Performance results for fp-bench:
Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
sqrt-single: 42.30 MFlops
sqrt-double: 22.97 MFlops
- after:
sqrt-single: 311.42 MFlops
sqrt-double: 311.08 MFlops
Here USE_FP makes a huge difference for f64's, with throughput
going from ~200 MFlops to ~300 MFlops.
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>
The appended paves the way for leveraging the host FPU for a subset
of guest FP operations. For most guest workloads (e.g. FP flags
aren't ever cleared, inexact occurs often and rounding is set to the
default [to nearest]) this will yield sizable performance speedups.
The approach followed here avoids checking the FP exception flags register.
See the added comment for details.
This assumes that QEMU is running on an IEEE754-compliant FPU and
that the rounding is set to the default (to nearest). The
implementation-dependent specifics of the FPU should not matter; things
like tininess detection and snan representation are still dealt with in
soft-fp. However, this approach will break on most hosts if we compile
QEMU with flags that break IEEE compatibility. There is no way to detect
all of these flags at compilation time, but at least we check for
-ffast-math (which defines __FAST_MATH__) and disable hardfloat
(plus emit a #warning) when it is set.
This patch just adds common code. Some operations will be migrated
to hardfloat in subsequent patches to ease bisection.
Note: some architectures (at least PPC, there might be others) clear
the status flags passed to softfloat before most FP operations. This
precludes the use of hardfloat, so to avoid introducing a performance
regression for those targets, we add a flag to disable hardfloat.
In the long run though it would be good to fix the targets so that
at least the inexact flag passed to softfloat is indeed sticky.
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>
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>
These will gain some users very soon.
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>
glibc >= 2.25 defines canonicalize in commit eaf5ad0
(Add canonicalize, canonicalizef, canonicalizel., 2016-10-26).
Given that we'll be including <math.h> soon, prepare
for this by prefixing our canonicalize() with sf_ to avoid
clashing with the libc's canonicalize().
Reported-by: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
Tested-by: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
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 paves the way for upcoming work.
Reviewed-by: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
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>
Given I've spent a fair amount of time around this code now I'm
putting myself forward as a maintainer. Also given that the code has
been extensively re-written and has testing and new incoming features
it is probably more than just Odd Fixes.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
This is a QEMU specific version of a gitdm config for generating
reports on the contributor base of the project. I've added enough
group maps and domain aliases to ensure the current top ten is as
reflective as it can be. As of this commit running:
git log --numstat --since "Last Year" | gitdm -n -l 10
Reports:
Top changeset contributors by employer
Red Hat 3172 (44.3%)
Linaro 1153 (16.1%)
(None) 549 (7.7%)
IBM 348 (4.9%)
Academics (various) 170 (2.4%)
Virtuozzo 168 (2.3%)
Wave Computing 118 (1.6%)
Xilinx 102 (1.4%)
Igalia 93 (1.3%)
Cadence Design Systems 88 (1.2%)
Top lines changed by employer
Red Hat 144092 (28.1%)
Cadence Design Systems 126554 (24.6%)
Linaro 77480 (15.1%)
Wave Computing 33134 (6.5%)
SiFive 14392 (2.8%)
IBM 12219 (2.4%)
(None) 11948 (2.3%)
Academics (various) 10447 (2.0%)
Virtuozzo 10445 (2.0%)
CodeWeavers 9179 (1.8%)
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Change the order in which we extract a/b and c/d to
match the output of the upstream xxhash32.
Tested with:
https://github.com/cota/xxhash/tree/qemu
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: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Before moving them all to include/qemu/xxhash.h.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Which we forgot to do in bd224fce60 ("qht-bench: add -p flag
to precompute hash values", 2018-09-26).
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
It's unused since 75e8b9b7aa.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181209193749.12277-9-cota@braap.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Instead of hard coding 31 for the shift right use TCG_TARGET_REG_BITS - 1.
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <7dfbddf7014a595150aa79011ddb342c3cc17ec3.1544648105.git.alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
For now, defined universally as true, since we previously required
backends to implement swapped memory operations. Future patches
may now remove that support where it is onerous.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Somehow we forgot these operations, once upon a time.
This will allow immediate stores to have their bswap
optimized away.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Based on the only current user, Sparc:
New code uses 2 constants that take 2 insns to load from constant pool,
plus 13. Old code used 6 constants that took 1 or 2 insns to create,
plus 21. The result is a new total of 17 vs an old total of 29.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Based on the only current user, Sparc:
New code uses 1 constant that takes 2 insns to create, plus 8.
Old code used 2 constants that took 2 insns to create, plus 9.
The result is a new total of 10 vs an old total of 13.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
These values are constant between all qemu_ld/st invocations;
there is no need to figure this out each time. If we cannot
use a segment or an offset directly for guest_base, load the
value into a register in the prologue.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
We now have an invariant that all TCG_TYPE_I32 values are
zero-extended, which means that we do not need to extend
them again during qemu_ld/st, either explicitly via a separate
tcg_out_ext32u or implicitly via P_ADDR32.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This preserves the invariant that all TCG_TYPE_I32 values are
zero-extended in the 64-bit host register.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This helps preserve the invariant that all TCG_TYPE_I32 values
are stored zero-extended in the 64-bit host registers.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This helps preserve the invariant that all TCG_TYPE_I32 values
are stored zero-extended in the 64-bit host registers.
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This does require an extra two checks within the slow paths
to replace the assert that we're moving. Also add two checks
within existing functions that lacked any kind of assert for
out of range branch.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
The reloc_pc{14,24}_val routines retain their asserts.
Use these directly within the slow paths.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This does require an extra two checks within the slow paths
to replace the assert that we're moving.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This does require an extra two checks within the slow paths
to replace the assert that we're moving.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This will move the assert for success from within (subroutines of)
patch_reloc into the callers. It will also let new code do something
different when a relocation is out of range.
For the moment, all backends are trivially converted to return true.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There is no longer a need for preserving branch offset operands,
as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There is no longer a need for preserving branch offset operands,
as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There is no longer a need for preserving branch offset operands,
as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There is no longer a need for preserving branch offset operands,
as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There are one use apiece for these. There is no longer a need for
preserving branch offset operands, as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
There are one use apiece for these. There is no longer a need for
preserving branch offset operands, as we no longer re-translate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
For x86_64, this can remove a REX prefix resulting in smaller code
when manipulating globals of type i32, as we move them between backing
store via cpu_env, aka TCG_AREG0.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Partially reverts ab20bdc116. The 14-bit displacement that we
allowed to reach the constant pool is not always sufficient.
Retain the tb-relative addressing, as that is how most return
values from the tb are computed.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
- qcow2: Decompression worker threads
- dmg: lzfse compression support
- file-posix: Simplify delegation to worker thread
- Don't pass flags to bdrv_reopen_queue()
- iotests: make 235 work on s390 (and others)
-----BEGIN PGP SIGNATURE-----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=XKq9
-----END PGP SIGNATURE-----
Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging
Block layer patches:
- qcow2: Decompression worker threads
- dmg: lzfse compression support
- file-posix: Simplify delegation to worker thread
- Don't pass flags to bdrv_reopen_queue()
- iotests: make 235 work on s390 (and others)
# gpg: Signature made Fri 14 Dec 2018 10:55:09 GMT
# gpg: using RSA key 7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74 56FE 7F09 B272 C88F 2FD6
* remotes/kevin/tags/for-upstream: (42 commits)
block/mirror: add missing coroutine_fn annotations
iotests: make 235 work on s390 (and others)
block: Assert that flags are up-to-date in bdrv_reopen_prepare()
block: Remove assertions from update_flags_from_options()
block: Stop passing flags to bdrv_reopen_queue_child()
block: Remove flags parameter from bdrv_reopen_queue()
block: Clean up reopen_backing_file() in block/replication.c
qemu-io: Put flag changes in the options QDict in reopen_f()
block: Drop bdrv_reopen()
block: Use bdrv_reopen_set_read_only() in the mirror driver
block: Use bdrv_reopen_set_read_only() in external_snapshot_commit()
block: Use bdrv_reopen_set_read_only() in qmp_change_backing_file()
block: Use bdrv_reopen_set_read_only() in stream_start/complete()
block: Use bdrv_reopen_set_read_only() in bdrv_commit()
block: Use bdrv_reopen_set_read_only() in commit_start/complete()
block: Use bdrv_reopen_set_read_only() in bdrv_backing_update_filename()
block: Add bdrv_reopen_set_read_only()
file-posix: Avoid aio_worker() for QEMU_AIO_IOCTL
file-posix: Switch to .bdrv_co_ioctl
file-posix: Remove paio_submit_co()
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
