yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2024-12-24 05:55:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
unicorn/qemu/target/arm/neon-dp.decode

514 lines
25 KiB
Plaintext
Raw Normal View History

target/arm: Add stubs for AArch32 Neon decodetree Add the infrastructure for building and invoking a decodetree decoder for the AArch32 Neon encodings. At the moment the new decoder covers nothing, so we always fall back to the existing hand-written decode. We follow the same pattern we did for the VFP decodetree conversion (commit 78e138bc1f672c145ef6ace74617d and following): code that deals with Neon will be moving gradually out to translate-neon.vfp.inc, which we #include into translate.c. In order to share the decode files between A32 and T32, we split Neon into 3 parts: * data-processing * load-store * 'shared' encodings The first two groups of instructions have similar but not identical A32 and T32 encodings, so we need to manually transform the T32 encoding into the A32 one before calling the decoder; the third group covers the Neon instructions which are identical in A32 and T32. Backports commit 625e3dd44a15dfbe9532daa6454df3f86cf04d3e from qemu
2020-05-07 12:59:38 +00:00
# AArch32 Neon data-processing instruction descriptions
#
# Copyright (c) 2020 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 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
#
target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree Convert the Neon 3-reg-same VADD and VSUB insns to decodetree. Note that we don't need the neon_3r_sizes[op] check here because all size values are OK for VADD and VSUB; we'll add this when we convert the first insn that has size restrictions. For this we need one of the GVecGen*Fn typedefs currently in translate-a64.h; move them all to translate.h as a block so they are visible to the 32-bit decoder. Backports commit a4e143ac5b9185f670d2f17ee9cc1a430047cb65 from qemu
2020-05-07 13:36:26 +00:00
# VFP/Neon register fields; same as vfp.decode
%vm_dp 5:1 0:4
%vn_dp 7:1 16:4
%vd_dp 22:1 12:4
target/arm: Add stubs for AArch32 Neon decodetree Add the infrastructure for building and invoking a decodetree decoder for the AArch32 Neon encodings. At the moment the new decoder covers nothing, so we always fall back to the existing hand-written decode. We follow the same pattern we did for the VFP decodetree conversion (commit 78e138bc1f672c145ef6ace74617d and following): code that deals with Neon will be moving gradually out to translate-neon.vfp.inc, which we #include into translate.c. In order to share the decode files between A32 and T32, we split Neon into 3 parts: * data-processing * load-store * 'shared' encodings The first two groups of instructions have similar but not identical A32 and T32 encodings, so we need to manually transform the T32 encoding into the A32 one before calling the decoder; the third group covers the Neon instructions which are identical in A32 and T32. Backports commit 625e3dd44a15dfbe9532daa6454df3f86cf04d3e from qemu
2020-05-07 12:59:38 +00:00
# Encodings for Neon data processing instructions where the T32 encoding
# is a simple transformation of the A32 encoding.
# More specifically, this file covers instructions where the A32 encoding is
# 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
# and the T32 encoding is
# 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
# This file works on the A32 encoding only; calling code for T32 has to
# transform the insn into the A32 version first.
target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree Convert the Neon 3-reg-same VADD and VSUB insns to decodetree. Note that we don't need the neon_3r_sizes[op] check here because all size values are OK for VADD and VSUB; we'll add this when we convert the first insn that has size restrictions. For this we need one of the GVecGen*Fn typedefs currently in translate-a64.h; move them all to translate.h as a block so they are visible to the 32-bit decoder. Backports commit a4e143ac5b9185f670d2f17ee9cc1a430047cb65 from qemu
2020-05-07 13:36:26 +00:00
######################################################################
# 3-reg-same grouping:
# 1111 001 U 0 D sz:2 Vn:4 Vd:4 opc:4 N Q M op Vm:4
######################################################################
&3same vm vn vd q size
@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
target/arm: Convert Neon VPMAX/VPMIN 3-reg-same insns to decodetree Convert the Neon integer VPMAX and VPMIN 3-reg-same insns to decodetree. These are 'pairwise' operations. Backports commit 059c2398a2b1ae86c6722c45e79fb0d0f4d95b1d from qemu
2020-05-16 02:57:54 +00:00
@3same_q0 .... ... . . . size:2 .... .... .... . 0 . . .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0
target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree. We already have gvec helpers for addition and subtraction, but must add one for fabd. Backports commit a26a352bb498662cd0c205cb433a352f86fac7d2 from qemu
2020-05-16 03:12:06 +00:00
# For FP insns the high bit of 'size' is used as part of opcode decode
@3same_fp .... ... . . . . size:1 .... .... .... . q:1 . . .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
target/arm: Convert Neon VPMIN/VPMAX/VPADD float 3-reg-same insns to decodetree Convert the Neon float VPMIN, VPMAX and VPADD 3-reg-same insns to decodetree. These are the only remaining 'pairwise' operations, so we can delete the pairwise-specific bits of the old decoder's for-each-element loop now. Backports commit ab978335a56e3618212868fdce3a54217c6e71e6 from qemu
2020-05-16 03:31:09 +00:00
@3same_fp_q0 .... ... . . . . size:1 .... .... .... . 0 . . .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0
target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree. We already have gvec helpers for addition and subtraction, but must add one for fabd. Backports commit a26a352bb498662cd0c205cb433a352f86fac7d2 from qemu
2020-05-16 03:12:06 +00:00
target/arm: Convert Neon VHADD 3-reg-same insns Convert the Neon VHADD insns in the 3-reg-same group to decodetree. Backports commit cb294bca866f1cd776e44e03e5e432942bc676e8 from qemu
2020-05-16 02:42:59 +00:00
VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same
VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same
target/arm: Convert Neon 3-reg-same VQADD/VQSUB to decodetree Convert the Neon VQADD/VQSUB insns in the 3-reg-same grouping to decodetree. Backports commit 7a9497f1cf73667a4744d09673b808c20e067915 from qemu
2020-05-07 13:47:17 +00:00
VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same
VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same
target/arm: Convert Neon VRHADD, VHSUB 3-reg-same insns to decodetree Convert the Neon VRHADD and VHSUB 3-reg-same insns to decodetree. (These are all the other insns in 3-reg-same which were using GEN_NEON_INTEGER_OP() and which are not pairwise or reversed-operands.) Backports commit 8e44d03f4b5590e19a4f7910ca1c327609933dd7 from qemu
2020-05-16 02:50:00 +00:00
VRHADD_S_3s 1111 001 0 0 . .. .... .... 0001 . . . 0 .... @3same
VRHADD_U_3s 1111 001 1 0 . .. .... .... 0001 . . . 0 .... @3same
target/arm: Convert Neon 3-reg-same logic ops to decodetree Convert the Neon logic ops in the 3-reg-same grouping to decodetree. Note that for the logic ops the 'size' field forms part of their decode and the actual operations are always bitwise. Backports commit 35a548edb6f5043386183b9f6b4139d99d1f130a from qemu
2020-05-07 13:38:30 +00:00
@3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0
VAND_3s 1111 001 0 0 . 00 .... .... 0001 ... 1 .... @3same_logic
VBIC_3s 1111 001 0 0 . 01 .... .... 0001 ... 1 .... @3same_logic
VORR_3s 1111 001 0 0 . 10 .... .... 0001 ... 1 .... @3same_logic
VORN_3s 1111 001 0 0 . 11 .... .... 0001 ... 1 .... @3same_logic
VEOR_3s 1111 001 1 0 . 00 .... .... 0001 ... 1 .... @3same_logic
VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic
VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic
VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic
target/arm: Convert Neon VRHADD, VHSUB 3-reg-same insns to decodetree Convert the Neon VRHADD and VHSUB 3-reg-same insns to decodetree. (These are all the other insns in 3-reg-same which were using GEN_NEON_INTEGER_OP() and which are not pairwise or reversed-operands.) Backports commit 8e44d03f4b5590e19a4f7910ca1c327609933dd7 from qemu
2020-05-16 02:50:00 +00:00
VHSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 0 .... @3same
VHSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 0 .... @3same
target/arm: Convert Neon 3-reg-same VQADD/VQSUB to decodetree Convert the Neon VQADD/VQSUB insns in the 3-reg-same grouping to decodetree. Backports commit 7a9497f1cf73667a4744d09673b808c20e067915 from qemu
2020-05-07 13:47:17 +00:00
VQSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 1 .... @3same
VQSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 1 .... @3same
target/arm: Convert Neon 3-reg-same comparisons to decodetree Convert the Neon comparison ops in the 3-reg-same grouping to decodetree. Backports commit 02bd0cdb64b3e79419ba3a8746cb86430883b3ae from qemu
2020-05-07 13:45:02 +00:00
VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same
VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same
VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
target/arm: Swap argument order for VSHL during decode Rather than perform the argument swap during code generation, perform it during decode. This means it doesn't have to be special cased later, and we can share code with aarch64 code generation. Hopefully the decode comment addresses any confusion that might arise in between. Backports commit e9eee5316ffec5f37643de806b2e5577c5c189cf from qemu
2020-05-16 01:07:56 +00:00
# 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
# Dd, Dm, Dn where other insns use Dd, Dn, Dm. For QEMU we choose
# to consider Vm and Vn as being in different fields in the insn,
# which allows us to avoid special-casing shifts in the trans_
# function code. We would otherwise need to manually swap the operands
# over to call Neon helper functions that are shared with AArch64,
# which does not have this odd reversed-operand situation.
@3same_rev .... ... . . . size:2 .... .... .... . q:1 . . .... \
&3same vn=%vm_dp vm=%vn_dp vd=%vd_dp
VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev
VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
target/arm: Convert Neon 3-reg-same VMUL, VMLA, VMLS, VSHL to decodetree Convert the Neon VMUL, VMLA, VMLS and VSHL insns in the 3-reg-same grouping to decodetree. Backports commit 0de34fd48ad4e44bf5caa2330657ebefa93cea7d from qemu
2020-05-07 13:49:57 +00:00
target/arm: Convert Neon 64-bit element 3-reg-same insns Convert the 64-bit element insns in the 3-reg-same group to decodetree. This covers VQSHL, VRSHL and VQRSHL where size==0b11. Backports commit 35d4352fa9e94b35bf17f58181cb16c184b98d56 from qemu
2020-05-16 02:38:53 +00:00
# Insns operating on 64-bit elements (size!=0b11 handled elsewhere)
# The _rev suffix indicates that Vn and Vm are reversed (as explained
# by the comment for the @3same_rev format).
@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \
&3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
target/arm: Convert Neon VQSHL, VRSHL, VQRSHL 3-reg-same insns to decodetree Convert the VQSHL, VRSHL and VQRSHL insns in the 3-reg-same group to decodetree. We have already implemented the size==0b11 case of these insns; this commit handles the remaining sizes Backports commit 6812dfdc6b0286730d6f903ebfbdc4f81b80c29b from qemu
2020-05-16 02:53:24 +00:00
{
VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
}
{
VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
}
{
VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
}
{
VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
}
{
VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev
}
{
VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev
}
target/arm: Convert Neon 64-bit element 3-reg-same insns Convert the 64-bit element insns in the 3-reg-same group to decodetree. This covers VQSHL, VRSHL and VQRSHL where size==0b11. Backports commit 35d4352fa9e94b35bf17f58181cb16c184b98d56 from qemu
2020-05-16 02:38:53 +00:00
target/arm: Convert Neon 3-reg-same VMAX/VMIN to decodetree Convert the Neon 3-reg-same VMAX and VMIN insns to decodetree. Backports commit 36b59310c38d45213bf860affa90618aa5eeca93 from qemu
2020-05-07 13:42:01 +00:00
VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same
target/arm: Convert Neon VABA/VABD 3-reg-same to decodetree Convert the Neon VABA and VABD insns in the 3-reg-same group to decodetree. Backports commit 7715098f93ff5205334edf161e5fe156346122b0 from qemu
2020-05-16 02:46:00 +00:00
VABD_S_3s 1111 001 0 0 . .. .... .... 0111 . . . 0 .... @3same
VABD_U_3s 1111 001 1 0 . .. .... .... 0111 . . . 0 .... @3same
VABA_S_3s 1111 001 0 0 . .. .... .... 0111 . . . 1 .... @3same
VABA_U_3s 1111 001 1 0 . .. .... .... 0111 . . . 1 .... @3same
target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree Convert the Neon 3-reg-same VADD and VSUB insns to decodetree. Note that we don't need the neon_3r_sizes[op] check here because all size values are OK for VADD and VSUB; we'll add this when we convert the first insn that has size restrictions. For this we need one of the GVecGen*Fn typedefs currently in translate-a64.h; move them all to translate.h as a block so they are visible to the 32-bit decoder. Backports commit a4e143ac5b9185f670d2f17ee9cc1a430047cb65 from qemu
2020-05-07 13:36:26 +00:00
VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same
VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
target/arm: Convert Neon 3-reg-same comparisons to decodetree Convert the Neon comparison ops in the 3-reg-same grouping to decodetree. Backports commit 02bd0cdb64b3e79419ba3a8746cb86430883b3ae from qemu
2020-05-07 13:45:02 +00:00
VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same
VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same
target/arm: Convert Neon 3-reg-same VMUL, VMLA, VMLS, VSHL to decodetree Convert the Neon VMUL, VMLA, VMLS and VSHL insns in the 3-reg-same grouping to decodetree. Backports commit 0de34fd48ad4e44bf5caa2330657ebefa93cea7d from qemu
2020-05-07 13:49:57 +00:00
VMLA_3s 1111 001 0 0 . .. .... .... 1001 . . . 0 .... @3same
VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same
VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same
VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same
target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH to decodetree Convert the Neon VQRDMLAH and VQRDMLSH insns in the 3-reg-same group to decodetree. These don't use do_3same() because they want to operate on VFP double registers, whose offsets are different from the neon_reg_offset() calculations do_3same does. Backports commit a063569508af8295cf6271e06700e5b956bb402d from qemu
2020-05-16 02:20:19 +00:00
target/arm: Convert Neon VPMAX/VPMIN 3-reg-same insns to decodetree Convert the Neon integer VPMAX and VPMIN 3-reg-same insns to decodetree. These are 'pairwise' operations. Backports commit 059c2398a2b1ae86c6722c45e79fb0d0f4d95b1d from qemu
2020-05-16 02:57:54 +00:00
VPMAX_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 0 .... @3same_q0
VPMAX_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 0 .... @3same_q0
VPMIN_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 1 .... @3same_q0
VPMIN_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 1 .... @3same_q0
target/arm: Convert Neon VQDMULH/VQRDMULH 3-reg-same to decodetree Convert the Neon VQDMULH and VQRDMULH 3-reg-same insns to decodetree. These are the last integer operations in the 3-reg-same group. Backports commit 7ecc28bc72b8033cf4e0c6332135ec20d4125dfb from qemu
2020-05-16 03:06:42 +00:00
VQDMULH_3s 1111 001 0 0 . .. .... .... 1011 . . . 0 .... @3same
VQRDMULH_3s 1111 001 1 0 . .. .... .... 1011 . . . 0 .... @3same
target/arm: Convert Neon VPADD 3-reg-same insns to decodetree Convert the Neon integer VPADD 3-reg-same insns to decodetree. These are 'pairwise' operations. (Note that VQRDMLAH, which shares the same primary opcode but has U=1, has already been converted.) Backports commit fa22827d4eb078b6c58cd3d19af0b50ed951e832 from qemu
2020-05-16 03:01:23 +00:00
VPADD_3s 1111 001 0 0 . .. .... .... 1011 . . . 1 .... @3same_q0
target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH to decodetree Convert the Neon VQRDMLAH and VQRDMLSH insns in the 3-reg-same group to decodetree. These don't use do_3same() because they want to operate on VFP double registers, whose offsets are different from the neon_reg_offset() calculations do_3same does. Backports commit a063569508af8295cf6271e06700e5b956bb402d from qemu
2020-05-16 02:20:19 +00:00
VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same
target/arm: Convert Neon 3-reg-same SHA to decodetree Convert the Neon SHA instructions in the 3-reg-same group to decodetree Backports commit 21290edfc29d8929741c0ed043733c23c69bc3b9 from qemu
2020-05-16 02:34:12 +00:00
target/arm: Convert sha1 and sha256 to gvec helpers Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Backports commit effa992f153f5e7ab97ab843b565690748c5b402 from qemu
2020-06-15 03:11:25 +00:00
@3same_crypto .... .... .... .... .... .... .... .... \
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 q=1
target/arm: Split helper_crypto_sha1_3reg Rather than passing an opcode to a helper, fully decode the operation at translate time. Use clear_tail_16 to zap the balance of the SVE register with the AdvSIMD write. Backports commit afc8b7d32668547308bdd654a63cf5228936e0ba from qemu
2020-06-15 03:18:43 +00:00
SHA1C_3s 1111 001 0 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto
SHA1P_3s 1111 001 0 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto
SHA1M_3s 1111 001 0 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto
SHA1SU0_3s 1111 001 0 0 . 11 .... .... 1100 . 1 . 0 .... @3same_crypto
target/arm: Convert sha1 and sha256 to gvec helpers Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Backports commit effa992f153f5e7ab97ab843b565690748c5b402 from qemu
2020-06-15 03:11:25 +00:00
SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto
SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto
SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto
target/arm: Convert Neon 3-reg-same SHA to decodetree Convert the Neon SHA instructions in the 3-reg-same group to decodetree Backports commit 21290edfc29d8929741c0ed043733c23c69bc3b9 from qemu
2020-05-16 02:34:12 +00:00
target/arm: Convert NEON VFMA, VFMS 3-reg-same insns to decodetree Convert the Neon floating point VFMA and VFMS insn to decodetree. These are the last insns in the 3-reg-same group so we can remove all the support/loop code from the old decoder. Backports commit e95485f85657be21135c17a9226e297c21e73360 from qemu
2020-05-16 03:49:18 +00:00
VFMA_fp_3s 1111 001 0 0 . 0 . .... .... 1100 ... 1 .... @3same_fp
VFMS_fp_3s 1111 001 0 0 . 1 . .... .... 1100 ... 1 .... @3same_fp
target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH to decodetree Convert the Neon VQRDMLAH and VQRDMLSH insns in the 3-reg-same group to decodetree. These don't use do_3same() because they want to operate on VFP double registers, whose offsets are different from the neon_reg_offset() calculations do_3same does. Backports commit a063569508af8295cf6271e06700e5b956bb402d from qemu
2020-05-16 02:20:19 +00:00
VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same
target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree. We already have gvec helpers for addition and subtraction, but must add one for fabd. Backports commit a26a352bb498662cd0c205cb433a352f86fac7d2 from qemu
2020-05-16 03:12:06 +00:00
VADD_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp
VSUB_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 0 .... @3same_fp
target/arm: Convert Neon VPMIN/VPMAX/VPADD float 3-reg-same insns to decodetree Convert the Neon float VPMIN, VPMAX and VPADD 3-reg-same insns to decodetree. These are the only remaining 'pairwise' operations, so we can delete the pairwise-specific bits of the old decoder's for-each-element loop now. Backports commit ab978335a56e3618212868fdce3a54217c6e71e6 from qemu
2020-05-16 03:31:09 +00:00
VPADD_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 0 .... @3same_fp_q0
target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree. We already have gvec helpers for addition and subtraction, but must add one for fabd. Backports commit a26a352bb498662cd0c205cb433a352f86fac7d2 from qemu
2020-05-16 03:12:06 +00:00
VABD_fp_3s 1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp
target/arm: Convert Neon fp VMUL, VMLA, VMLS 3-reg-same insns to decodetree Convert the Neon integer VMUL, VMLA, and VMLS 3-reg-same inssn to decodetree. We don't have a gvec helper for multiply-accumulate, so VMLA and VMLS need a loop function do_3same_fp(). This takes a reads_vd parameter to do_3same_fp() which tells it to load the old value into vd before calling the callback function, in the same way that the do_vfp_3op_sp() and do_vfp_3op_dp() functions in translate-vfp.inc.c work. (The only uses in this patch pass reads_vd == true, but later commits will use reads_vd == false.) This conversion fixes in passing an underdecoding for VMUL Backports commit 8aa71ead912ca0a9c0d29b74e0976f91952f950a from qemu
2020-05-16 03:35:19 +00:00
VMLA_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 1 .... @3same_fp
VMLS_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 1 .... @3same_fp
VMUL_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 1 .... @3same_fp
target/arm: Convert Neon 3-reg-same compare insns to decodetree Convert the Neon integer 3-reg-same compare insns VCGE, VCGT, VCEQ, VACGE and VACGT to decodetree. Backports commit 727ff1d63213e6666e511956903b9e97a339ec7e from qemu
2020-05-16 03:37:51 +00:00
VCEQ_fp_3s 1111 001 0 0 . 0 . .... .... 1110 ... 0 .... @3same_fp
VCGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 0 .... @3same_fp
VACGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 1 .... @3same_fp
VCGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 0 .... @3same_fp
VACGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 1 .... @3same_fp
target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree Convert the Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS 3-reg-same insns to decodetree. (These are all the remaining non-accumulation instructions in this group.) Backports commit d5fdf9e9e1c6f2bbb0a4bcaafd85d344cce9c298 from qemu
2020-05-16 03:44:50 +00:00
VMAX_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 0 .... @3same_fp
VMIN_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 0 .... @3same_fp
target/arm: Convert Neon VPMIN/VPMAX/VPADD float 3-reg-same insns to decodetree Convert the Neon float VPMIN, VPMAX and VPADD 3-reg-same insns to decodetree. These are the only remaining 'pairwise' operations, so we can delete the pairwise-specific bits of the old decoder's for-each-element loop now. Backports commit ab978335a56e3618212868fdce3a54217c6e71e6 from qemu
2020-05-16 03:31:09 +00:00
VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0
VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0
target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree Convert the Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS 3-reg-same insns to decodetree. (These are all the remaining non-accumulation instructions in this group.) Backports commit d5fdf9e9e1c6f2bbb0a4bcaafd85d344cce9c298 from qemu
2020-05-16 03:44:50 +00:00
VRECPS_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
VRSQRTS_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
VMAXNM_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp
VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift group to decodetree. Backports commit d3c8c736f8b4bdd02831076286b1788232f46ced from qemu
2020-06-15 16:05:19 +00:00
######################################################################
# 2-reg-and-shift grouping:
# 1111 001 U 1 D immH:3 immL:3 Vd:4 opc:4 L Q M 1 Vm:4
######################################################################
&2reg_shift vm vd q shift size
target/arm: Convert Neon VSHR 2-reg-shift insns to decodetree Convert the VSHR 2-reg-shift insns to decodetree. Note that unlike the legacy decoder, we present the right shift amount to the trans_ function as a positive integer. Backports commit 66432d6b8294e3508218b360acfdf7c244eea993 from qemu
2020-06-15 16:10:45 +00:00
# Right shifts are encoded as N - shift, where N is the element size in bits.
%neon_rshift_i6 16:6 !function=rsub_64
%neon_rshift_i5 16:5 !function=rsub_32
%neon_rshift_i4 16:4 !function=rsub_16
%neon_rshift_i3 16:3 !function=rsub_8
@2reg_shr_d .... ... . . . ...... .... .... 1 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=3 shift=%neon_rshift_i6
@2reg_shr_s .... ... . . . 1 ..... .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=2 shift=%neon_rshift_i5
@2reg_shr_h .... ... . . . 01 .... .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4
@2reg_shr_b .... ... . . . 001 ... .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i3
target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift group to decodetree. Backports commit d3c8c736f8b4bdd02831076286b1788232f46ced from qemu
2020-06-15 16:05:19 +00:00
@2reg_shl_d .... ... . . . shift:6 .... .... 1 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=3
@2reg_shl_s .... ... . . . 1 shift:5 .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=2
@2reg_shl_h .... ... . . . 01 shift:4 .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=1
@2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0
target/arm: Convert Neon narrowing shifts with op==8 to decodetree Convert the Neon narrowing shifts where op==8 to decodetree: * VSHRN * VRSHRN * VQSHRUN * VQRSHRUN backports commit 712182d340e33c2ce86143f25fb2f04ae23d90de from qemu
2020-06-15 16:28:29 +00:00
# Narrowing right shifts: here the Q bit is part of the opcode decode
@2reg_shrn_d .... ... . . . 1 ..... .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=3 q=0 \
shift=%neon_rshift_i5
@2reg_shrn_s .... ... . . . 01 .... .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0 \
shift=%neon_rshift_i4
@2reg_shrn_h .... ... . . . 001 ... .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 \
shift=%neon_rshift_i3
target/arm: Convert Neon VSHLL, VMOVL to decodetree Convert the VSHLL and VMOVL insns from the 2-reg-shift group to decodetree. Since the loop always has two passes, we unroll it to avoid the awkward reassignment of one TCGv to another. Backports commit 968bf842742a5ffbb0041cb31089e61a9f7a833d from qemu
2020-06-15 16:35:30 +00:00
# Long left shifts: again Q is part of opcode decode
@2reg_shll_s .... ... . . . 1 shift:5 .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0
@2reg_shll_h .... ... . . . 01 shift:4 .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0
@2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0
target/arm: Convert VCVT fixed-point ops to decodetree Convert the VCVT fixed-point conversion operations in the Neon 2-regs-and-shift group to decodetree. Backports commit 3da26f11711caeaa18318b6afa14dfb81d7650ab from qemu
2020-06-15 16:40:58 +00:00
# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings.
@2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \
&2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5
target/arm: Convert Neon VSHR 2-reg-shift insns to decodetree Convert the VSHR 2-reg-shift insns to decodetree. Note that unlike the legacy decoder, we present the right shift amount to the trans_ function as a positive integer. Backports commit 66432d6b8294e3508218b360acfdf7c244eea993 from qemu
2020-06-15 16:10:45 +00:00
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h
VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b
VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d
VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s
VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h
VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b
VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d
VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s
VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h
VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b
VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d
VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s
VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h
VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b
VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d
VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s
VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h
VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b
VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d
VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s
VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h
VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b
VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d
VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s
VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h
VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b
VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d
VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s
VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h
VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b
VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_d
VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_s
VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_h
VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_b
target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift group to decodetree. Backports commit d3c8c736f8b4bdd02831076286b1788232f46ced from qemu
2020-06-15 16:05:19 +00:00
VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d
VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s
VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h
VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b
VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d
VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s
VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h
VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b
target/arm: Convert VQSHLU, VQSHL 2-reg-shift insns to decodetree Convert the VQSHLU and QVSHL 2-reg-shift insns to decodetree. These are the last of the simple shift-by-immediate insns. Backports commit 37bfce81b10450071193c8495a07f182ec652e2a from qemu
2020-06-15 16:18:54 +00:00
VQSHLU_64_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d
VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_s
VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_h
VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_b
VQSHL_S_64_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
VQSHL_U_64_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
target/arm: Convert Neon narrowing shifts with op==8 to decodetree Convert the Neon narrowing shifts where op==8 to decodetree: * VSHRN * VRSHRN * VQSHRUN * VQRSHRUN backports commit 712182d340e33c2ce86143f25fb2f04ae23d90de from qemu
2020-06-15 16:28:29 +00:00
VSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d
VSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s
VSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h
VRSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d
VRSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s
VRSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h
VQSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d
VQSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s
VQSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h
VQRSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d
VQRSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s
VQRSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h
target/arm: Convert Neon narrowing shifts with op==9 to decodetree Convert the remaining Neon narrowing shifts to decodetree: * VQSHRN * VQRSHRN Backports commit b4a3a77bb7a0dff1cc5673fe3be467d9e3635d44 from qemu
2020-06-15 16:31:32 +00:00
# VQSHRN with signed input
VQSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d
VQSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s
VQSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h
# VQRSHRN with signed input
VQRSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d
VQRSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s
VQRSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h
# VQSHRN with unsigned input
VQSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d
VQSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s
VQSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h
# VQRSHRN with unsigned input
VQRSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d
VQRSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s
VQRSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h
target/arm: Convert Neon VSHLL, VMOVL to decodetree Convert the VSHLL and VMOVL insns from the 2-reg-shift group to decodetree. Since the loop always has two passes, we unroll it to avoid the awkward reassignment of one TCGv to another. Backports commit 968bf842742a5ffbb0041cb31089e61a9f7a833d from qemu
2020-06-15 16:35:30 +00:00
VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s
VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h
VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s
VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h
VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
target/arm: Convert VCVT fixed-point ops to decodetree Convert the VCVT fixed-point conversion operations in the Neon 2-regs-and-shift group to decodetree. Backports commit 3da26f11711caeaa18318b6afa14dfb81d7650ab from qemu
2020-06-15 16:40:58 +00:00
# VCVT fixed<->float conversions
# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101
VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt
VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt
target/arm: Convert Neon one-register-and-immediate insns to decodetree Convert the insns in the one-register-and-immediate group to decodetree. In the new decode, our asimd_imm_const() function returns a 64-bit value rather than a 32-bit one, which means we don't need to treat cmode=14 op=1 as a special case in the decoder (it is the only encoding where the two halves of the 64-bit value are different). Backports commit 2c35a39eda0b16c2ed85c94cec204bf5efb97812 from qemu
2020-06-15 16:44:52 +00:00
######################################################################
# 1-reg-and-modified-immediate grouping:
# 1111 001 i 1 D 000 imm:3 Vd:4 cmode:4 0 Q op 1 Vm:4
######################################################################
&1reg_imm vd q imm cmode op
%asimd_imm_value 24:1 16:3 0:4
@1reg_imm .... ... . . . ... ... .... .... . q:1 . . .... \
&1reg_imm imm=%asimd_imm_value vd=%vd_dp
# The cmode/op bits here decode VORR/VBIC/VMOV/VMNV, 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 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
target/arm: Convert Neon 3-reg-diff prewidening ops to decodetree Convert the "pre-widening" insns VADDL, VSUBL, VADDW and VSUBW in the Neon 3-registers-different-lengths group to decodetree. These insns work by widening one or both inputs to double their size, performing an add or subtract at the doubled size and then storing the double-size result. As usual, rather than copying the loop of the original decoder (which needs awkward code to avoid problems when source and destination registers overlap) we just unroll the two passes. Backports commit b28be09570d0827969b62b8f82b0f720a9915427 from qemu
2020-06-17 03:29:51 +00:00
######################################################################
# Within the "two registers, or three registers of different lengths"
# grouping ([23,4]=0b10), bits [21:20] are either part of the opcode
# decode: 0b11 for VEXT, two-reg-misc, VTBL, and duplicate-scalar;
# or they are a size field for the three-reg-different-lengths and
# two-reg-and-scalar insn groups (where size cannot be 0b11). This
# is slightly awkward for decodetree: we handle it with this
# non-exclusive group which contains within it two exclusive groups:
# one for the size=0b11 patterns, and one for the size-not-0b11
# patterns. This allows us to check that none of the insns within
# each subgroup accidentally overlap each other. Note that all the
# trans functions for the size-not-0b11 patterns must check and
# return false for size==3.
######################################################################
{
# 0b11 subgroup will go here
# Subgroup for size != 0b11
[
##################################################################
# 3-reg-different-length grouping:
# 1111 001 U 1 D sz!=11 Vn:4 Vd:4 opc:4 N 0 M 0 Vm:4
##################################################################
&3diff vm vn vd size
@3diff .... ... . . . size:2 .... .... .... . . . . .... \
&3diff vm=%vm_dp vn=%vn_dp vd=%vd_dp
VADDL_S_3d 1111 001 0 1 . .. .... .... 0000 . 0 . 0 .... @3diff
VADDL_U_3d 1111 001 1 1 . .. .... .... 0000 . 0 . 0 .... @3diff
VADDW_S_3d 1111 001 0 1 . .. .... .... 0001 . 0 . 0 .... @3diff
VADDW_U_3d 1111 001 1 1 . .. .... .... 0001 . 0 . 0 .... @3diff
VSUBL_S_3d 1111 001 0 1 . .. .... .... 0010 . 0 . 0 .... @3diff
VSUBL_U_3d 1111 001 1 1 . .. .... .... 0010 . 0 . 0 .... @3diff
VSUBW_S_3d 1111 001 0 1 . .. .... .... 0011 . 0 . 0 .... @3diff
VSUBW_U_3d 1111 001 1 1 . .. .... .... 0011 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff narrowing ops to decodetree Convert the narrow-to-high-half insns VADDHN, VSUBHN, VRADDHN, VRSUBHN in the Neon 3-registers-different-lengths group to decodetree. Backports commit 0fa1ab0302badabc3581aefcbb2f189ef52c4985 from qemu
2020-06-17 03:36:15 +00:00
VADDHN_3d 1111 001 0 1 . .. .... .... 0100 . 0 . 0 .... @3diff
VRADDHN_3d 1111 001 1 1 . .. .... .... 0100 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff VABAL, VABDL to decodetree Convert the Neon 3-reg-diff insns VABAL and VABDL to decodetree. Like almost all the remaining insns in this group, these are a combination of a two-input operation which returns a double width result and then a possible accumulation of that double width result into the destination. Backports commit f5b28401200ec95ba89552df3ecdcdc342f6b90b from qemu
2020-06-17 03:41:18 +00:00
VABAL_S_3d 1111 001 0 1 . .. .... .... 0101 . 0 . 0 .... @3diff
VABAL_U_3d 1111 001 1 1 . .. .... .... 0101 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff narrowing ops to decodetree Convert the narrow-to-high-half insns VADDHN, VSUBHN, VRADDHN, VRSUBHN in the Neon 3-registers-different-lengths group to decodetree. Backports commit 0fa1ab0302badabc3581aefcbb2f189ef52c4985 from qemu
2020-06-17 03:36:15 +00:00
VSUBHN_3d 1111 001 0 1 . .. .... .... 0110 . 0 . 0 .... @3diff
VRSUBHN_3d 1111 001 1 1 . .. .... .... 0110 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff VABAL, VABDL to decodetree Convert the Neon 3-reg-diff insns VABAL and VABDL to decodetree. Like almost all the remaining insns in this group, these are a combination of a two-input operation which returns a double width result and then a possible accumulation of that double width result into the destination. Backports commit f5b28401200ec95ba89552df3ecdcdc342f6b90b from qemu
2020-06-17 03:41:18 +00:00
VABDL_S_3d 1111 001 0 1 . .. .... .... 0111 . 0 . 0 .... @3diff
VABDL_U_3d 1111 001 1 1 . .. .... .... 0111 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff long multiplies Convert the Neon 3-reg-diff insns VMULL, VMLAL and VMLSL; these perform a 32x32->64 multiply with possible accumulate. Note that for VMLSL we do the accumulate directly with a subtraction rather than doing a negate-then-add as the old code did. Backports commit 3a1d9eb07b767a7592abca642af80906f9eab0ed from qemu
2020-06-17 03:47:26 +00:00
VMLAL_S_3d 1111 001 0 1 . .. .... .... 1000 . 0 . 0 .... @3diff
VMLAL_U_3d 1111 001 1 1 . .. .... .... 1000 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff saturating doubling multiplies Convert the Neon 3-reg-diff insns VQDMULL, VQDMLAL and VQDMLSL: these are all saturating doubling long multiplies with a possible accumulate step. These are the last insns in the group which use the pass-over-each elements loop, so we can delete that code. Backports commit 9546ca5998d3cbd98a81b2d46a2e92a11b0f78a4 from qemu
2020-06-17 03:51:54 +00:00
VQDMLAL_3d 1111 001 0 1 . .. .... .... 1001 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff long multiplies Convert the Neon 3-reg-diff insns VMULL, VMLAL and VMLSL; these perform a 32x32->64 multiply with possible accumulate. Note that for VMLSL we do the accumulate directly with a subtraction rather than doing a negate-then-add as the old code did. Backports commit 3a1d9eb07b767a7592abca642af80906f9eab0ed from qemu
2020-06-17 03:47:26 +00:00
VMLSL_S_3d 1111 001 0 1 . .. .... .... 1010 . 0 . 0 .... @3diff
VMLSL_U_3d 1111 001 1 1 . .. .... .... 1010 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff saturating doubling multiplies Convert the Neon 3-reg-diff insns VQDMULL, VQDMLAL and VQDMLSL: these are all saturating doubling long multiplies with a possible accumulate step. These are the last insns in the group which use the pass-over-each elements loop, so we can delete that code. Backports commit 9546ca5998d3cbd98a81b2d46a2e92a11b0f78a4 from qemu
2020-06-17 03:51:54 +00:00
VQDMLSL_3d 1111 001 0 1 . .. .... .... 1011 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff long multiplies Convert the Neon 3-reg-diff insns VMULL, VMLAL and VMLSL; these perform a 32x32->64 multiply with possible accumulate. Note that for VMLSL we do the accumulate directly with a subtraction rather than doing a negate-then-add as the old code did. Backports commit 3a1d9eb07b767a7592abca642af80906f9eab0ed from qemu
2020-06-17 03:47:26 +00:00
VMULL_S_3d 1111 001 0 1 . .. .... .... 1100 . 0 . 0 .... @3diff
VMULL_U_3d 1111 001 1 1 . .. .... .... 1100 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff saturating doubling multiplies Convert the Neon 3-reg-diff insns VQDMULL, VQDMLAL and VQDMLSL: these are all saturating doubling long multiplies with a possible accumulate step. These are the last insns in the group which use the pass-over-each elements loop, so we can delete that code. Backports commit 9546ca5998d3cbd98a81b2d46a2e92a11b0f78a4 from qemu
2020-06-17 03:51:54 +00:00
VQDMULL_3d 1111 001 0 1 . .. .... .... 1101 . 0 . 0 .... @3diff
target/arm: Convert Neon 3-reg-diff polynomial VMULL Convert the Neon 3-reg-diff insn polynomial VMULL. This is the last insn in this group to be converted. Backports commit 18fb58d588898550919392277787979ee7d0d84e from qemu
2020-06-17 03:54:49 +00:00
VMULL_P_3d 1111 001 0 1 . .. .... .... 1110 . 0 . 0 .... @3diff
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
##################################################################
# 2-regs-plus-scalar grouping:
# 1111 001 Q 1 D sz!=11 Vn:4 Vd:4 opc:4 N 1 M 0 Vm:4
##################################################################
&2scalar vm vn vd size q
@2scalar .... ... q:1 . . size:2 .... .... .... . . . . .... \
&2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp
target/arm: Convert Neon 2-reg-scalar long multiplies to decodetree Convert the Neon 2-reg-scalar long multiplies to decodetree. These are the last instructions in the group. Backports commit 77e576a9281825fc170f3b3af83f47e110549b5c from qemu
2020-06-17 04:22:22 +00:00
# For the 'long' ops the Q bit is part of insn decode
@2scalar_q0 .... ... . . . size:2 .... .... .... . . . . .... \
&2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
VMLA_2sc 1111 001 . 1 . .. .... .... 0000 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar float multiplies to decodetree Convert the float versions of VMLA, VMLS and VMUL in the Neon 2-reg-scalar group to decodetree. Backports commit 85ac9aef9a5418de3168df569e21258e853840a2 from qemu
2020-06-17 04:09:29 +00:00
VMLA_F_2sc 1111 001 . 1 . .. .... .... 0001 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
target/arm: Convert Neon 2-reg-scalar long multiplies to decodetree Convert the Neon 2-reg-scalar long multiplies to decodetree. These are the last instructions in the group. Backports commit 77e576a9281825fc170f3b3af83f47e110549b5c from qemu
2020-06-17 04:22:22 +00:00
VMLAL_S_2sc 1111 001 0 1 . .. .... .... 0010 . 1 . 0 .... @2scalar_q0
VMLAL_U_2sc 1111 001 1 1 . .. .... .... 0010 . 1 . 0 .... @2scalar_q0
VQDMLAL_2sc 1111 001 0 1 . .. .... .... 0011 . 1 . 0 .... @2scalar_q0
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
VMLS_2sc 1111 001 . 1 . .. .... .... 0100 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar float multiplies to decodetree Convert the float versions of VMLA, VMLS and VMUL in the Neon 2-reg-scalar group to decodetree. Backports commit 85ac9aef9a5418de3168df569e21258e853840a2 from qemu
2020-06-17 04:09:29 +00:00
VMLS_F_2sc 1111 001 . 1 . .. .... .... 0101 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
target/arm: Convert Neon 2-reg-scalar long multiplies to decodetree Convert the Neon 2-reg-scalar long multiplies to decodetree. These are the last instructions in the group. Backports commit 77e576a9281825fc170f3b3af83f47e110549b5c from qemu
2020-06-17 04:22:22 +00:00
VMLSL_S_2sc 1111 001 0 1 . .. .... .... 0110 . 1 . 0 .... @2scalar_q0
VMLSL_U_2sc 1111 001 1 1 . .. .... .... 0110 . 1 . 0 .... @2scalar_q0
VQDMLSL_2sc 1111 001 0 1 . .. .... .... 0111 . 1 . 0 .... @2scalar_q0
target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Backports commit 96fc80f5f186decd1a649f6c04252faceb057ad2 from qemu
2020-06-17 04:02:01 +00:00
VMUL_2sc 1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar float multiplies to decodetree Convert the float versions of VMLA, VMLS and VMUL in the Neon 2-reg-scalar group to decodetree. Backports commit 85ac9aef9a5418de3168df569e21258e853840a2 from qemu
2020-06-17 04:09:29 +00:00
VMUL_F_2sc 1111 001 . 1 . .. .... .... 1001 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar VQDMULH, VQRDMULH to decodetree Convert the VQDMULH and VQRDMULH insns in the 2-reg-scalar group to decodetree. Backports commit b2fc7be972b94872f6a6dd32d9bda1b88ddbcaad from qemu
2020-06-17 04:11:54 +00:00
target/arm: Convert Neon 2-reg-scalar long multiplies to decodetree Convert the Neon 2-reg-scalar long multiplies to decodetree. These are the last instructions in the group. Backports commit 77e576a9281825fc170f3b3af83f47e110549b5c from qemu
2020-06-17 04:22:22 +00:00
VMULL_S_2sc 1111 001 0 1 . .. .... .... 1010 . 1 . 0 .... @2scalar_q0
VMULL_U_2sc 1111 001 1 1 . .. .... .... 1010 . 1 . 0 .... @2scalar_q0
VQDMULL_2sc 1111 001 0 1 . .. .... .... 1011 . 1 . 0 .... @2scalar_q0
target/arm: Convert Neon 2-reg-scalar VQDMULH, VQRDMULH to decodetree Convert the VQDMULH and VQRDMULH insns in the 2-reg-scalar group to decodetree. Backports commit b2fc7be972b94872f6a6dd32d9bda1b88ddbcaad from qemu
2020-06-17 04:11:54 +00:00
VQDMULH_2sc 1111 001 . 1 . .. .... .... 1100 . 1 . 0 .... @2scalar
VQRDMULH_2sc 1111 001 . 1 . .. .... .... 1101 . 1 . 0 .... @2scalar
target/arm: Convert Neon 2-reg-scalar VQRDMLAH, VQRDMLSH to decodetree Convert the VQRDMLAH and VQRDMLSH insns in the 2-reg-scalar group to decodetree. Backports commit aa318f5b9b4ab3b6744b5305dd8ae9b96676f20e from qemu
2020-06-17 04:15:16 +00:00
VQRDMLAH_2sc 1111 001 . 1 . .. .... .... 1110 . 1 . 0 .... @2scalar
VQRDMLSH_2sc 1111 001 . 1 . .. .... .... 1111 . 1 . 0 .... @2scalar
target/arm: Convert Neon 3-reg-diff prewidening ops to decodetree Convert the "pre-widening" insns VADDL, VSUBL, VADDW and VSUBW in the Neon 3-registers-different-lengths group to decodetree. These insns work by widening one or both inputs to double their size, performing an add or subtract at the doubled size and then storing the double-size result. As usual, rather than copying the loop of the original decoder (which needs awkward code to avoid problems when source and destination registers overlap) we just unroll the two passes. Backports commit b28be09570d0827969b62b8f82b0f720a9915427 from qemu
2020-06-17 03:29:51 +00:00
]
}
Reference in a new issue Copy permalink