OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity
d10b5ea157
qemu-e2k/target/arm/mve.decode

833 lines
37 KiB
Plaintext
Raw Normal View History

target/arm: Add framework for MVE decode Add the framework for decoding MVE insns, with the necessary new files and the meson.build rules, but no actual content yet. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210614151007.4545-11-peter.maydell@linaro.org
2021-06-14 17:09:20 +02:00
# 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
#
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
%qd 22:1 13:3
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
%qm 5:1 1:3
target/arm: Implement MVE VDUP Implement the MVE VDUP insn, which duplicates a value from a general-purpose register into every lane of a vector register (subject to predication). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-11-peter.maydell@linaro.org
2021-06-17 14:15:54 +02:00
%qn 7:1 17:3
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
target/arm: Implement MVE VQDMULL scalar Implement the MVE VQDMULL scalar insn. This multiplies the top or bottom half of each element by the scalar, doubles and saturates to a double-width result. Note that this encoding overlaps with VQADD and VQSUB; it uses what in VQADD and VQSUB would be the 'size=0b11' encoding. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-30-peter.maydell@linaro.org
2021-06-17 14:16:13 +02:00
# VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit
%size_28 28:1 !function=plus_1
target/arm: Implement MVE VADD (floating-point) Implement the MVE VADD (floating-point) insn. Handling of this is similar to the 2-operand integer insns, except that we must take care to only update the floating point exception status if the least significant bit of the predicate mask for each element is active. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:34 +02:00
# 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit,
# like Neon FP insns.
%2op_fp_size 20:1 !function=neon_3same_fp_size
target/arm: Implement MVE VCADD Implement the MVE VCADD insn. Note that here the size bit is the opposite sense to the other 2-operand fp insns. We don't check for the sz == 1 && Qd == Qm UNPREDICTABLE case, because that would mean we can't use the DO_2OP_FP macro in translate-mve.c. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
# VCADD is an exception, where bit 20 is 0 for 16 bit and 1 for 32 bit
%2op_fp_size_rev 20:1 !function=plus_1
target/arm: Implement MVE scalar fp insns Implement the MVE scalar floating point insns VADD, VSUB and VMUL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:36 +02:00
# FP scalars have size in bit 28, 1 for 16 bit, 0 for 32 bit
%2op_fp_scalar_size 28:1 !function=neon_3same_fp_size
target/arm: Implement MVE VADD (floating-point) Implement the MVE VADD (floating-point) insn. Handling of this is similar to the 2-operand integer insns, except that we must take care to only update the floating point exception status if the least significant bit of the predicate mask for each element is active. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:34 +02:00
target/arm: Implement MVE logical immediate insns Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
2021-06-28 15:58:23 +02:00
# 1imm format immediate
%imm_28_16_0 28:1 16:3 0:4
target/arm: Implement widening/narrowing MVE VLDR/VSTR insns Implement the variants of MVE VLDR (encodings T1, T2) which perform "widening" loads where bytes or halfwords are loaded from memory and zero or sign-extended into halfword or word length vector elements, and the narrowing MVE VSTR (encodings T1, T2) where bytes or halfwords are stored from halfword or word elements. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-3-peter.maydell@linaro.org
2021-06-17 14:15:46 +02:00
&vldr_vstr rn qd imm p a w size l u
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
&1op qd qm size
target/arm: Implement MVE VAND, VBIC, VORR, VORN, VEOR Implement the MVE vector logical operations operating on two registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-12-peter.maydell@linaro.org
2021-06-17 14:15:55 +02:00
&2op qd qm qn size
target/arm: Implement MVE VADD (scalar) Implement the scalar form of the MVE VADD insn. This takes the scalar operand from a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-23-peter.maydell@linaro.org
2021-06-17 14:16:06 +02:00
&2scalar qd qn rm size
target/arm: Implement MVE logical immediate insns Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
2021-06-28 15:58:23 +02:00
&1imm qd imm cmode op
target/arm: Implement MVE vector shift left by immediate insns Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-8-peter.maydell@linaro.org
2021-06-28 15:58:24 +02:00
&2shift qd qm shift size
target/arm: Implement MVE incrementing/decrementing dup insns Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:50 +02:00
&vidup qd rn size imm
&viwdup qd rn rm size imm
target/arm: Implement MVE integer vector comparisons Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
&vcmp qm qn size mask
target/arm: Implement MVE integer vector-vs-scalar comparisons Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
&vcmp_scalar qn rm size mask
target/arm: Implement MVE shift-by-scalar Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
&shl_scalar qda rm size
target/arm: Implement MVE integer min/max across vector Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
&vmaxv qm rda size
target/arm: Implement MVE VABAV Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
&vabav qn qm rda size
target/arm: Implement MVE scatter-gather insns Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:56 +02:00
&vldst_sg qd qm rn size msize os
target/arm: Implement MVE scatter-gather immediate forms Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:57 +02:00
&vldst_sg_imm qd qm a w imm
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>
2021-08-13 18:11:57 +02:00
&vldst_il qd rn size pat w
target/arm: Implement MVE scatter-gather insns Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:56 +02:00
# scatter-gather memory size is in bits 6:4
%sg_msize 6:1 4:1
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
target/arm: Implement widening/narrowing MVE VLDR/VSTR insns Implement the variants of MVE VLDR (encodings T1, T2) which perform "widening" loads where bytes or halfwords are loaded from memory and zero or sign-extended into halfword or word length vector elements, and the narrowing MVE VSTR (encodings T1, T2) where bytes or halfwords are stored from halfword or word elements. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-3-peter.maydell@linaro.org
2021-06-17 14:15:46 +02:00
@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
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
target/arm: Implement MVE scatter-gather insns Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:56 +02:00
@vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \
qd=%qd qm=%qm msize=%sg_msize
target/arm: Implement MVE scatter-gather immediate forms Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:57 +02:00
# Qm is in the fields usually labeled Qn
@vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \
qd=%qd qm=%qn
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>
2021-08-13 18:11:57 +02:00
# Deinterleaving load/interleaving store
@vldst_il .... .... .. w:1 . rn:4 .... ... size:2 pat:2 ..... &vldst_il \
qd=%qd
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
@1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm
target/arm: Implement MVE VMVN (register) Implement the MVE VMVN(register) operation. Note that for predication this operation is byte-by-byte. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-7-peter.maydell@linaro.org
2021-06-17 14:15:50 +02:00
@1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0
target/arm: Implement MVE VADD, VSUB, VMUL Implement the MVE VADD, VSUB and VMUL insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-13-peter.maydell@linaro.org
2021-06-17 14:15:56 +02:00
@2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn
target/arm: Implement MVE VAND, VBIC, VORR, VORN, VEOR Implement the MVE vector logical operations operating on two registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-12-peter.maydell@linaro.org
2021-06-17 14:15:55 +02:00
@2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0
target/arm: Implement MVE VQDMULL (vector) Implement the vector form of the MVE VQDMULL insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-39-peter.maydell@linaro.org
2021-06-17 14:16:22 +02:00
@2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \
size=%size_28
target/arm: Implement MVE logical immediate insns Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
2021-06-28 15:58:23 +02:00
@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
target/arm: Implement MVE VQSHL (vector) Implement the MVE VQSHL insn (encoding T4, which is the vector-shift-by-vector version). The DO_SQSHL_OP and DO_UQSHL_OP macros here are derived from the neon_helper.c code for qshl_u{8,16,32} and qshl_s{8,16,32}. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-33-peter.maydell@linaro.org
2021-06-17 14:16:16 +02:00
# 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
# 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
target/arm: Implement MVE VADD (scalar) Implement the scalar form of the MVE VADD insn. This takes the scalar operand from a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-23-peter.maydell@linaro.org
2021-06-17 14:16:06 +02:00
@2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
target/arm: Implement MVE VQDMULL scalar Implement the MVE VQDMULL scalar insn. This multiplies the top or bottom half of each element by the scalar, doubles and saturates to a double-width result. Note that this encoding overlaps with VQADD and VQSUB; it uses what in VQADD and VQSUB would be the 'size=0b11' encoding. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-30-peter.maydell@linaro.org
2021-06-17 14:16:13 +02:00
@2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
target/arm: Implement MVE VADD (scalar) Implement the scalar form of the MVE VADD insn. This takes the scalar operand from a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-23-peter.maydell@linaro.org
2021-06-17 14:16:06 +02:00
target/arm: Implement MVE vector shift left by immediate insns Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-8-peter.maydell@linaro.org
2021-06-28 15:58:24 +02:00
@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
# VSHLL encoding T2 where shift == esize
@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \
qd=%qd qm=%qm size=0 shift=8
@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \
qd=%qd qm=%qm size=1 shift=16
target/arm: Implement MVE vector shift right by immediate insns Implement the MVE vector shift right by immediate insns VSHRI and VRSHRI. As with Neon, we implement these by using helper functions which perform left shifts but allow negative shift counts to indicate right shifts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-9-peter.maydell@linaro.org
2021-06-28 15:58:25 +02:00
# Right shifts are encoded as N - shift, where N is the element size in bits.
%rshift_i5 16:5 !function=rsub_32
%rshift_i4 16:4 !function=rsub_16
%rshift_i3 16:3 !function=rsub_8
@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \
size=0 shift=%rshift_i3
@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \
size=1 shift=%rshift_i4
@2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \
size=2 shift=%rshift_i5
target/arm: Implement MVE shift-by-scalar Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
@shl_scalar .... .... .... size:2 .. .... .... .... rm:4 &shl_scalar qda=%qd
target/arm: Implement MVE integer vector comparisons Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
# Vector comparison; 4-bit Qm but 3-bit Qn
%mask_22_13 22:1 13:3
@vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13
target/arm: Implement MVE integer vector-vs-scalar comparisons Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \
mask=%mask_22_13
target/arm: Implement MVE integer vector comparisons Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
target/arm: Implement MVE fp vector comparisons Implement the MVE fp vector comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
@vcmp_fp .... .... .... qn:3 . .... .... .... .... &vcmp \
qm=%qm size=%2op_fp_scalar_size mask=%mask_22_13
target/arm: Implement MVE fp scalar comparisons Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
# Bit 28 is a 2op_fp_scalar_size bit, but we do not decode it in this
# format to avoid complicated overlapping-instruction-groups
@vcmp_fp_scalar .... .... .... qn:3 . .... .... .... rm:4 &vcmp_scalar \
mask=%mask_22_13
target/arm: Implement MVE integer min/max across vector Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm
target/arm: Implement MVE VADD (floating-point) Implement the MVE VADD (floating-point) insn. Handling of this is similar to the 2-operand integer insns, except that we must take care to only update the floating point exception status if the least significant bit of the predicate mask for each element is active. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:34 +02:00
@2op_fp .... .... .... .... .... .... .... .... &2op \
qd=%qd qn=%qn qm=%qm size=%2op_fp_size
target/arm: Implement MVE VCADD Implement the MVE VCADD insn. Note that here the size bit is the opposite sense to the other 2-operand fp insns. We don't check for the sz == 1 && Qd == Qm UNPREDICTABLE case, because that would mean we can't use the DO_2OP_FP macro in translate-mve.c. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
@2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \
qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev
target/arm: Implement MVE VMAXNMA and VMINNMA Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:36 +02:00
# 2-operand, but Qd and Qn share a field. Size is in bit 28, but we
# don't decode it in this format
@vmaxnma .... .... .... .... .... .... .... .... &2op \
qd=%qd qn=%qd qm=%qm
target/arm: Implement MVE FP max/min across vector Implement the MVE VMAXNMV, VMINNMV, VMAXNMAV, VMINNMAV insns. These calculate the maximum or minimum of floating point elements across a vector, starting with a value in a general purpose register and returning the result there. The pseudocode silences a possible SNaN in the accumulating result on every iteration (by calling FPConvertNaN), but we do it only on the input ra, because if none of the inputs to float*_maxnum or float*_minnum are SNaNs then the result can't be an SNaN. Note that we can't use the float*_maxnuma() etc functions we defined earlier for VMAXNMA and VMINNMA, because we mustn't take the absolute value of the starting general-purpose register value, which could be negative. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
# Here also we don't decode the bit 28 size in the format to avoid
# awkward nested overlap groups
@vmaxnmv .... .... .... .... rda:4 .... .... .... &vmaxv qm=%qm
target/arm: Implement MVE scalar fp insns Implement the MVE scalar floating point insns VADD, VSUB and VMUL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:36 +02:00
@2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \
qd=%qd qn=%qn size=%2op_fp_scalar_size
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
# Vector loads and stores
target/arm: Implement widening/narrowing MVE VLDR/VSTR insns Implement the variants of MVE VLDR (encodings T1, T2) which perform "widening" loads where bytes or halfwords are loaded from memory and zero or sign-extended into halfword or word length vector elements, and the narrowing MVE VSTR (encodings T1, T2) where bytes or halfwords are stored from halfword or word elements. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-3-peter.maydell@linaro.org
2021-06-17 14:15:46 +02:00
# 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
target/arm: Implement MVE VLDR/VSTR (non-widening forms) Implement the forms of the MVE VLDR and VSTR insns which perform non-widening loads of bytes, halfwords or words from memory into vector elements of the same width (encodings T5, T6, T7). (At the moment we know for MVE and M-profile in general that vfp_access_check() can never return false, but we include the conventional return-true-on-failure check for consistency with non-M-profile translation code.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
2021-06-17 14:15:45 +02:00
# 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
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
target/arm: Implement MVE scatter-gather insns Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:56 +02:00
# gather loads/scatter stores
VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg
VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg
VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg
target/arm: Implement MVE scatter-gather immediate forms Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:57 +02:00
VLDRW_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1110 .... .... @vldst_sg_imm
VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm
VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm
VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm
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>
2021-08-13 18:11:57 +02:00
# deinterleaving loads/interleaving stores
VLD2 1111 1100 1 .. 1 .... ... 1 111 .. .. 00000 @vldst_il
VLD4 1111 1100 1 .. 1 .... ... 1 111 .. .. 00001 @vldst_il
VST2 1111 1100 1 .. 0 .... ... 1 111 .. .. 00000 @vldst_il
VST4 1111 1100 1 .. 0 .... ... 1 111 .. .. 00001 @vldst_il
target/arm: Implement MVE VMOV to/from 2 general-purpose registers Implement the MVE VMOV forms that move data between 2 general-purpose registers and 2 32-bit lanes in a vector register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:55 +02:00
# Moves between 2 32-bit vector lanes and 2 general purpose registers
VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd
VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd
target/arm: Implement MVE VAND, VBIC, VORR, VORN, VEOR Implement the MVE vector logical operations operating on two registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-12-peter.maydell@linaro.org
2021-06-17 14:15:55 +02:00
# 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
target/arm: Implement MVE VADD, VSUB, VMUL Implement the MVE VADD, VSUB and VMUL insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-13-peter.maydell@linaro.org
2021-06-17 14:15:56 +02:00
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
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
# The VSHLL T2 encoding is not a @2op pattern, but is here because it
# overlaps what would be size=0b11 VMULH/VRMULH
{
target/arm: Implement MVE VCVT between single and half precision Implement the MVE VCVT instruction which converts between single and half precision floating point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:39 +02:00
VCVTB_SH 111 0 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz
target/arm: Implement MVE VMAXNMA and VMINNMA Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:36 +02:00
VMAXNMA 111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
target/arm: Implement MVE narrowing moves Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op
VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op
target/arm: Implement MVE VMAXA, VMINA Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:55 +02:00
VMAXA 111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
}
{
target/arm: Implement MVE VCVT between single and half precision Implement the MVE VCVT instruction which converts between single and half precision floating point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:39 +02:00
VCVTB_HS 111 1 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz
target/arm: Implement MVE VMAXNMA and VMINNMA Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:36 +02:00
VMAXNMA 111 1 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
target/arm: Implement MVE VMULH Implement the MVE VMULH insn, which performs a vector multiply and returns the high half of the result. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-14-peter.maydell@linaro.org
2021-06-17 14:15:57 +02:00
target/arm: Implement MVE narrowing moves Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
VMOVNB 111 1 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op
VQMOVN_BU 111 1 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
}
{
target/arm: Implement MVE VCVT between single and half precision Implement the MVE VCVT instruction which converts between single and half precision floating point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:39 +02:00
VCVTT_SH 111 0 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz
target/arm: Implement MVE VMAXNMA and VMINNMA Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:36 +02:00
VMINNMA 111 0 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
target/arm: Implement MVE narrowing moves Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op
VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op
target/arm: Implement MVE VMAXA, VMINA Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:55 +02:00
VMINA 111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
}
{
target/arm: Implement MVE VCVT between single and half precision Implement the MVE VCVT instruction which converts between single and half precision floating point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:39 +02:00
VCVTT_HS 111 1 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz
target/arm: Implement MVE VMAXNMA and VMINNMA Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:36 +02:00
VMINNMA 111 1 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
target/arm: Implement MVE narrowing moves Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
VMOVNT 111 1 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op
VQMOVN_TU 111 1 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
}
target/arm: Implement MVE VRMULH Implement the MVE VRMULH insn, which performs a rounding multiply and then returns the high half. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-15-peter.maydell@linaro.org
2021-06-17 14:15:58 +02:00
target/arm: Implement MVE VMAX, VMIN Implement the MVE VMAX and VMIN insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-16-peter.maydell@linaro.org
2021-06-17 14:15:59 +02:00
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
target/arm: Implement MVE VABD Implement the MVE VABD insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-17-peter.maydell@linaro.org
2021-06-17 14:16:00 +02:00
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
target/arm: Implement MVE VHADD, VHSUB Implement MVE VHADD and VHSUB insns, which perform an addition or subtraction and then halve the result. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-18-peter.maydell@linaro.org
2021-06-17 14:16:01 +02:00
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
target/arm: Implement MVE VMULL (polynomial) Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the inputs are in either the low or the high half of each double-width element. The assembler for this insn indicates the size with "P8" or "P16", encoded into bit 28 as size = 0 or 1. We choose to follow the same encoding as VQDMULL and decode this into a->size as MO_16 or MO_32 indicating the size of the result elements. This then carries through to the helper function names where it then matches up with the existing pmull_h() which does an 8x8->16 operation and a new pmull_w() which does the 16x16->32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:50 +02:00
{
VMULLP_B 111 . 1110 0 . 11 ... 1 ... 0 1110 . 0 . 0 ... 0 @2op_sz28
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
}
{
VMULLP_T 111 . 1110 0 . 11 ... 1 ... 1 1110 . 0 . 0 ... 0 @2op_sz28
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
}
target/arm: Implement MVE VMULL Implement the MVE VMULL insn, which multiplies two single width integer elements to produce a double width result. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-19-peter.maydell@linaro.org
2021-06-17 14:16:02 +02:00
target/arm: Implement MVE VQDMULH, VQRDMULH (vector) Implement the vector forms of the MVE VQDMULH and VQRDMULH insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-31-peter.maydell@linaro.org
2021-06-17 14:16:14 +02:00
VQDMULH 1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op
VQRDMULH 1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op
target/arm: Implement MVE VQADD, VQSUB (vector) Implement the vector forms of the MVE VQADD and VQSUB insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-32-peter.maydell@linaro.org
2021-06-17 14:16:15 +02:00
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
target/arm: Implement MVE VSHL insn Implement the MVE VSHL insn (vector form). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-35-peter.maydell@linaro.org
2021-06-17 14:16:18 +02:00
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
target/arm: Implement MVE VRSHL Implement the MVE VRSHL insn (vector form). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-36-peter.maydell@linaro.org
2021-06-17 14:16:19 +02:00
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
target/arm: Implement MVE VQSHL (vector) Implement the MVE VQSHL insn (encoding T4, which is the vector-shift-by-vector version). The DO_SQSHL_OP and DO_UQSHL_OP macros here are derived from the neon_helper.c code for qshl_u{8,16,32} and qshl_s{8,16,32}. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-33-peter.maydell@linaro.org
2021-06-17 14:16:16 +02:00
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
target/arm: Implement MVE VQRSHL Implement the MV VQRSHL (vector) insn. Again, the code to perform the actual shifts is borrowed from neon_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-34-peter.maydell@linaro.org
2021-06-17 14:16:17 +02:00
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
target/arm: Implement MVE VCMUL and VCMLA Implement the MVE VCMUL and VCMLA insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
{
VCMUL0 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 0 @2op_sz28
VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
}
target/arm: Implement MVE VQDMLADH and VQRDMLADH Implement the MVE VQDMLADH and VQRDMLADH insns. These multiply elements, and then add pairs of products, double, possibly round, saturate and return the high half of the result. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-37-peter.maydell@linaro.org
2021-06-17 14:16:20 +02:00
target/arm: Implement MVE VCMUL and VCMLA Implement the MVE VCMUL and VCMLA insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
{
VCMUL180 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 0 @2op_sz28
VQDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
VQDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
}
{
VCMUL90 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 1 @2op_sz28
VQRDMLADH 111 0 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
VQRDMLSDH 111 1 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
}
{
VCMUL270 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 1 @2op_sz28
VQRDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
VQRDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
}
target/arm: Implement MVE VQDMLSDH and VQRDMLSDH Implement the MVE VQDMLSDH and VQRDMLSDH insns, which are like VQDMLADH and VQRDMLADH except that products are subtracted rather than added. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-38-peter.maydell@linaro.org
2021-06-17 14:16:21 +02:00
target/arm: Implement MVE VQDMULL (vector) Implement the vector form of the MVE VQDMULL insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-39-peter.maydell@linaro.org
2021-06-17 14:16:22 +02:00
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
target/arm: Implement MVE VRHADD Implement the MVE VRHADD insn, which performs a rounded halving addition. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-40-peter.maydell@linaro.org
2021-06-17 14:16:23 +02:00
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
target/arm: Implement MVE VHCADD Implement the MVE VHCADD insn, which is similar to VCADD but performs a halving step. This one overlaps with VADC. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-43-peter.maydell@linaro.org
2021-06-17 14:16:26 +02:00
{
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
}
target/arm: Implement MVE VCADD Implement the MVE VCADD insn, which performs a complex add with rotate. Note that the size=0b11 encoding is VSBC. The architecture grants some leeway for the "destination and Vm source overlap" case for the size MO_32 case, but we choose not to make use of it, instead always calculating all 16 bytes worth of results before setting the destination register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-42-peter.maydell@linaro.org
2021-06-17 14:16:25 +02:00
{
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
}
target/arm: Implement MVE VADC, VSBC Implement the MVE VADC and VSBC insns. 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 1 or is from FPSCR.C; the carry out at the end is written back to FPSCR.C. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-41-peter.maydell@linaro.org
2021-06-17 14:16:24 +02:00
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
# Vector miscellaneous
target/arm: Implement MVE VCLS Implement the MVE VCLS insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-5-peter.maydell@linaro.org
2021-06-17 14:15:48 +02:00
VCLS 1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
target/arm: Implement MVE VCLZ Implement the MVE VCLZ insn (and the necessary machinery for MVE 1-input vector ops). Note that for non-load instructions predication is always performed at a byte level granularity regardless of element size (R_ZLSJ), and so the masking logic here differs from that used in the VLDR and VSTR helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
2021-06-17 14:15:47 +02:00
VCLZ 1111 1111 1 . 11 .. 00 ... 0 0100 11 . 0 ... 0 @1op
target/arm: Implement MVE VREV16, VREV32, VREV64 Implement the MVE instructions VREV16, VREV32 and VREV64. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-6-peter.maydell@linaro.org
2021-06-17 14:15:49 +02:00
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
target/arm: Implement MVE VMVN (register) Implement the MVE VMVN(register) operation. Note that for predication this operation is byte-by-byte. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-7-peter.maydell@linaro.org
2021-06-17 14:15:50 +02:00
VMVN 1111 1111 1 . 11 00 00 ... 0 0101 11 . 0 ... 0 @1op_nosz
target/arm: Implement MVE VABS Implement the MVE VABS functions (both integer and floating point). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-8-peter.maydell@linaro.org
2021-06-17 14:15:51 +02:00
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
target/arm: Implement MVE VNEG Implement the MVE VNEG insn (both integer and floating point forms). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-9-peter.maydell@linaro.org
2021-06-17 14:15:52 +02:00
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
target/arm: Implement MVE VDUP Implement the MVE VDUP insn, which duplicates a value from a general-purpose register into every lane of a vector register (subject to predication). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-11-peter.maydell@linaro.org
2021-06-17 14:15:54 +02:00
target/arm: Implement MVE VQABS, VQNEG Implement the MVE 1-operand saturating operations VQABS and VQNEG. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:55 +02:00
VQABS 1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op
VQNEG 1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op
target/arm: Implement MVE VDUP Implement the MVE VDUP insn, which duplicates a value from a general-purpose register into every lane of a vector register (subject to predication). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-11-peter.maydell@linaro.org
2021-06-17 14:15:54 +02:00
&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
target/arm: Implement MVE VMLALDAV Implement the MVE VMLALDAV insn, which multiplies pairs of integer elements, accumulating them into a 64-bit result in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-20-peter.maydell@linaro.org
2021-06-17 14:16:03 +02:00
target/arm: Implement MVE incrementing/decrementing dup insns Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:50 +02:00
# Incrementing and decrementing dup
# VIDUP, VDDUP format immediate: 1 << (immh:imml)
%imm_vidup 7:1 0:1 !function=vidup_imm
# VIDUP, VDDUP registers: Rm bits [3:1] from insn, bit 0 is 1;
# Rn bits [3:1] from insn, bit 0 is 0
%vidup_rm 1:3 !function=times_2_plus_1
%vidup_rn 17:3 !function=times_2
@vidup .... .... . . size:2 .... .... .... .... .... \
qd=%qd imm=%imm_vidup rn=%vidup_rn &vidup
@viwdup .... .... . . size:2 .... .... .... .... .... \
qd=%qd imm=%imm_vidup rm=%vidup_rm rn=%vidup_rn &viwdup
{
VIDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 111 . @vidup
VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup
}
{
target/arm: Implement MVE fp scalar comparisons Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
VCMPGT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=2
VCMPLE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=2
VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup
VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup
target/arm: Implement MVE incrementing/decrementing dup insns Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:50 +02:00
}
target/arm: Implement MVE VMLALDAV Implement the MVE VMLALDAV insn, which multiplies pairs of integer elements, accumulating them into a 64-bit result in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-20-peter.maydell@linaro.org
2021-06-17 14:16:03 +02:00
# 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
target/arm: Implement MVE VMLADAV and VMLSLDAV Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
&vmladav rda size qn qm x a
target/arm: Implement MVE VMLALDAV Implement the MVE VMLALDAV insn, which multiplies pairs of integer elements, accumulating them into a 64-bit result in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-20-peter.maydell@linaro.org
2021-06-17 14:16:03 +02:00
target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
@vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \
target/arm: Implement MVE VMLALDAV Implement the MVE VMLALDAV insn, which multiplies pairs of integer elements, accumulating them into a 64-bit result in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-20-peter.maydell@linaro.org
2021-06-17 14:16:03 +02:00
qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav
target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
@vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \
target/arm: Implement MVE VRMLALDAVH, VRMLSLDAVH Implement the MVE VRMLALDAVH and VRMLSLDAVH insns, which accumulate the results of a rounded multiply of pairs of elements into a 72-bit accumulator, returning the top 64 bits in a pair of general purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-22-peter.maydell@linaro.org
2021-06-17 14:16:05 +02:00
qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav
target/arm: Implement MVE VMLADAV and VMLSLDAV Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
@vmladav .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \
qn=%qn rda=%rdalo size=%size_16 &vmladav
@vmladav_nosz .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \
qn=%qn rda=%rdalo size=0 &vmladav
target/arm: Implement MVE VMLSLDAV Implement the MVE insn VMLSLDAV, which multiplies source elements, alternately adding and subtracting them, and accumulates into a 64-bit result in a pair of general purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-21-peter.maydell@linaro.org
2021-06-17 14:16:04 +02:00
target/arm: Implement MVE VMLADAV and VMLSLDAV Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
{
VMLADAV_S 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav
VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav
}
{
VMLADAV_U 1111 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav
VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav
}
{
VMLSDAV 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 1 @vmladav
VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav
}
{
VMLSDAV 1111 1110 1111 ... 0 ... . 1110 . 0 . 0 ... 1 @vmladav_nosz
VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz
}
VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz
VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz
target/arm: Implement MVE VRMLALDAVH, VRMLSLDAVH Implement the MVE VRMLALDAVH and VRMLSLDAVH insns, which accumulate the results of a rounded multiply of pairs of elements into a 72-bit accumulator, returning the top 64 bits in a pair of general purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-22-peter.maydell@linaro.org
2021-06-17 14:16:05 +02:00
target/arm: Implement MVE integer min/max across vector Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
{
target/arm: Implement MVE FP max/min across vector Implement the MVE VMAXNMV, VMINNMV, VMAXNMAV, VMINNMAV insns. These calculate the maximum or minimum of floating point elements across a vector, starting with a value in a general purpose register and returning the result there. The pseudocode silences a possible SNaN in the accumulating result on every iteration (by calling FPConvertNaN), but we do it only on the input ra, because if none of the inputs to float*_maxnum or float*_minnum are SNaNs then the result can't be an SNaN. Note that we can't use the float*_maxnuma() etc functions we defined earlier for VMAXNMA and VMINNMA, because we mustn't take the absolute value of the starting general-purpose register value, which could be negative. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
[
VMAXNMAV 1110 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2
VMINNMAV 1110 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2
VMAXNMV 1110 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2
VMINNMV 1110 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2
]
[
VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv
VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv
VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv
VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv
]
target/arm: Implement MVE VMLADAV and VMLSLDAV Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz
target/arm: Implement MVE integer min/max across vector Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz
}
{
target/arm: Implement MVE FP max/min across vector Implement the MVE VMAXNMV, VMINNMV, VMAXNMAV, VMINNMAV insns. These calculate the maximum or minimum of floating point elements across a vector, starting with a value in a general purpose register and returning the result there. The pseudocode silences a possible SNaN in the accumulating result on every iteration (by calling FPConvertNaN), but we do it only on the input ra, because if none of the inputs to float*_maxnum or float*_minnum are SNaNs then the result can't be an SNaN. Note that we can't use the float*_maxnuma() etc functions we defined earlier for VMAXNMA and VMINNMA, because we mustn't take the absolute value of the starting general-purpose register value, which could be negative. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
[
VMAXNMAV 1111 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1
VMINNMAV 1111 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1
VMAXNMV 1111 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1
VMINNMV 1111 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1
]
[
VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv
VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv
]
target/arm: Implement MVE VMLADAV and VMLSLDAV Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz
target/arm: Implement MVE integer min/max across vector Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz
}
target/arm: Implement MVE VRMLALDAVH, VRMLSLDAVH Implement the MVE VRMLALDAVH and VRMLSLDAVH insns, which accumulate the results of a rounded multiply of pairs of elements into a 72-bit accumulator, returning the top 64 bits in a pair of general purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-22-peter.maydell@linaro.org
2021-06-17 14:16:05 +02:00
target/arm: Implement MVE VADD (scalar) Implement the scalar form of the MVE VADD insn. This takes the scalar operand from a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-23-peter.maydell@linaro.org
2021-06-17 14:16:06 +02:00
# Scalar operations
target/arm: Implement MVE fp scalar comparisons Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
{
VCMPEQ_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=2
VCMPNE_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=2
VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar
}
{
VCMPLT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=2
VCMPGE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=2
VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar
}
target/arm: Implement MVE shift-by-scalar Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
{
VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar
VRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar
VQSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar
VQRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar
VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar
}
{
VSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar
VRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar
VQSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar
VQRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar
VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar
}
target/arm: Implement MVE scalar fp insns Implement the MVE scalar floating point insns VADD, VSUB and VMUL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:36 +02:00
{
VADD_fp_scalar 111 . 1110 0 . 11 ... 0 ... 0 1111 . 100 .... @2op_fp_scalar
VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
}
{
VSUB_fp_scalar 111 . 1110 0 . 11 ... 0 ... 1 1111 . 100 .... @2op_fp_scalar
VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
}
target/arm: Implement MVE VQADD and VQSUB Implement the MVE VQADD and VQSUB insns, which perform saturating addition of a scalar to each element. Note that individual bytes of each result element are used or discarded according to the predicate mask, but FPSCR.QC is only set if the predicate mask for the lowest byte of the element is set. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-28-peter.maydell@linaro.org
2021-06-17 14:16:11 +02:00
target/arm: Implement MVE VQDMULL scalar Implement the MVE VQDMULL scalar insn. This multiplies the top or bottom half of each element by the scalar, doubles and saturates to a double-width result. Note that this encoding overlaps with VQADD and VQSUB; it uses what in VQADD and VQSUB would be the 'size=0b11' encoding. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-30-peter.maydell@linaro.org
2021-06-17 14:16:13 +02:00
{
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
}
target/arm: Implement MVE scalar fp insns Implement the MVE scalar floating point insns VADD, VSUB and VMUL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:36 +02:00
{
VMUL_fp_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 110 .... @2op_fp_scalar
VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
}
target/arm: Implement MVE VQDMULH and VQRDMULH (scalar) Implement the MVE VQDMULH and VQRDMULH scalar insns, which multiply elements by the scalar, double, possibly round, take the high half and saturate. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-29-peter.maydell@linaro.org
2021-06-17 14:16:12 +02:00
target/arm: Implement MVE fp-with-scalar VFMA, VFMAS Implement the MVE fp-with-scalar VFMA and VFMAS insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:36 +02:00
{
VFMA_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 100 .... @2op_fp_scalar
# The U bit (28) is don't-care because it does not affect the result
VMLA 111 - 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
}
{
VFMAS_scalar 111 . 1110 0 . 11 ... 1 ... 1 1110 . 100 .... @2op_fp_scalar
# The U bit (28) is don't-care because it does not affect the result
VMLAS 111 - 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
}
target/arm: Implement MVE VMLAS Implement the MVE VMLAS insn, which multiplies a vector by a vector and adds a scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:52 +02:00
target/arm: Implement MVE saturating doubling multiply accumulates Implement the MVE saturating doubling multiply accumulate insns VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply, double, add the accumulator shifted by the element size, possibly round, saturate to twice the element size, then take the high half of the result. The *MLAH insns do vector * scalar + vector, and the *MLASH insns do vector * vector + scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:54 +02:00
VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar
VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar
VQDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 110 .... @2scalar
VQDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 110 .... @2scalar
target/arm: Implement MVE VADDV Implement the MVE VADDV insn, which performs an addition across vector lanes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-44-peter.maydell@linaro.org
2021-06-17 14:16:27 +02:00
# Vector add across vector
target/arm: Implement MVE VADDLV Implement the MVE VADDLV insn; this is similar to VADDV, except that it accumulates 32-bit elements into a 64-bit accumulator stored in a pair of general-purpose registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-15-peter.maydell@linaro.org
2021-06-28 15:58:31 +02:00
{
VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo
VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \
rdahi=%rdahi rdalo=%rdalo
}
target/arm: Implement MVE VQDMULL scalar Implement the MVE VQDMULL scalar insn. This multiplies the top or bottom half of each element by the scalar, doubles and saturates to a double-width result. Note that this encoding overlaps with VQADD and VQSUB; it uses what in VQADD and VQSUB would be the 'size=0b11' encoding. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210617121628.20116-30-peter.maydell@linaro.org
2021-06-17 14:16:13 +02:00
target/arm: Implement MVE VABAV Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:53 +02:00
@vabav .... .... .. size:2 .... rda:4 .... .... .... &vabav qn=%qn qm=%qm
VABAV_S 111 0 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav
VABAV_U 111 1 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav
target/arm: Implement MVE logical immediate insns Implement the MVE logical-immediate insns (VMOV, VMVN, VORR and VBIC). These have essentially the same encoding as their Neon equivalents, and we implement the decode in the same way. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
2021-06-28 15:58:23 +02:00
# 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
target/arm: Implement MVE vector shift left by immediate insns Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL and VQSHLU. The size-and-immediate encoding here is the same as Neon, and we handle it the same way neon-dp.decode does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-8-peter.maydell@linaro.org
2021-06-28 15:58:24 +02:00
# Shifts by immediate
VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w
target/arm: Implement MVE vector shift right by immediate insns Implement the MVE vector shift right by immediate insns VSHRI and VRSHRI. As with Neon, we implement these by using helper functions which perform left shifts but allow negative shift counts to indicate right shifts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-9-peter.maydell@linaro.org
2021-06-28 15:58:25 +02:00
VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file
target/arm: Note that we handle VMOVL as a special case of VSHLL Although the architecture doesn't define it as an alias, VMOVL (vector move long) is encoded as a VSHLL with a zero shift. Add a comment in the decode file noting that we handle VMOVL as part of VSHLL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:46 +02:00
# Note that VMOVL is encoded as "VSHLL with a zero shift count"; we
# implement it that way rather than special-casing it in the decode.
target/arm: Implement MVE VSHLL Implement the MVE VHLL (vector shift left long) insn. This has two encodings: the T1 encoding is the usual shift-by-immediate format, and the T2 encoding is a special case where the shift count is always equal to the element size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
2021-06-28 15:58:26 +02:00
VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
target/arm: Implement MVE VSRI, VSLI Implement the MVE VSRI and VSLI insns, which perform a shift-and-insert operation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-11-peter.maydell@linaro.org
2021-06-28 15:58:27 +02:00
# Shift-and-insert
VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b
VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h
VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
target/arm: Implement MVE VSHRN, VRSHRN Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN. do_urshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-12-peter.maydell@linaro.org
2021-06-28 15:58:28 +02:00
# Narrowing shifts (which only support b and h sizes)
VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
target/arm: Implement MVE saturating narrowing shifts Implement the MVE saturating shift-right-and-narrow insns VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. do_srshr() is borrowed from sve_helper.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-13-peter.maydell@linaro.org
2021-06-28 15:58:29 +02:00
VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
target/arm: Implement MVE VSHLC Implement the MVE VSHLC insn, which performs a shift left of the entire vector with carry in bits provided from a general purpose register and carry out bits written back to that register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210628135835.6690-14-peter.maydell@linaro.org
2021-06-28 15:58:30 +02:00
VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd
target/arm: Implement MVE integer vector comparisons Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
# Comparisons. We expand out the conditions which are split across
# encodings T1, T2, T3 and the fc bits. These include VPT, which is
# effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero.
target/arm: Implement MVE fp vector comparisons Implement the MVE fp vector comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
{
VCMPEQ_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp_fp
VCMPEQ 111 1 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp
}
{
VCMPNE_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp_fp
VCMPNE 111 1 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp
}
{
VCMPGE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp_fp
VCMPGE 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp
}
{
VCMPLT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp_fp
VCMPLT 111 1 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp
}
{
VCMPGT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp_fp
VCMPGT 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp
}
{
VCMPLE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp_fp
VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp
}
target/arm: Implement MVE VPSEL Implement the MVE VPSEL insn, which sets each byte of the destination vector Qd to the byte from either Qn or Qm depending on the value of the corresponding bit in VPR.P0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
{
VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz
VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp
VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp
}
target/arm: Implement MVE integer vector-vs-scalar comparisons Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
{
target/arm: Implement MVE fp scalar comparisons Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101
VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
VCMPEQ_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=1
VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0100 .... @vcmp_scalar
target/arm: Implement MVE integer vector-vs-scalar comparisons Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
}
target/arm: Implement MVE fp scalar comparisons Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:37 +02:00
{
VCMPNE_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=1
VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1100 .... @vcmp_scalar
}
{
VCMPGT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=1
VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0110 .... @vcmp_scalar
}
{
VCMPLE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=1
VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1110 .... @vcmp_scalar
}
{
VCMPGE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=1
VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0100 .... @vcmp_scalar
}
{
VCMPLT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=1
VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1100 .... @vcmp_scalar
}
target/arm: Implement MVE integer vector-vs-scalar comparisons Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-08-13 18:11:51 +02:00
VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar
VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar
target/arm: Implement MVE VADD (floating-point) Implement the MVE VADD (floating-point) insn. Handling of this is similar to the 2-operand integer insns, except that we must take care to only update the floating point exception status if the least significant bit of the predicate mask for each element is active. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:34 +02:00
# 2-operand FP
VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM Implement more simple 2-operand floating point MVE insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:34 +02:00
VSUB_fp 1110 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
VMUL_fp 1111 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 1 ... 0 @2op_fp
VABD_fp 1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
VMAXNM 1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp
VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp
target/arm: Implement MVE VCADD Implement the MVE VCADD insn. Note that here the size bit is the opposite sense to the other 2-operand fp insns. We don't check for the sz == 1 && Qd == Qm UNPREDICTABLE case, because that would mean we can't use the DO_2OP_FP macro in translate-mve.c. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
VCADD90_fp 1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
target/arm: Implement MVE VFMA and VFMS Implement the MVE VFMA and VFMS insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
VFMA 1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
VFMS 1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
target/arm: Implement MVE VCMUL and VCMLA Implement the MVE VCMUL and VCMLA insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2021-09-01 10:02:35 +02:00
VCMLA0 1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
VCMLA90 1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
VCMLA180 1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
VCMLA270 1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
target/arm: Implement MVE VCVT between floating and fixed point Implement the MVE VCVT insns which convert between floating and fixed point. As with the Neon equivalents, these use essentially the same constant encoding as right-shift-by-immediate. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:38 +02:00
# floating-point <-> fixed-point conversions. Naming convention:
# VCVT_<from><to>, S = signed int, U = unsigned int, H = halfprec, F = singleprec
@vcvt .... .... .. 1 ..... .... .. 1 . .... .... &2shift \
qd=%qd qm=%qm shift=%rshift_i5 size=2
@vcvt_f16 .... .... .. 11 .... .... .. 0 . .... .... &2shift \
qd=%qd qm=%qm shift=%rshift_i4 size=1
VCVT_SH_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16
VCVT_UH_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16
VCVT_HS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16
VCVT_HU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16
VCVT_SF_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt
VCVT_UF_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt
VCVT_FS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt
VCVT_FU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt
target/arm: Implement MVE VCVT between fp and integer Implement the MVE "VCVT (between floating-point and integer)" insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:38 +02:00
# VCVT between floating point and integer (halfprec and single);
# VCVT_<from><to>, S = signed int, U = unsigned int, F = float
VCVT_SF 1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op
VCVT_UF 1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op
VCVT_FS 1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op
VCVT_FU 1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op
target/arm: Implement MVE VCVT with specified rounding mode Implement the MVE VCVT which converts from floating-point to integer using a rounding mode specified by the instruction. We implement this similarly to the Neon equivalents, by passing the required rounding mode as an extra integer parameter to the helper functions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:38 +02:00
# VCVT from floating point to integer with specified rounding mode
VCVTAS 1111 1111 1 . 11 .. 11 ... 000 00 0 1 . 0 ... 0 @1op
VCVTAU 1111 1111 1 . 11 .. 11 ... 000 00 1 1 . 0 ... 0 @1op
VCVTNS 1111 1111 1 . 11 .. 11 ... 000 01 0 1 . 0 ... 0 @1op
VCVTNU 1111 1111 1 . 11 .. 11 ... 000 01 1 1 . 0 ... 0 @1op
VCVTPS 1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op
VCVTPU 1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op
VCVTMS 1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op
VCVTMU 1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op
target/arm: Implement MVE VRINT insns Implement the MVE VRINT insns, which round floating point inputs to integer values, leaving them in floating point format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
2021-09-01 10:02:39 +02:00
VRINTN 1111 1111 1 . 11 .. 10 ... 001 000 1 . 0 ... 0 @1op
VRINTX 1111 1111 1 . 11 .. 10 ... 001 001 1 . 0 ... 0 @1op
VRINTA 1111 1111 1 . 11 .. 10 ... 001 010 1 . 0 ... 0 @1op
VRINTZ 1111 1111 1 . 11 .. 10 ... 001 011 1 . 0 ... 0 @1op
VRINTM 1111 1111 1 . 11 .. 10 ... 001 101 1 . 0 ... 0 @1op
VRINTP 1111 1111 1 . 11 .. 10 ... 001 111 1 . 0 ... 0 @1op
Reference in New Issue Copy Permalink