The new helper always validates the contents of FRM, even
if the new rounding mode is not DYN. This is required by
the vector unit.
Track whether we've validated FRM separately from whether
we've updated fp_status with a given rounding mode, so that
we can elide calls correctly.
This partially reverts d6c4d3f2a6 which attempted the to do
the same thing, but with two calls to gen_set_rm(), which is
both inefficient and tickles an assertion in decode_save_opc.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1441
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20230115160657.3169274-2-richard.henderson@linaro.org>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
When icount is not enabled, there is no API in QEMU that can get the
guest instruction number.
Translate the guest code in a way that each TB only has one instruction.
After executing the instruction, decrease the count by 1 until it reaches 0
where the itrigger fires.
Note that only when priviledge matches the itrigger configuration,
the count will decrease.
Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20221013062946.7530-2-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Starting with RVV1.0, the original vf[w]redsum_vs instruction was renamed
to vf[w]redusum_vs. The distinction between ordered and unordered is also
more consistent with other instructions, although there is no difference
in implementation between the two for QEMU.
Signed-off-by: Yang Liu <liuyang22@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Message-Id: <20220817074802.20765-2-liuyang22@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
According to v-spec, mask agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of mask policies, QEMU should be able to simulate the mask
agnostic behavior as "set mask elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between mask policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This is the first commit regarding the optional mask agnostic
behavior. Follow-up commits will add this optional behavior
for all rvv instructions.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165570784143.17634.35095816584573691-1@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
When running a 32-bit guest, with a e64 vmv.v.x and vl_eq_vlmax set to
true the `tcg_debug_assert(vece <= MO_32)` will be triggered inside
tcg_gen_gvec_dup_i32().
This patch checks that condition and instead uses tcg_gen_gvec_dup_i64()
is required.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1028
Suggested-by: Robert Bu <robert.bu@gmail.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220608234701.369536-1-alistair.francis@opensource.wdc.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
The tail elements in the destination mask register are updated under
a tail-agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-14@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Compares write mask registers, and so always operate under a tail-
agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-12@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
`vmadc` and `vmsbc` produces a mask value, they always operate with
a tail agnostic policy.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-7@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Destination register of unit-stride mask load and store instructions are
always written with a tail-agnostic policy.
A vector segment load / store instruction may contain fractional lmul
with nf * lmul > 1. The rest of the elements in the last register should
be treated as tail elements.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-6@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
According to v-spec, tail agnostic behavior can be either kept as
undisturbed or set elements' bits to all 1s. To distinguish the
difference of tail policies, QEMU should be able to simulate the tail
agnostic behavior as "set tail elements' bits to all 1s".
There are multiple possibility for agnostic elements according to
v-spec. The main intent of this patch-set tries to add option that
can distinguish between tail policies. Setting agnostic elements to
all 1s allows QEMU to express this.
This is the first commit regarding the optional tail agnostic
behavior. Follow-up commits will add this optional behavior
for all rvv instructions.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-5@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
According to v-spec (section 5.4):
When vstart ≥ vl, there are no body elements, and no elements are
updated in any destination vector register group, including that
no tail elements are updated with agnostic values.
vmsbf.m, vmsif.m, vmsof.m, viota.m, vcompress instructions themselves
require vstart to be zero. So they don't need the early exit.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-4@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector whole register load instructions have EEW encoded in the opcode,
so we shouldn't take SEW here. Vector whole register store instructions
are always EEW=8.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165181414065.18540.14828125053334599921-0@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
LEN is not used for GEN_VEXT_VMV_WHOLE macro, so vmv<nr>r.v can share
the same helper
Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Junqiang Wang <wangjunqiang@iscas.ac.cn>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220325085902.29500-2-liweiwei@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
for some cases, scale is always equal or less than 0, since lmul is not larger than 3
Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Junqiang Wang <wangjunqiang@iscas.ac.cn>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220325085902.29500-1-liweiwei@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Replace a config-time define with a compile time condition
define (compatible with clang and gcc) that must be declared prior to
its usage. This avoids having a global configure time define, but also
prevents from bad usage, if the config header wasn't included before.
This can help to make some code independent from qemu too.
gcc supports __BYTE_ORDER__ from about 4.6 and clang from 3.2.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
[ For the s390x parts I'm involved in ]
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220323155743.1585078-7-marcandre.lureau@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
According to v-spec (section 7.9):
The instructions operate with an effective vector length, evl=NFIELDS*VLEN/EEW,
regardless of current settings in vtype and vl. The usual property that no
elements are written if vstart ≥ vl does not apply to these instructions.
Instead, no elements are written if vstart ≥ evl.
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <164762720573.18409.3931931227997483525-0@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
The implementation in trans_{rvi,rvv,rvzfh}.c.inc accesses the shallow
copies (in DisasContext) of some of the elements available in the
RISCVCPUConfig structure. This commit redirects accesses to use the
cfg_ptr copied into DisasContext and removes the shallow copies.
Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220202005249.3566542-4-philipp.tomsich@vrull.eu>
[ Changes by AF:
- Fixup checkpatch failures
]
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
When sew <= 32bits, not need to extend scalar reg.
When sew > 32bits, if xlen is less that sew, we should sign extend
the scalar register, except explicitly specified by the spec.
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220120122050.41546-21-zhiwei_liu@c-sky.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
When pc is written, it is sign-extended to fill the widest supported XLEN.
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220120122050.41546-5-zhiwei_liu@c-sky.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector narrowing conversion instructions are provided to and from all
supported integer EEWs for Zve32f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-17-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector widening conversion instructions are provided to and from all
supported integer EEWs for Zve32f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-16-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector single-width floating-point reduction operations for EEW=32 are
supported for Zve32f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-15-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Zve32f extension requires the scalar processor to implement the F
extension and implement all vector floating-point instructions for
floating-point operands with EEW=32 (i.e., no widening floating-point
operations).
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-14-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
All Zve* extensions support the vector configuration instructions.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-13-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector narrowing conversion instructions are provided to and from all
supported integer EEWs for Zve64f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-10-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector widening conversion instructions are provided to and from all
supported integer EEWs for Zve64f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-9-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector single-width floating-point reduction operations for EEW=32 are
supported for Zve64f extension.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-8-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Zve64f extension requires the scalar processor to implement the F
extension and implement all vector floating-point instructions for
floating-point operands with EEW=32 (i.e., no widening floating-point
operations).
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-7-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
All Zve* extensions support all vector fixed-point arithmetic
instructions, except that vsmul.vv and vsmul.vx are not supported
for EEW=64 in Zve64*.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-6-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
All Zve* extensions support all vector integer instructions,
except that the vmulh integer multiply variants that return the
high word of the product (vmulh.vv, vmulh.vx, vmulhu.vv, vmulhu.vx,
vmulhsu.vv, vmulhsu.vx) are not included for EEW=64 in Zve64*.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-5-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
All Zve* extensions support all vector load and store instructions,
except Zve64* extensions do not support EEW=64 for index values when
XLEN=32.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-4-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
All Zve* extensions support the vector configuration instructions.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-id: 20220118014522.13613-3-frank.chang@sifive.com
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
vfncvt.f.xu.w, vfncvt.f.x.w convert double-width integer to single-width
floating-point. Therefore, should use require_rvf() to check whether
RVF/RVD is enabled.
vfncvt.f.f.w, vfncvt.rod.f.f.w convert double-width floating-point to
single-width integer. Therefore, should use require_scale_rvf() to check
whether RVF/RVD is enabled.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220105022247.21131-4-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
vfwcvt.xu.f.v, vfwcvt.x.f.v, vfwcvt.rtz.xu.f.v and vfwcvt.rtz.x.f.v
convert single-width floating-point to double-width integer.
Therefore, should use require_rvf() to check whether RVF/RVD is enabled.
vfwcvt.f.xu.v, vfwcvt.f.x.v convert single-width integer to double-width
floating-point, and vfwcvt.f.f.v convert double-width floating-point to
single-width floating-point. Therefore, should use require_scale_rvf() to
check whether RVF/RVD is enabled.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220105022247.21131-3-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector widening floating-point instructions should use
require_scale_rvf() instead of require_rvf() to check whether RVF/RVD is
enabled.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220105022247.21131-2-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
SEW has the limitation which cannot exceed ELEN.
Widening instructions have a destination group with EEW = 2*SEW
and narrowing instructions have a source operand with EEW = 2*SEW.
Both of the instructions have the limitation of: 2*SEW <= ELEN.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-78-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Vector Integer Add-with-Carry / Subtract-with-Borrow Instructions is
moved to Section 11.4 in RVV v1.0 spec. Update the comment, no
functional changes.
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-77-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-76-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-75-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-73-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Richard Henderson