxs)
DO_2OP(VMAX_U, vmaxu)
DO_2OP(VMIN_S, vmins)
DO_2OP(VMIN_U, vminu)
DO_2OP(VABD_S, vabds)
DO_2OP(VABD_U, vabdu)
DO_2OP(VHADD_S, vhadds)
DO_2OP(VHADD_U, vhaddu)
DO_2OP(VHSUB_S, vhsubs)
DO_2OP(VHSUB_U, vhsubu)
DO_2OP(VMULL_BS, vmullbs)
DO_2OP(VMULL_BU, vmullbu)
DO_2OP(VMULL_TS, vmullts)
DO_2OP(VMULL_TU, vmulltu)
DO_2OP(VQDMULH, vqdmulh)
DO_2OP(VQRDMULH, vqrdmulh)
DO_2OP(VQADD_S, vqadds)
DO_2OP(VQADD_U, vqaddu)
DO_2OP(VQSUB_S, vqsubs)
DO_2OP(VQSUB_U, vqsubu)
DO_2OP(VSHL_S, vshls)
DO_2OP(VSHL_U, vshlu)
DO_2OP(VRSHL_S, vrshls)
DO_2OP(VRSHL_U, vrshlu)
DO_2OP(VQSHL_S, vqshls)
DO_2OP(VQSHL_U, vqshlu)
DO_2OP(VQRSHL_S, vqrshls)
DO_2OP(VQRSHL_U, vqrshlu)
DO_2OP(VQDMLADH, vqdmladh)
DO_2OP(VQDMLADHX, vqdmladhx)
DO_2OP(VQRDMLADH, vqrdmladh)
DO_2OP(VQRDMLADHX, vqrdmladhx)
DO_2OP(VQDMLSDH, vqdmlsdh)
DO_2OP(VQDMLSDHX, vqdmlsdhx)
DO_2OP(VQRDMLSDH, vqrdmlsdh)
DO_2OP(VQRDMLSDHX, vqrdmlsdhx)
DO_2OP(VRHADD_S, vrhadds)
DO_2OP(VRHADD_U, vrhaddu)
/*
* VCADD Qd == Qm at size MO_32 is UNPREDICTABLE; we choose not to diagnose
* so we can reuse the DO_2OP macro. (Our implementation calculates the
* "expected" results in this case.) Similarly for VHCADD.
*/
DO_2OP(VCADD90, vcadd90)
DO_2OP(VCADD270, vcadd270)
DO_2OP(VHCADD90, vhcadd90)
DO_2OP(VHCADD270, vhcadd270)
static bool trans_VQDMULLB(DisasContext *s, arg_2op *a)
{
static MVEGenTwoOpFn * const fns[] = {
NULL,
gen_helper_mve_vqdmullbh,
gen_helper_mve_vqdmullbw,
NULL,
};
if (a->size == MO_32 && (a->qd == a->qm || a->qd == a->qn)) {
/* UNPREDICTABLE; we choose to undef */
return false;
}
return do_2op(s, a, fns[a->size]);
}
static bool trans_VQDMULLT(DisasContext *s, arg_2op *a)
{
static MVEGenTwoOpFn * const fns[] = {
NULL,
gen_helper_mve_vqdmullth,
gen_helper_mve_vqdmulltw,
NULL,
};
if (a->size == MO_32 && (a->qd == a->qm || a->qd == a->qn)) {
/* UNPREDICTABLE; we choose to undef */
return false;
}
return do_2op(s, a, fns[a->size]);
}
static bool trans_VMULLP_B(DisasContext *s, arg_2op *a)
{
/*
* Note that a->size indicates the output size, ie VMULL.P8
* is the 8x8->16 operation and a->size is MO_16; VMULL.P16
* is the 16x16->32 operation and a->size is MO_32.
*/
static MVEGenTwoOpFn * const fns[] = {
NULL,
gen_helper_mve_vmullpbh,
gen_helper_mve_vmullpbw,
NULL,
};
return do_2op(s, a, fns[a->size]);
}
static bool trans_VMULLP_T(DisasContext *s, arg_2op *a)
{
/* a->size is as for trans_VMULLP_B */
static MVEGenTwoOpFn * const fns[] = {
NULL,
gen_helper_mve_vmullpth,
gen_helper_mve_vmullptw,
NULL,
};
return do_2op(s, a, fns[a->size]);
}
/*
* VADC and VSBC: these perform an add-with-carry or subtract-with-carry
* of the 32-bit elements in each lane of the input vectors, where the
* carry-out of each add is the carry-in of the next. The initial carry
* input is either fixed (0 for VADCI, 1 for VSBCI) or is from FPSCR.C
* (for VADC and VSBC); the carry out at the end is written back to FPSCR.C.
* These insns are subject to beat-wise execution. Partial execution
* of an I=1 (initial carry input fixed) insn which does not
* execute the first beat must start with the current FPSCR.NZCV
* value, not the fixed constant input.
*/
static bool trans_VADC(DisasContext *s, arg_2op *a)
{
return do_2op(s, a, gen_helper_mve_vadc);
}
static bool trans_VADCI(DisasContext *s, arg_2op *a)
{
if (mve_skip_first_beat(s)) {
return trans_VADC(s, a);
}
return do_2op(s, a, gen_helper_mve_vadci);
}
static bool trans_VSBC(DisasContext *s, arg_2op *a)
{
return do_2op(s, a, gen_helper_mve_vsbc);
}
static bool trans_VSBCI(DisasContext *s, arg_2op *a)
{
if (mve_skip_first_beat(s)) {
return trans_VSBC(s, a);
}
return do_2op(s, a, gen_helper_mve_vsbci);
}
static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
MVEGenTwoOpScalarFn fn)
{
TCGv_ptr qd, qn;
TCGv_i32 rm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qn) ||
!fn) {
return false;
}
if (a->rm == 13 || a->rm == 15) {
/* UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qn = mve_qreg_ptr(a->qn);
rm = load_reg(s, a->rm);
fn(cpu_env, qd, qn, rm);
tcg_temp_free_i32(rm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qn);
mve_update_eci(s);
return true;
}
#define DO_2OP_SCALAR(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \
{ \
static MVEGenTwoOpScalarFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_2op_scalar(s, a, fns[a->size]); \
}
DO_2OP_SCALAR(VADD_scalar, vadd_scalar)
DO_2OP_SCALAR(VSUB_scalar, vsub_scalar)
DO_2OP_SCALAR(VMUL_scalar, vmul_scalar)
DO_2OP_SCALAR(VHADD_S_scalar, vhadds_scalar)
DO_2OP_SCALAR(VHADD_U_scalar, vhaddu_scalar)
DO_2OP_SCALAR(VHSUB_S_scalar, vhsubs_scalar)
DO_2OP_SCALAR(VHSUB_U_scalar, vhsubu_scalar)
DO_2OP_SCALAR(VQADD_S_scalar, vqadds_scalar)
DO_2OP_SCALAR(VQADD_U_scalar, vqaddu_scalar)
DO_2OP_SCALAR(VQSUB_S_scalar, vqsubs_scalar)
DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar)
DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar)
DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar)
DO_2OP_SCALAR(VBRSR, vbrsr)
DO_2OP_SCALAR(VMLA, vmla)
DO_2OP_SCALAR(VMLAS, vmlas)
DO_2OP_SCALAR(VQDMLAH, vqdmlah)
DO_2OP_SCALAR(VQRDMLAH, vqrdmlah)
DO_2OP_SCALAR(VQDMLASH, vqdmlash)
DO_2OP_SCALAR(VQRDMLASH, vqrdmlash)
static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a)
{
static MVEGenTwoOpScalarFn * const fns[] = {
NULL,
gen_helper_mve_vqdmullb_scalarh,
gen_helper_mve_vqdmullb_scalarw,
NULL,
};
if (a->qd == a->qn && a->size == MO_32) {
/* UNPREDICTABLE; we choose to undef */
return false;
}
return do_2op_scalar(s, a, fns[a->size]);
}
static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a)
{
static MVEGenTwoOpScalarFn * const fns[] = {
NULL,
gen_helper_mve_vqdmullt_scalarh,
gen_helper_mve_vqdmullt_scalarw,
NULL,
};
if (a->qd == a->qn && a->size == MO_32) {
/* UNPREDICTABLE; we choose to undef */
return false;
}
return do_2op_scalar(s, a, fns[a->size]);
}
static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a,
MVEGenLongDualAccOpFn *fn)
{
TCGv_ptr qn, qm;
TCGv_i64 rda;
TCGv_i32 rdalo, rdahi;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qn | a->qm) ||
!fn) {
return false;
}
/*
* rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related
* encoding; rdalo always has bit 0 clear so cannot be 13 or 15.
*/
if (a->rdahi == 13 || a->rdahi == 15) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qn = mve_qreg_ptr(a->qn);
qm = mve_qreg_ptr(a->qm);
/*
* This insn is subject to beat-wise execution. Partial execution
* of an A=0 (no-accumulate) insn which does not execute the first
* beat must start with the current rda value, not 0.
*/
if (a->a || mve_skip_first_beat(s)) {
rda = tcg_temp_new_i64();
rdalo = load_reg(s, a->rdalo);
rdahi = load_reg(s, a->rdahi);
tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
tcg_temp_free_i32(rdalo);
tcg_temp_free_i32(rdahi);
} else {
rda = tcg_const_i64(0);
}
fn(rda, cpu_env, qn, qm, rda);
tcg_temp_free_ptr(qn);
tcg_temp_free_ptr(qm);
rdalo = tcg_temp_new_i32();
rdahi = tcg_temp_new_i32();
tcg_gen_extrl_i64_i32(rdalo, rda);
tcg_gen_extrh_i64_i32(rdahi, rda);
store_reg(s, a->rdalo, rdalo);
store_reg(s, a->rdahi, rdahi);
tcg_temp_free_i64(rda);
mve_update_eci(s);
return true;
}
static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[4][2] = {
{ NULL, NULL },
{ gen_helper_mve_vmlaldavsh, gen_helper_mve_vmlaldavxsh },
{ gen_helper_mve_vmlaldavsw, gen_helper_mve_vmlaldavxsw },
{ NULL, NULL },
};
return do_long_dual_acc(s, a, fns[a->size][a->x]);
}
static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[4][2] = {
{ NULL, NULL },
{ gen_helper_mve_vmlaldavuh, NULL },
{ gen_helper_mve_vmlaldavuw, NULL },
{ NULL, NULL },
};
return do_long_dual_acc(s, a, fns[a->size][a->x]);
}
static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[4][2] = {
{ NULL, NULL },
{ gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh },
{ gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw },
{ NULL, NULL },
};
return do_long_dual_acc(s, a, fns[a->size][a->x]);
}
static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[] = {
gen_helper_mve_vrmlaldavhsw, gen_helper_mve_vrmlaldavhxsw,
};
return do_long_dual_acc(s, a, fns[a->x]);
}
static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[] = {
gen_helper_mve_vrmlaldavhuw, NULL,
};
return do_long_dual_acc(s, a, fns[a->x]);
}
static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a)
{
static MVEGenLongDualAccOpFn * const fns[] = {
gen_helper_mve_vrmlsldavhsw, gen_helper_mve_vrmlsldavhxsw,
};
return do_long_dual_acc(s, a, fns[a->x]);
}
static bool do_dual_acc(DisasContext *s, arg_vmladav *a, MVEGenDualAccOpFn *fn)
{
TCGv_ptr qn, qm;
TCGv_i32 rda;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qn) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qn = mve_qreg_ptr(a->qn);
qm = mve_qreg_ptr(a->qm);
/*
* This insn is subject to beat-wise execution. Partial execution
* of an A=0 (no-accumulate) insn which does not execute the first
* beat must start with the current rda value, not 0.
*/
if (a->a || mve_skip_first_beat(s)) {
rda = load_reg(s, a->rda);
} else {
rda = tcg_const_i32(0);
}
fn(rda, cpu_env, qn, qm, rda);
store_reg(s, a->rda, rda);
tcg_temp_free_ptr(qn);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_DUAL_ACC(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_vmladav *a) \
{ \
static MVEGenDualAccOpFn * const fns[4][2] = { \
{ gen_helper_mve_##FN##b, gen_helper_mve_##FN##xb }, \
{ gen_helper_mve_##FN##h, gen_helper_mve_##FN##xh }, \
{ gen_helper_mve_##FN##w, gen_helper_mve_##FN##xw }, \
{ NULL, NULL }, \
}; \
return do_dual_acc(s, a, fns[a->size][a->x]); \
}
DO_DUAL_ACC(VMLADAV_S, vmladavs)
DO_DUAL_ACC(VMLSDAV, vmlsdav)
static bool trans_VMLADAV_U(DisasContext *s, arg_vmladav *a)
{
static MVEGenDualAccOpFn * const fns[4][2] = {
{ gen_helper_mve_vmladavub, NULL },
{ gen_helper_mve_vmladavuh, NULL },
{ gen_helper_mve_vmladavuw, NULL },
{ NULL, NULL },
};
return do_dual_acc(s, a, fns[a->size][a->x]);
}
static void gen_vpst(DisasContext *s, uint32_t mask)
{
/*
* Set the VPR mask fields. We take advantage of MASK01 and MASK23
* being adjacent fields in the register.
*
* Updating the masks is not predicated, but it is subject to beat-wise
* execution, and the mask is updated on the odd-numbered beats.
* So if PSR.ECI says we should skip beat 1, we mustn't update the
* 01 mask field.
*/
TCGv_i32 vpr = load_cpu_field(v7m.vpr);
switch (s->eci) {
case ECI_NONE:
case ECI_A0:
/* Update both 01 and 23 fields */
tcg_gen_deposit_i32(vpr, vpr,
tcg_constant_i32(mask | (mask << 4)),
R_V7M_VPR_MASK01_SHIFT,
R_V7M_VPR_MASK01_LENGTH + R_V7M_VPR_MASK23_LENGTH);
break;
case ECI_A0A1:
case ECI_A0A1A2:
case ECI_A0A1A2B0:
/* Update only the 23 mask field */
tcg_gen_deposit_i32(vpr, vpr,
tcg_constant_i32(mask),
R_V7M_VPR_MASK23_SHIFT, R_V7M_VPR_MASK23_LENGTH);
break;
default:
g_assert_not_reached();
}
store_cpu_field(vpr, v7m.vpr);
}
static bool trans_VPST(DisasContext *s, arg_VPST *a)
{
/* mask == 0 is a "related encoding" */
if (!dc_isar_feature(aa32_mve, s) || !a->mask) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
gen_vpst(s, a->mask);
mve_update_and_store_eci(s);
return true;
}
static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a)
{
/*
* Invert the predicate in VPR.P0. We have call out to
* a helper because this insn itself is beatwise and can
* be predicated.
*/
if (!dc_isar_feature(aa32_mve, s)) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
gen_helper_mve_vpnot(cpu_env);
mve_update_eci(s);
return true;
}
static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
{
/* VADDV: vector add across vector */
static MVEGenVADDVFn * const fns[4][2] = {
{ gen_helper_mve_vaddvsb, gen_helper_mve_vaddvub },
{ gen_helper_mve_vaddvsh, gen_helper_mve_vaddvuh },
{ gen_helper_mve_vaddvsw, gen_helper_mve_vaddvuw },
{ NULL, NULL }
};
TCGv_ptr qm;
TCGv_i32 rda;
if (!dc_isar_feature(aa32_mve, s) ||
a->size == 3) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
/*
* This insn is subject to beat-wise execution. Partial execution
* of an A=0 (no-accumulate) insn which does not execute the first
* beat must start with the current value of Rda, not zero.
*/
if (a->a || mve_skip_first_beat(s)) {
/* Accumulate input from Rda */
rda = load_reg(s, a->rda);
} else {
/* Accumulate starting at zero */
rda = tcg_const_i32(0);
}
qm = mve_qreg_ptr(a->qm);
fns[a->size][a->u](rda, cpu_env, qm, rda);
store_reg(s, a->rda, rda);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a)
{
/*
* Vector Add Long Across Vector: accumulate the 32-bit
* elements of the vector into a 64-bit result stored in
* a pair of general-purpose registers.
* No need to check Qm's bank: it is only 3 bits in decode.
*/
TCGv_ptr qm;
TCGv_i64 rda;
TCGv_i32 rdalo, rdahi;
if (!dc_isar_feature(aa32_mve, s)) {
return false;
}
/*
* rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related
* encoding; rdalo always has bit 0 clear so cannot be 13 or 15.
*/
if (a->rdahi == 13 || a->rdahi == 15) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
/*
* This insn is subject to beat-wise execution. Partial execution
* of an A=0 (no-accumulate) insn which does not execute the first
* beat must start with the current value of RdaHi:RdaLo, not zero.
*/
if (a->a || mve_skip_first_beat(s)) {
/* Accumulate input from RdaHi:RdaLo */
rda = tcg_temp_new_i64();
rdalo = load_reg(s, a->rdalo);
rdahi = load_reg(s, a->rdahi);
tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
tcg_temp_free_i32(rdalo);
tcg_temp_free_i32(rdahi);
} else {
/* Accumulate starting at zero */
rda = tcg_const_i64(0);
}
qm = mve_qreg_ptr(a->qm);
if (a->u) {
gen_helper_mve_vaddlv_u(rda, cpu_env, qm, rda);
} else {
gen_helper_mve_vaddlv_s(rda, cpu_env, qm, rda);
}
tcg_temp_free_ptr(qm);
rdalo = tcg_temp_new_i32();
rdahi = tcg_temp_new_i32();
tcg_gen_extrl_i64_i32(rdalo, rda);
tcg_gen_extrh_i64_i32(rdahi, rda);
store_reg(s, a->rdalo, rdalo);
store_reg(s, a->rdahi, rdahi);
tcg_temp_free_i64(rda);
mve_update_eci(s);
return true;
}
static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn)
{
TCGv_ptr qd;
uint64_t imm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
imm = asimd_imm_const(a->imm, a->cmode, a->op);
qd = mve_qreg_ptr(a->qd);
fn(cpu_env, qd, tcg_constant_i64(imm));
tcg_temp_free_ptr(qd);
mve_update_eci(s);
return true;
}
static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a)
{
/* Handle decode of cmode/op here between VORR/VBIC/VMOV */
MVEGenOneOpImmFn *fn;
if ((a->cmode & 1) && a->cmode < 12) {
if (a->op) {
/*
* For op=1, the immediate will be inverted by asimd_imm_const(),
* so the VBIC becomes a logical AND operation.
*/
fn = gen_helper_mve_vandi;
} else {
fn = gen_helper_mve_vorri;
}
} else {
/* There is one unallocated cmode/op combination in this space */
if (a->cmode == 15 && a->op == 1) {
return false;
}
/* asimd_imm_const() sorts out VMVNI vs VMOVI for us */
fn = gen_helper_mve_vmovi;
}
return do_1imm(s, a, fn);
}
static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn,
bool negateshift)
{
TCGv_ptr qd, qm;
int shift = a->shift;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
/*
* When we handle a right shift insn using a left-shift helper
* which permits a negative shift count to indicate a right-shift,
* we must negate the shift count.
*/
if (negateshift) {
shift = -shift;
}
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm, tcg_constant_i32(shift));
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \
static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
{ \
static MVEGenTwoOpShiftFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_2shift(s, a, fns[a->size], NEGATESHIFT); \
}
DO_2SHIFT(VSHLI, vshli_u, false)
DO_2SHIFT(VQSHLI_S, vqshli_s, false)
DO_2SHIFT(VQSHLI_U, vqshli_u, false)
DO_2SHIFT(VQSHLUI, vqshlui_s, false)
/* These right shifts use a left-shift helper with negated shift count */
DO_2SHIFT(VSHRI_S, vshli_s, true)
DO_2SHIFT(VSHRI_U, vshli_u, true)
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
DO_2SHIFT(VSRI, vsri, false)
DO_2SHIFT(VSLI, vsli, false)
static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a,
MVEGenTwoOpShiftFn *fn)
{
TCGv_ptr qda;
TCGv_i32 rm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qda) ||
a->rm == 13 || a->rm == 15 || !fn) {
/* Rm cases are UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qda = mve_qreg_ptr(a->qda);
rm = load_reg(s, a->rm);
fn(cpu_env, qda, qda, rm);
tcg_temp_free_ptr(qda);
tcg_temp_free_i32(rm);
mve_update_eci(s);
return true;
}
#define DO_2SHIFT_SCALAR(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_shl_scalar *a) \
{ \
static MVEGenTwoOpShiftFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_2shift_scalar(s, a, fns[a->size]); \
}
DO_2SHIFT_SCALAR(VSHL_S_scalar, vshli_s)
DO_2SHIFT_SCALAR(VSHL_U_scalar, vshli_u)
DO_2SHIFT_SCALAR(VRSHL_S_scalar, vrshli_s)
DO_2SHIFT_SCALAR(VRSHL_U_scalar, vrshli_u)
DO_2SHIFT_SCALAR(VQSHL_S_scalar, vqshli_s)
DO_2SHIFT_SCALAR(VQSHL_U_scalar, vqshli_u)
DO_2SHIFT_SCALAR(VQRSHL_S_scalar, vqrshli_s)
DO_2SHIFT_SCALAR(VQRSHL_U_scalar, vqrshli_u)
#define DO_VSHLL(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
{ \
static MVEGenTwoOpShiftFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
}; \
return do_2shift(s, a, fns[a->size], false); \
}
DO_VSHLL(VSHLL_BS, vshllbs)
DO_VSHLL(VSHLL_BU, vshllbu)
DO_VSHLL(VSHLL_TS, vshllts)
DO_VSHLL(VSHLL_TU, vshlltu)
#define DO_2SHIFT_N(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
{ \
static MVEGenTwoOpShiftFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
}; \
return do_2shift(s, a, fns[a->size], false); \
}
DO_2SHIFT_N(VSHRNB, vshrnb)
DO_2SHIFT_N(VSHRNT, vshrnt)
DO_2SHIFT_N(VRSHRNB, vrshrnb)
DO_2SHIFT_N(VRSHRNT, vrshrnt)
DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s)
DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s)
DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u)
DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u)
DO_2SHIFT_N(VQSHRUNB, vqshrunb)
DO_2SHIFT_N(VQSHRUNT, vqshrunt)
DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s)
DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s)
DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u)
DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u)
DO_2SHIFT_N(VQRSHRUNB, vqrshrunb)
DO_2SHIFT_N(VQRSHRUNT, vqrshrunt)
static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a)
{
/*
* Whole Vector Left Shift with Carry. The carry is taken
* from a general purpose register and written back there.
* An imm of 0 means "shift by 32".
*/
TCGv_ptr qd;
TCGv_i32 rdm;
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) {
return false;
}
if (a->rdm == 13 || a->rdm == 15) {
/* CONSTRAINED UNPREDICTABLE: we UNDEF */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
rdm = load_reg(s, a->rdm);
gen_helper_mve_vshlc(rdm, cpu_env, qd, rdm, tcg_constant_i32(a->imm));
store_reg(s, a->rdm, rdm);
tcg_temp_free_ptr(qd);
mve_update_eci(s);
return true;
}
static bool do_vidup(DisasContext *s, arg_vidup *a, MVEGenVIDUPFn *fn)
{
TCGv_ptr qd;
TCGv_i32 rn;
/*
* Vector increment/decrement with wrap and duplicate (VIDUP, VDDUP).
* This fills the vector with elements of successively increasing
* or decreasing values, starting from Rn.
*/
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) {
return false;
}
if (a->size == MO_64) {
/* size 0b11 is another encoding */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
rn = load_reg(s, a->rn);
fn(rn, cpu_env, qd, rn, tcg_constant_i32(a->imm));
store_reg(s, a->rn, rn);
tcg_temp_free_ptr(qd);
mve_update_eci(s);
return true;
}
static bool do_viwdup(DisasContext *s, arg_viwdup *a, MVEGenVIWDUPFn *fn)
{
TCGv_ptr qd;
TCGv_i32 rn, rm;
/*
* Vector increment/decrement with wrap and duplicate (VIWDUp, VDWDUP)
* This fills the vector with elements of successively increasing
* or decreasing values, starting from Rn. Rm specifies a point where
* the count wraps back around to 0. The updated offset is written back
* to Rn.
*/
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) {
return false;
}
if (!fn || a->rm == 13 || a->rm == 15) {
/*
* size 0b11 is another encoding; Rm == 13 is UNPREDICTABLE;
* Rm == 13 is VIWDUP, VDWDUP.
*/
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
rn = load_reg(s, a->rn);
rm = load_reg(s, a->rm);
fn(rn, cpu_env, qd, rn, rm, tcg_constant_i32(a->imm));
store_reg(s, a->rn, rn);
tcg_temp_free_ptr(qd);
tcg_temp_free_i32(rm);
mve_update_eci(s);
return true;
}
static bool trans_VIDUP(DisasContext *s, arg_vidup *a)
{
static MVEGenVIDUPFn * const fns[] = {
gen_helper_mve_vidupb,
gen_helper_mve_viduph,
gen_helper_mve_vidupw,
NULL,
};
return do_vidup(s, a, fns[a->size]);
}
static bool trans_VDDUP(DisasContext *s, arg_vidup *a)
{
static MVEGenVIDUPFn * const fns[] = {
gen_helper_mve_vidupb,
gen_helper_mve_viduph,
gen_helper_mve_vidupw,
NULL,
};
/* VDDUP is just like VIDUP but with a negative immediate */
a->imm = -a->imm;
return do_vidup(s, a, fns[a->size]);
}
static bool trans_VIWDUP(DisasContext *s, arg_viwdup *a)
{
static MVEGenVIWDUPFn * const fns[] = {
gen_helper_mve_viwdupb,
gen_helper_mve_viwduph,
gen_helper_mve_viwdupw,
NULL,
};
return do_viwdup(s, a, fns[a->size]);
}
static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a)
{
static MVEGenVIWDUPFn * const fns[] = {
gen_helper_mve_vdwdupb,
gen_helper_mve_vdwduph,
gen_helper_mve_vdwdupw,
NULL,
};
return do_viwdup(s, a, fns[a->size]);
}
static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn)
{
TCGv_ptr qn, qm;
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qn = mve_qreg_ptr(a->qn);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qn, qm);
tcg_temp_free_ptr(qn);
tcg_temp_free_ptr(qm);
if (a->mask) {
/* VPT */
gen_vpst(s, a->mask);
}
mve_update_eci(s);
return true;
}
static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a,
MVEGenScalarCmpFn *fn)
{
TCGv_ptr qn;
TCGv_i32 rm;
if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qn = mve_qreg_ptr(a->qn);
if (a->rm == 15) {
/* Encoding Rm=0b1111 means "constant zero" */
rm = tcg_constant_i32(0);
} else {
rm = load_reg(s, a->rm);
}
fn(cpu_env, qn, rm);
tcg_temp_free_ptr(qn);
tcg_temp_free_i32(rm);
if (a->mask) {
/* VPT */
gen_vpst(s, a->mask);
}
mve_update_eci(s);
return true;
}
#define DO_VCMP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \
{ \
static MVEGenCmpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_vcmp(s, a, fns[a->size]); \
} \
static bool trans_##INSN##_scalar(DisasContext *s, \
arg_vcmp_scalar *a) \
{ \
static MVEGenScalarCmpFn * const fns[] = { \
gen_helper_mve_##FN##_scalarb, \
gen_helper_mve_##FN##_scalarh, \
gen_helper_mve_##FN##_scalarw, \
NULL, \
}; \
return do_vcmp_scalar(s, a, fns[a->size]); \
}
DO_VCMP(VCMPEQ, vcmpeq)
DO_VCMP(VCMPNE, vcmpne)
DO_VCMP(VCMPCS, vcmpcs)
DO_VCMP(VCMPHI, vcmphi)
DO_VCMP(VCMPGE, vcmpge)
DO_VCMP(VCMPLT, vcmplt)
DO_VCMP(VCMPGT, vcmpgt)
DO_VCMP(VCMPLE, vcmple)
static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn)
{
/*
* MIN/MAX operations across a vector: compute the min or
* max of the initial value in a general purpose register
* and all the elements in the vector, and store it back
* into the general purpose register.
*/
TCGv_ptr qm;
TCGv_i32 rda;
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) ||
!fn || a->rda == 13 || a->rda == 15) {
/* Rda cases are UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qm = mve_qreg_ptr(a->qm);
rda = load_reg(s, a->rda);
fn(rda, cpu_env, qm, rda);
store_reg(s, a->rda, rda);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_VMAXV(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \
{ \
static MVEGenVADDVFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_vmaxv(s, a, fns[a->size]); \
}
DO_VMAXV(VMAXV_S, vmaxvs)
DO_VMAXV(VMAXV_U, vmaxvu)
DO_VMAXV(VMAXAV, vmaxav)
DO_VMAXV(VMINV_S, vminvs)
DO_VMAXV(VMINV_U, vminvu)
DO_VMAXV(VMINAV, vminav)
static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn)
{
/* Absolute difference accumulated across vector */
TCGv_ptr qn, qm;
TCGv_i32 rda;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qm | a->qn) ||
!fn || a->rda == 13 || a->rda == 15) {
/* Rda cases are UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qm = mve_qreg_ptr(a->qm);
qn = mve_qreg_ptr(a->qn);
rda = load_reg(s, a->rda);
fn(rda, cpu_env, qn, qm, rda);
store_reg(s, a->rda, rda);
tcg_temp_free_ptr(qm);
tcg_temp_free_ptr(qn);
mve_update_eci(s);
return true;
}
#define DO_VABAV(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_vabav *a) \
{ \
static MVEGenVABAVFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_vabav(s, a, fns[a->size]); \
}
DO_VABAV(VABAV_S, vabavs)
DO_VABAV(VABAV_U, vabavu)
static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a)
{
/*
* VMOV two 32-bit vector lanes to two general-purpose registers.
* This insn is not predicated but it is subject to beat-wise
* execution if it is not in an IT block. For us this means
* only that if PSR.ECI says we should not be executing the beat
* corresponding to the lane of the vector register being accessed
* then we should skip perfoming the move, and that we need to do
* the usual check for bad ECI state and advance of ECI state.
* (If PSR.ECI is non-zero then we cannot be in an IT block.)
*/
TCGv_i32 tmp;
int vd;
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) ||
a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 ||
a->rt == a->rt2) {
/* Rt/Rt2 cases are UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
/* Convert Qreg index to Dreg for read_neon_element32() etc */
vd = a->qd * 2;
if (!mve_skip_vmov(s, vd, a->idx, MO_32)) {
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, vd, a->idx, MO_32);
store_reg(s, a->rt, tmp);
}
if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) {
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, vd + 1, a->idx, MO_32);
store_reg(s, a->rt2, tmp);
}
mve_update_and_store_eci(s);
return true;
}
static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a)
{
/*
* VMOV two general-purpose registers to two 32-bit vector lanes.
* This insn is not predicated but it is subject to beat-wise
* execution if it is not in an IT block. For us this means
* only that if PSR.ECI says we should not be executing the beat
* corresponding to the lane of the vector register being accessed
* then we should skip perfoming the move, and that we need to do
* the usual check for bad ECI state and advance of ECI state.
* (If PSR.ECI is non-zero then we cannot be in an IT block.)
*/
TCGv_i32 tmp;
int vd;
if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) ||
a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) {
/* Rt/Rt2 cases are UNPREDICTABLE */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
/* Convert Qreg idx to Dreg for read_neon_element32() etc */
vd = a->qd * 2;
if (!mve_skip_vmov(s, vd, a->idx, MO_32)) {
tmp = load_reg(s, a->rt);
write_neon_element32(tmp, vd, a->idx, MO_32);
tcg_temp_free_i32(tmp);
}
if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) {
tmp = load_reg(s, a->rt2);
write_neon_element32(tmp, vd + 1, a->idx, MO_32);
tcg_temp_free_i32(tmp);
}
mve_update_and_store_eci(s);
return true;
}
Reference in New Issue View Git Blame Copy Permalink