Implement the MVE long shifts by register, which perform shifts on a
pair of general-purpose registers treated as a 64-bit quantity, with
the shift count in another general-purpose register, which might be
either positive or negative.
Like the long-shifts-by-immediate, these encodings sit in the space
that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15.
Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and
also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases),
we have to move the CSEL pattern into the same decodetree group.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-17-peter.maydell@linaro.org
The MVE extension to v8.1M includes some new shift instructions which
sit entirely within the non-coprocessor part of the encoding space
and which operate only on general-purpose registers. They take up
the space which was previously UNPREDICTABLE MOVS and ORRS encodings
with Rm == 13 or 15.
Implement the long shifts by immediate, which perform shifts on a
pair of general-purpose registers treated as a 64-bit quantity, with
an immediate shift count between 1 and 32.
Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for
the Rm==13,15 case, we need to explicitly emit code to UNDEF for the
cases where v8.1M now requires that. (Trying to change MOVS and ORRS
is too difficult, because the functions that generate the code are
shared between a dozen different kinds of arithmetic or logical
instruction for all A32, T16 and T32 encodings, and for some insns
and some encodings Rm==13,15 are valid.)
We make the helper functions we need for UQSHLL and SQSHLL take
a 32-bit value which the helper casts to int8_t because we'll need
these helpers also for the shift-by-register insns, where the shift
count might be < 0 or > 32.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-16-peter.maydell@linaro.org
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
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
Use dup_const() instead of bitfield_replicate() in
disas_simd_mod_imm().
(We can't replace the other use of bitfield_replicate() in this file,
in logic_imm_decode_wmask(), because that location needs to handle 2
and 4 bit elements, which dup_const() cannot.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-6-peter.maydell@linaro.org
The A64 AdvSIMD modified-immediate grouping uses almost the same
constant encoding that A32 Neon does; reuse asimd_imm_const() (to
which we add the AArch64-specific case for cmode 15 op 1) instead of
reimplementing it all.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-5-peter.maydell@linaro.org
The function asimd_imm_const() in translate-neon.c is an
implementation of the pseudocode AdvSIMDExpandImm(), which we will
also want for MVE. Move the implementation to translate.c, with a
prototype in translate.h.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-4-peter.maydell@linaro.org
The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH
insns had some bugs:
* the 32x32 multiply of elements was being done as 32x32->32,
not 32x32->64
* we were incorrectly maintaining the accumulator in its full
72-bit form across all 4 beats of the insn; in the pseudocode
it is squashed back into the 64 bits of the RdaHi:RdaLo
registers after each beat
In particular, fixing the second of these allows us to recast
the implementation to avoid 128-bit arithmetic entirely.
Since the element size here is always 4, we can also drop the
parameterization of ESIZE to make the code a little more readable.
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-3-peter.maydell@linaro.org
In do_ldst(), the calculation of the offset needs to be based on the
size of the memory access, not the size of the elements in the
vector. This meant we were getting it wrong for the widening and
narrowing variants of the various VLDR and VSTR insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-2-peter.maydell@linaro.org
We can eliminate the requirement for a zero-extended output,
because the following store will ignore any garbage high bits.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
For the sf version, we are performing two 32-bit bswaps
in either half of the register. This is equivalent to
performing one 64-bit bswap followed by a rotate.
For the non-sf version, we can remove TCG_BSWAP_IZ
and the preceding zero-extension.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Implement the new semantics in the fallback expansion.
Change all callers to supply the flags that keep the
semantics unchanged locally.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
In a CPU with MVE, the VMOV (vector lane to general-purpose register)
and VMOV (general-purpose register to vector lane) insns are not
predicated, but they are subject to beatwise execution if they
are not in an IT block.
Since our implementation always executes all 4 beats in one tick,
this means only that we need to handle PSR.ECI:
* we must do the usual check for bad ECI state
* we must advance ECI state if the insn succeeds
* if ECI says we should not be executing the beat corresponding
to the lane of the vector register being accessed then we
should skip performing the move
Note that if PSR.ECI is non-zero then we cannot be in an IT block.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-45-peter.maydell@linaro.org
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
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
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
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
