xref: /qemu/target/arm/tcg/mve.decode (revision eab84139855dac258c8d89ad736f6649e3edc76a)

# M-profile MVE instruction descriptions
#
#  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/>.

#
# This file is processed by scripts/decodetree.py
#

%qd 22:1 13:3
%qm 5:1 1:3
%qn 7:1 17:3

# VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit
%size_28 28:1 !function=plus_1

# 1imm format immediate
%imm_28_16_0 28:1 16:3 0:4

&vldr_vstr rn qd imm p a w size l u
&1op qd qm size
&2op qd qm qn size
&2scalar qd qn rm size
&1imm qd imm cmode op

@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
# Note that both Rn and Qd are 3 bits only (no D bit)
@vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr

@1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm
@1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0
@2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn
@2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0
@2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \
     size=%size_28
@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0

# The _rev suffix indicates that Vn and Vm are reversed. This is
# the case for shifts. In the Arm ARM these insns are documented
# with the Vm and Vn fields in their usual places, but in the
# assembly the operands are listed "backwards", ie in the order
# Qd, Qm, Qn where other insns use Qd, Qn, Qm. For QEMU we choose
# to consider Vm and Vn as being in different fields in the insn.
# This gives us consistency with A64 and Neon.
@2op_rev .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qn qn=%qm

@2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
@2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn

# Vector loads and stores

# Widening loads and narrowing stores:
# for these P=0 W=0 is 'related encoding'; sz=11 is 'related encoding'
# This means we need to expand out to multiple patterns for P, W, SZ.
# For stores the U bit must be 0 but we catch that in the trans_ function.
# The naming scheme here is "VLDSTB_H == in-memory byte load/store to/from
# signed halfword element in register", etc.
VLDSTB_H         111 . 110 0 a:1 0 1   . 0 ... ... 0 111 01 ....... @vldst_wn \
                 p=0 w=1 size=1
VLDSTB_H         111 . 110 1 a:1 0 w:1 . 0 ... ... 0 111 01 ....... @vldst_wn \
                 p=1 size=1
VLDSTB_W         111 . 110 0 a:1 0 1   . 0 ... ... 0 111 10 ....... @vldst_wn \
                 p=0 w=1 size=2
VLDSTB_W         111 . 110 1 a:1 0 w:1 . 0 ... ... 0 111 10 ....... @vldst_wn \
                 p=1 size=2
VLDSTH_W         111 . 110 0 a:1 0 1   . 1 ... ... 0 111 10 ....... @vldst_wn \
                 p=0 w=1 size=2
VLDSTH_W         111 . 110 1 a:1 0 w:1 . 1 ... ... 0 111 10 ....... @vldst_wn \
                 p=1 size=2

# Non-widening loads/stores (P=0 W=0 is 'related encoding')
VLDR_VSTR        1110110 0 a:1 . 1   . .... ... 111100 .......   @vldr_vstr \
                 size=0 p=0 w=1
VLDR_VSTR        1110110 0 a:1 . 1   . .... ... 111101 .......   @vldr_vstr \
                 size=1 p=0 w=1
VLDR_VSTR        1110110 0 a:1 . 1   . .... ... 111110 .......   @vldr_vstr \
                 size=2 p=0 w=1
VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111100 .......   @vldr_vstr \
                 size=0 p=1
VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111101 .......   @vldr_vstr \
                 size=1 p=1
VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111110 .......   @vldr_vstr \
                 size=2 p=1

# Vector 2-op
VAND             1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
VBIC             1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
VORR             1110 1111 0 . 10 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
VORN             1110 1111 0 . 11 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
VEOR             1111 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz

VADD             1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
VSUB             1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op

VMULH_S          111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
VMULH_U          111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op

VRMULH_S         111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
VRMULH_U         111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op

VMAX_S           111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
VMAX_U           111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
VMIN_S           111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 1 ... 0 @2op
VMIN_U           111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 1 ... 0 @2op

VABD_S           111 0 1111 0 . .. ... 0 ... 0 0111 . 1 . 0 ... 0 @2op
VABD_U           111 1 1111 0 . .. ... 0 ... 0 0111 . 1 . 0 ... 0 @2op

VHADD_S          111 0 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op
VHADD_U          111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op
VHSUB_S          111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op
VHSUB_U          111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op

VMULL_BS         111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op
VMULL_BU         111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op
VMULL_TS         111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op
VMULL_TU         111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op

VQDMULH          1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op
VQRDMULH         1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op

VQADD_S          111 0 1111 0 . .. ... 0 ... 0 0000 . 1 . 1 ... 0 @2op
VQADD_U          111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 1 ... 0 @2op
VQSUB_S          111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 1 ... 0 @2op
VQSUB_U          111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 1 ... 0 @2op

VSHL_S           111 0 1111 0 . .. ... 0 ... 0 0100 . 1 . 0 ... 0 @2op_rev
VSHL_U           111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 0 ... 0 @2op_rev

VRSHL_S          111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 0 ... 0 @2op_rev
VRSHL_U          111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 0 ... 0 @2op_rev

VQSHL_S          111 0 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev
VQSHL_U          111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev

VQRSHL_S         111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev
VQRSHL_U         111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev

VQDMLADH         1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
VQDMLADHX        1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
VQRDMLADH        1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
VQRDMLADHX       1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op

VQDMLSDH         1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
VQDMLSDHX        1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
VQRDMLSDH        1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
VQRDMLSDHX       1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op

VQDMULLB         111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28
VQDMULLT         111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28

VRHADD_S         111 0 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op
VRHADD_U         111 1 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op

{
  VADC           1110 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 0 @2op_nosz
  VADCI          1110 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 0 @2op_nosz
  VHCADD90       1110 1110 0 . .. ... 0 ... 0 1111 . 0 . 0 ... 0 @2op
  VHCADD270      1110 1110 0 . .. ... 0 ... 1 1111 . 0 . 0 ... 0 @2op
}

{
  VSBC           1111 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 0 @2op_nosz
  VSBCI          1111 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 0 @2op_nosz
  VCADD90        1111 1110 0 . .. ... 0 ... 0 1111 . 0 . 0 ... 0 @2op
  VCADD270       1111 1110 0 . .. ... 0 ... 1 1111 . 0 . 0 ... 0 @2op
}

# Vector miscellaneous

VCLS             1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
VCLZ             1111 1111 1 . 11 .. 00 ... 0 0100 11 . 0 ... 0 @1op

VREV16           1111 1111 1 . 11 .. 00 ... 0 0001 01 . 0 ... 0 @1op
VREV32           1111 1111 1 . 11 .. 00 ... 0 0000 11 . 0 ... 0 @1op
VREV64           1111 1111 1 . 11 .. 00 ... 0 0000 01 . 0 ... 0 @1op

VMVN             1111 1111 1 . 11 00 00 ... 0 0101 11 . 0 ... 0 @1op_nosz

VABS             1111 1111 1 . 11 .. 01 ... 0 0011 01 . 0 ... 0 @1op
VABS_fp          1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 ... 0 @1op
VNEG             1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op
VNEG_fp          1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op

&vdup qd rt size
# Qd is in the fields usually named Qn
@vdup            .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup

# B and E bits encode size, which we decode here to the usual size values
VDUP             1110 1110 1 1 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=0
VDUP             1110 1110 1 0 10 ... 0 .... 1011 . 0 1 1 0000 @vdup size=1
VDUP             1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2

# multiply-add long dual accumulate
# rdahi: bits [3:1] from insn, bit 0 is 1
# rdalo: bits [3:1] from insn, bit 0 is 0
%rdahi 20:3 !function=times_2_plus_1
%rdalo 13:3 !function=times_2
# size bit is 0 for 16 bit, 1 for 32 bit
%size_16 16:1 !function=plus_1

&vmlaldav rdahi rdalo size qn qm x a

@vmlaldav        .... .... . ... ... . ... . .... .... qm:3 . \
                 qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav
@vmlaldav_nosz   .... .... . ... ... . ... . .... .... qm:3 . \
                 qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav
VMLALDAV_S       1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav
VMLALDAV_U       1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav

VMLSLDAV         1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav

VRMLALDAVH_S     1110 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz
VRMLALDAVH_U     1111 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz

VRMLSLDAVH       1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_nosz

# Scalar operations

VADD_scalar      1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar
VSUB_scalar      1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar
VMUL_scalar      1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar
VHADD_S_scalar   1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
VHADD_U_scalar   1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
VHSUB_S_scalar   1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
VHSUB_U_scalar   1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar

{
  VQADD_S_scalar  1110  1110 0 . .. ... 0 ... 0 1111 . 110 .... @2scalar
  VQADD_U_scalar  1111  1110 0 . .. ... 0 ... 0 1111 . 110 .... @2scalar
  VQDMULLB_scalar 111 . 1110 0 . 11 ... 0 ... 0 1111 . 110 .... @2scalar_nosz \
                  size=%size_28
}

{
  VQSUB_S_scalar  1110  1110 0 . .. ... 0 ... 1 1111 . 110 .... @2scalar
  VQSUB_U_scalar  1111  1110 0 . .. ... 0 ... 1 1111 . 110 .... @2scalar
  VQDMULLT_scalar 111 . 1110 0 . 11 ... 0 ... 1 1111 . 110 .... @2scalar_nosz \
                  size=%size_28
}

VBRSR            1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar

VQDMULH_scalar   1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
VQRDMULH_scalar  1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar

# Vector add across vector
VADDV            111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo

# Predicate operations
%mask_22_13      22:1 13:3
VPST             1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13

# Logical immediate operations (1 reg and modified-immediate)

# The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but
# not in a way we can conveniently represent in decodetree without
# a lot of repetition:
# VORR: op=0, (cmode & 1) && cmode < 12
# VBIC: op=1, (cmode & 1) && cmode < 12
# VMOV: everything else
# So we have a single decode line and check the cmode/op in the
# trans function.
Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm