Currently we handle flushing of output denormals in uncanon_normal
always before we deal with rounding. This works for architectures
that detect tininess before rounding, but is usually not the right
place when the architecture detects tininess after rounding. For
example, for x86 the SDM states that the MXCSR FTZ control bit causes
outputs to be flushed to zero "when it detects a floating-point
underflow condition". This means that we mustn't flush to zero if
the input is such that after rounding it is no longer tiny.
At least one of our guest architectures does underflow detection
after rounding but flushing of denormals before rounding (MIPS MSA);
this means we need to have a config knob for this that is separate
from our existing tininess_before_rounding setting.
Add an ftz_detection flag. For consistency with
tininess_before_rounding, we make it default to "detect ftz after
rounding"; this means that we need to explicitly set the flag to
"detect ftz before rounding" on every existing architecture that sets
flush_to_zero, so that this commit has no behaviour change.
(This means more code change here but for the long term a less
confusing API.)
For several architectures the current behaviour is either
definitely or possibly wrong; annotate those with TODO comments.
These architectures are definitely wrong (and should detect
ftz after rounding):
* x86
* Alpha
For these architectures the spec is unclear:
* MIPS (for non-MSA)
* RX
* SH4
PA-RISC makes ftz detection IMPDEF, but we aren't setting the
"tininess before rounding" setting that we ought to.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Set the default NaN pattern explicitly for the tests/fp code.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241202131347.498124-36-peter.maydell@linaro.org
Explicitly set a rule in the softfloat tests for propagating NaNs in
the muladd case. In meson.build we put -DTARGET_ARM in fpcflags, and
so we should select here the Arm rule of float_3nan_prop_s_cab.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241202131347.498124-17-peter.maydell@linaro.org
Explicitly set a rule in the softfloat tests for the inf-zero-nan
muladd special case. In meson.build we put -DTARGET_ARM in fpcflags,
and so we should select here the Arm rule of
float_infzeronan_dnan_if_qnan.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20241202131347.498124-5-peter.maydell@linaro.org
Explicitly set a 2-NaN propagation rule in the softfloat tests. In
meson.build we put -DTARGET_ARM in fpcflags, and so we should select
here the Arm propagation rule of float_2nan_prop_s_ab.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241025141254.2141506-3-peter.maydell@linaro.org
At the moment we run all fp-test tests except for the muladd ones
with the default meson test timeout of 30s. This is plenty for
most of the test cases, but for multiplication and division we
can sometimes hit the timeout if the CI runner is going slow.
Add support to meson.build for a way to override the timeout on
a per test basis, and use it to set the timeout to 60s for
fp-test-rem, fp-test-div and fp-test-mul. We can use this new
generic mechanism also to set the timeout for mulAdd rather
than hardcoding it.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240917141641.2836265-1-peter.maydell@linaro.org
When running the tests in slow mode with --enable-debug on a very loaded
system, the fp-test-mulAdd test can take longer than 2 minutes. Bump the
timeout to three minutes to make sure it passes in such situations, too.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20231215070357.10888-16-thuth@redhat.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
This variable is about the host OS, not the target. It is used a lot
more since the Meson conversion, but the original sin dates back to 2003.
Time to fix it.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
config_all now lists only accelerators, rename it to indicate its actual
content.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
tests/fp/berkeley-softfloat-3 and tests/fp/berkeley-testfloat-3
have been replaced by subprojects, so remove the now-unnecessary
submodules.
Reported-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unlike other subprojects, these require an overlay directory to include
meson rules to build the libraries. The rules are basically lifted
from tests/fp/meson.build, with a few changes to create platform.h
and publish a dependency.
The build defines are passed through a subproject option, and posted
back to users of the library via the dependency's compile_args.
The only remaining user of GIT_SUBMODULES and GIT_SUBMODULES_ACTION
is roms/SLOF, which is used to build pc-bios/s390-ccw. All other
roms submodules are only present to satisfy the license on pre-built
firmware blobs.
Best reviewed with --color-moved.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
As we like to run tests under CI with V=1 flags the softfloat tests
can add up to a fair amount of extra log lines. With an update to the
testfloat library we can now call fp-test with the -q flag and reduce
the output to a terse one line per function tested.
make check-softfloat V=1 | wc -l
759
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230228190653.1602033-5-alex.bennee@linaro.org>
We've been very gradually adding G_GNUC_PRINTF annotations
to functions over years. This has been useful in detecting
certain malformed printf strings, or cases where we pass
user data as the printf format which is a potential security
flaw.
Given the inherant memory corruption danger in use of format
strings vs mis-matched variadic arguments, it is worth applying
G_GNUC_PRINTF to all functions using printf, even if we know
they are safe.
The compilers can reasonably reliably identify such places
with the -Wsuggest-attribute=format / -Wmissing-format-attribute
flags.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20221219130205.687815-7-berrange@redhat.com>
[-Wsuggest-attribute=format and -Wmissing-format-attribute are
synonyms, only include one; disable it for testfloat. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Technically we don't need the TCG accelerator to run the
softfloat3 tests. However it is unlikely an interesting
build combination. Developers using softfloat3 likely use
TCG too. Similarly, developers disabling TCG shouldn't
mind much about softfloat3 tests.
This reduces a non-TCG build by 474 objects!
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20220204152924.6253-3-f4bug@amsat.org>
Signed-off-by: Thomas Huth <thuth@redhat.com>
G_NORETURN was introduced in glib 2.68, fallback to G_GNUC_NORETURN in
glib-compat.
Note that this attribute must be placed before the function declaration
(bringing a bit of consistency in qemu codebase usage).
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Warner Losh <imp@bsdimp.com>
Message-Id: <20220420132624.2439741-20-marcandre.lureau@redhat.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>
Since we already use -Wno-unknown-pragmas, we can also use
-Wno-ignored-pragmas. This silences hundred of warnings using
clang 13 on macOS Monterey:
[409/771] Compiling C object tests/fp/libtestfloat.a.p/berkeley-testfloat-3_source_test_az_f128_rx.c.o
../tests/fp/berkeley-testfloat-3/source/test_az_f128_rx.c:49:14: warning: '#pragma FENV_ACCESS' is not supported on this target - ignored [-Wignored-pragmas]
#pragma STDC FENV_ACCESS ON
^
1 warning generated.
Having:
$ cc -v
Apple clang version 13.0.0 (clang-1300.0.29.30)
Reported-by: Roman Bolshakov <roman@roolebo.dev>
Reviewed-by: Akihiko Odaki <akihiko.odaki@gmail.com>
Tested-by: Akihiko Odaki <akihiko.odaki@gmail.com>
Acked-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
"meson test" starting with version 0.57 is just as capable and easy to
use as QEMU's own TAP driver. All existing options for "make check"
work. The only required code change involves how to mark "slow" tests;
they need to belong to an additional "slow" suite.
The rules for .tap output are replaced by JUnit XML; GitLab is able
to parse that output and present it in the CI pipeline report.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fix the trivial typo in extF80_lt_quiet, and re-enable
all of the floatx80 tests that are now fixed.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-ID: <87bl9iyahr.fsf@linaro.org>
[rth: Squash the fix for lt_quiet, and enable that too.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Rename to parts$N_log2. Though this is partly a ruse, since I do not
believe the code will succeed for float128 without work. Which is ok
for now, because we do not need this for more than float32 and float64.
Since berkeley-testfloat-3 doesn't support log2, compare float64_log2
vs the system log2. Fix the errors for inputs near 1.0:
test: 3ff00000000000b0 +0x1.00000000000b0p+0
sf: 3d2fa00000000000 +0x1.fa00000000000p-45
libm: 3d2fbd422b1bd36f +0x1.fbd422b1bd36fp-45
Error in fraction: 32170028290927 ulp
test: 3feec24f6770b100 +0x1.ec24f6770b100p-1
sf: bfad3740d13c9ec0 -0x1.d3740d13c9ec0p-5
libm: bfad3740d13c9e98 -0x1.d3740d13c9e98p-5
Error in fraction: 40 ulp
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Many qemu softfloat will check floatx80_rounding_precision
even when berkeley testfloat will not. So begin with
floatx80_precision_x, so that's the one we use
when !FUNC_EFF_ROUNDINGPRECISION.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Use an enumeration instead of raw 32/64/80 values.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Rename to parts$N_muladd.
Implement float128_muladd with FloatParts128.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Currently this only support softfloat calculations because working out
if the hardware supports 128 bit floats needs configure magic. The 3
op muladd operation is currently unimplemented so commented out for
now.
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20201020163738.27700-8-alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Follow the inclusive terminology from the "Conscious Language in your
Open Source Projects" guidelines [*] and replace the word "blacklist"
appropriately.
[*] https://github.com/conscious-lang/conscious-lang-docs/blob/main/faq.md
Acked-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20210303184644.1639691-6-philmd@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Adjust the timeouts for the benchmarks (Meson 0.57 allows 0 to mean
infinite) and for the longest running tests. These are the
times that I measured and the corresponding timeouts. For generic
qtests, the target that reported the longest runtime is included.
unit tests:
test-crypto-tlscredsx509 13.15s 45s
test-crypto-tlssession 14.12s 45s
qtests:
qos-test 21.26s 60s (i386)
ahci-test 22.18s 60s
pxe-test 26.51s 60s
boot-serial-test 28.02s 60s (sparc)
prom-env-test 28.86s 60s
bios-tables-test 50.17s 120s (aarch64)
test-hmp 57.15s 120s (aarch64)
npcm7xx_pwm-test 71.27s 150s
migration-test 97.09s 150s (aarch64)
qom-test 139.20s 240s (aarch64)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The softfloat tests are external repositories, so we do not care
about implicit fallthrough warnings in this code.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Chen Qun <kuhn.chenqun@huawei.com>
Message-Id: <20201211152426.350966-12-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Starting with meson 0.56, colons are used to separate the subproject name
from the test name. Use dash or slash depending on what looks nicer.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Since we are now always doing out-of-tree builds, these gitignore
files should not be necessary anymore.
Message-Id: <20200919133637.72744-1-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Build all executables by default except for the known-broken ones.
This also allows running qemu-iotests without manually building
socket_scm_helper.
Reported-by: Max Reitz <mreitz@redhat.com>
Tested-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
With Makefiles that have automatically generated dependencies, you
generated includes are set as dependencies of the Makefile, so that they
are built before everything else and they are available when first
building the .c files.
Alternatively you can use a fine-grained dependency, e.g.
target/arm/translate.o: target/arm/decode-neon-shared.inc.c
With Meson you have only one choice and it is a third option, namely
"build at the beginning of the corresponding target"; the way you
express it is to list the includes in the sources of that target.
The problem is that Meson decides if something is a source vs. a
generated include by looking at the extension: '.c', '.cc', '.m', '.C'
are sources, while everything else is considered an include---including
'.inc.c'.
Use '.c.inc' to avoid this, as it is consistent with our other convention
of using '.rst.inc' for included reStructuredText files. The editorconfig
file is adjusted.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Slightly tidies the usage within softfloat.c and the
representation in float_status.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Re-calling the main make is counter-productive and really messes up
with parallel builds. Just ensure we have built the pre-requisites
before we build the fp-test bits. If the user builds manually just
complain if the parent build hasn't got the bits we need.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Emilio G. Cota <cota@braap.org>
Previously this was only supported for roundAndPackFloat64.
New support in round_canonical, round_to_int, float128_round_to_int,
roundAndPackFloat32, roundAndPackInt32, roundAndPackInt64,
roundAndPackUint64. This does not include any of the floatx80 routines,
as we do not have users for that rounding mode there.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20190215170225.15537-1-richard.henderson@linaro.org>
Tested-by: David Hildenbrand <david@redhat.com>
[AJB: add missing break]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Needed to test: softfloat: Implement float128_to_uint32
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
We get HOST_WORDS_BIGENDIAN from config-host.h, but the include
is missing. Fix it.
This fixes `make check-softfloat' on big endian hosts.
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
At this point random_ops[] only contains normals, so there's
no need to do anything to them. In fact, raising the exponent
here can make the output !normal, which is precisely
what the comment says we want to avoid.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
The second test in the branches is wrong; fix while converting
to a switch statement, which is easier to get right.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Clean up includes so that osdep.h is included first and headers
which it implies are not included manually.
This commit was created with scripts/clean-includes, with the changes
to the following files manually reverted:
contrib/libvhost-user/libvhost-user-glib.h
contrib/libvhost-user/libvhost-user.c
contrib/libvhost-user/libvhost-user.h
linux-user/mips64/cpu_loop.c
linux-user/mips64/signal.c
linux-user/sparc64/cpu_loop.c
linux-user/sparc64/signal.c
linux-user/x86_64/cpu_loop.c
linux-user/x86_64/signal.c
target/s390x/gen-features.c
tests/migration/s390x/a-b-bios.c
tests/test-rcu-simpleq.c
tests/test-rcu-tailq.c
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20181204172535.2799-1-armbru@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Acked-by: Yuval Shaia <yuval.shaia@oracle.com>
Acked-by: Viktor Prutyanov <viktor.prutyanov@phystech.edu>
These microbenchmarks will allow us to measure the performance impact of
FP emulation optimizations. Note that we can measure both directly the impact
on the softfloat functions (with "-t soft"), or the impact on an
emulated workload (call with "-t host" and run under qemu user-mode).
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
This gets rid of the muladd errors due to not raising the invalid flag.
- Before:
Errors found in f64_mulAdd, rounding near_even, tininess before rounding:
+000.0000000000000 +7FF.0000000000000 +7FF.FFFFFFFFFFFFF
=> +7FF.FFFFFFFFFFFFF ..... expected -7FF.FFFFFFFFFFFFF v....
[...]
- After:
In 6133248 tests, no errors found in f64_mulAdd, rounding near_even, tininess before rounding.
[...]
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
By leveraging berkeley's softfloat and testfloat.
With this we get decent coverage of softfloat.c:
$ ./fp-test -r even: 67.22% coverage
$ ./fp-test -r all: 73.11% coverage
Note that we do not yet test parts of softfloat.c that aren't
in the original softfloat library, namely:
- denormal inputs
- *_to_int16/uint16 conversions
- scalbn for fixed point
- muladd variants
- min/max
- exp2
- log2
- float*_compare (except float16_compare)
Signed-off-by: Emilio G. Cota <cota@braap.org>
[rth: Add the new modules to git_submodules.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
These are BSD-licensed so we can add them as submodules.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Peter Maydell
Thomas Huth
Paolo Bonzini
Alex Bennée
Daniel P. Berrangé
Philippe Mathieu-Daudé
Marc-André Lureau
Richard Henderson
Philippe Mathieu-Daudé
Emilio G. Cota
Markus Armbruster