Commit Graph

946 Commits

Author SHA1 Message Date
Jilin Zhou
0ae233ab23 [#766] add x-compile support for QNX SDP7 (#770)
Since googletest already supports x-compilation for QNX, it is nice to
 have google benchmark support it too.
Fixes #766
2019-02-19 13:05:55 +00:00
Wes McKinney
7c571338b5 Prefer -pthread to -lpthread for better compatibility when cross-compiling (#771) 2019-02-19 12:32:11 +00:00
Roman Lebedev
b8ca0c4217
README.md: mention that fixture has SetUp() / TearDown() 2019-02-04 16:26:51 +03:00
Daniel Kraft
97393e5ef8 Add -lpthread to pkg-config Libs.private. (#755)
Since pthread is required at least for GCC (according to the
documentation), this should be reflected by the pkg-config file.

The same is, for instance, also done by the gflags library:
1005485222/cmake/package.pc.in (L13)
2019-02-01 15:51:44 +03:00
Dominic Hamon
785e2c3158
Move Statistics struct to internal namespace (#753) 2019-01-15 13:19:36 +00:00
Andriy Berestovskyy
4b9f43e2c4 Fix header lines length (#752)
Commit 17a012d7 added a newline to the str, so the line built from
str.length() is one character longer than it should be.
2019-01-13 17:26:49 +03:00
Michael "Croydon" Keck
eec9a8e497 Add minimal Conan support (#728) 2019-01-03 13:42:07 +00:00
Reid Kleckner
dc10645549 Set CMP0048 policy before project() to silence warnings (#750)
If this policy isn't set, CMake emits a large warning when project() is
called from a cmake subdirectory.

This came up when the benchmark library was added to the LLVM build, and
it was reported in https://llvm.org/PR38874. This patch was the fix I
applied locally to fix the issue, and I wanted to send it upstream.
2018-12-30 20:46:07 +03:00
Eric
4528c76b71
Print at least three significant digits for times. (#701)
Some benchmarks are particularly sensitive and they run in less than
a nanosecond. In order for the console reporter to provide meaningful
output for such benchmarks it needs to be able to display the times
using more resolution than a single nanosecond.

This patch changes the console reporter to print at least three
significant digits for all results.

Unlike the initial attempt, this patch does not align the decimal point.
2018-12-13 22:49:21 -05:00
Roman Lebedev
57bf879d49
README.md: document State::{Pause,Resume}Timing()
As pointed out in IRC, these are not documented.
2018-12-14 01:20:01 +03:00
Dominic Hamon
0ed529a7e3
Update documentation of benchmark_filter (#744)
It should now match reality.
2018-12-13 11:14:50 +00:00
Jatin Chaudhary
47a5f77d75 #722 Adding Host Name in Reporting (#733)
* Adding Host Name and test

* Addressing Review Comments

* Adding Test for JSON Reporter

* Adding HOST_NAME_MAX for MacOS systems

* Adding Explaination for MacOS HOST_NAME_MAX Addition

* Addressing Peer Review Comments

* Adding codecvt in windows header guard

* Changing name SystemInfo and adding empty message incase host name fetch fails

* Adding Comment on Struct SystemInfo
2018-12-11 11:23:02 +00:00
Tobias Ulvgård
1f3cba06e4 Update reference to complexity calculation (#723) 2018-12-10 15:15:34 +00:00
Cyrille
5cb8f8a03d Fix signed vs unsigned comparisons in string_util unit tests (#742)
Unit-tests fail to build due to the following errors:

/home/cfx/Dev/google-benchmark/benchmark.git/test/string_util_gtest.cc:12:5: required from here
/home/cfx/Applications/googletest-1.8.1/include/gtest/gtest.h:1444:11: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
   if (lhs == rhs) {
       ~~~~^~~~~~

Fixes #741
2018-12-10 10:24:22 +00:00
Jusufadis Bakamovic
eee8b05c97 [tools] Run autopep8 and apply fixes found. (#739) 2018-12-07 16:34:00 +03:00
Eric
eafa34a5e8
Remove use of std::tmpnam. (#734)
std::tmpnam is deprecated and its use is discouraged. For our purposes
in the tests, we really just need a file name which is unlikely to
exist.

This patch converts the tests to using a dummy random file name
generator, which should hopefully avoid name conflicts.
2018-11-29 22:51:44 -05:00
Roman Lebedev
19f7d5c2bc
README.md: complexity lambda takes int64_t arg. Fixes #719 2018-11-29 01:23:25 +03:00
Roman Lebedev
c9f2693ea9 StrFormat() is a printf-like function, mark it as such, fix fallout. (#727)
Fixes #714.
2018-11-26 19:55:05 -05:00
Roman Lebedev
c9311a44e1
README.md: BM_Sequential(): the return type is 'void'
Used that example as a snippet, and it took a moment to notice
what needed to be changed to make it compile..
2018-11-26 15:39:36 +03:00
Denis Glazachev
56f5cd6a72 Fix C++17 mode compilation with Apple clang (#721) 2018-11-21 21:38:24 -05:00
Dominic Hamon
b1717916d1 Merge branch 'atdt-report_loadavg' 2018-11-13 10:14:28 +00:00
Dominic Hamon
b5082bbd65 Merge branch 'report_loadavg' of https://github.com/atdt/benchmark into atdt-report_loadavg 2018-11-13 10:13:58 +00:00
Dominic Hamon
bb15a4e3bf Ensure all informational cmake messages have STATUS type 2018-11-13 09:56:22 +00:00
Kirill Bobyrev
a9b31c51b1 Disable exceptions in Microsoft STL (#715)
This is the copy of patch proposed to LLVM's copy of benchmark via
https://reviews.llvm.org/D52998.
2018-11-02 16:03:49 +00:00
Anton Gladky
c6193afe7e Fix parsing of cpuinfo for s390 platform. (#712)
s390 has another line structure for processor-field.
It should be differently parsed.
2018-10-21 11:01:42 +03:00
Roman Lebedev
507c06e636
Aggregates: use non-aggregate count as iteration count. (#706)
It is incorrect to say that an aggregate is computed over
run's iterations, because those iterations already got averaged.
Similarly, if there are N repetitions with 1 iterations each,
an aggregate will be computed over N measurements, not 1.
Thus it is best to simply use the count of separate reports.

Fixes #586.
2018-10-18 17:17:14 +03:00
Roman Lebedev
99d1356c04
[NFC] BenchmarkRunner: always populate *_report_aggregates_only bools. (#708)
It is better to let the RunBenchmarks(), report() decide
whether to actually *only* output aggregates or not,
depending on whether there are actually aggregates.

It's subtle indeed.

Previously, `BenchmarkRunner()` always said that "if there are no repetitions,
then you should never output only the repetitions". And the `report()` simply assumed
that the `report_aggregates_only` bool it received makes sense, and simply used it.

Now, the logic is the same, but the blame has shifted.
`BenchmarkRunner()` always propagates what those benchmarks would have wanted
to happen wrt the aggregates. And the `report()` lambda has to actually consider
both the `report_aggregates_only` bool, and it's meaningfulness.

To put it in the context of the patch series - if the repetition count was `1`,
but `*_report_aggregates_only` was set to `true`, and we capture each iteration separately,
then we will compute the aggregates, but then output everything, both the iteration,
and aggregates, despite `*_report_aggregates_only` being set to `true`.
2018-10-18 15:08:59 +03:00
Roman Lebedev
9cacec8e78
[NFC] RunBenchmarks(): s/has_repetitions/might_have_aggregates/ (#707)
That is the real purpose of that bool. A follow-up change will
make it consider something else other than repetitions.
2018-10-18 15:03:17 +03:00
Olzhas Kaiyrakhmet
d731697a5d Fix SOURCE_DIR in HandleGTest.cmake (#705)
If benchmark added as cmake subproject, HandleGTest throws an error as  does return absolute source dir.
Change it to , so it will be refering to it's own source dir.

Also see PR #703.
2018-10-13 01:06:41 -07:00
Eric
8356d646bf
Revert "Fix SOURCE_DIR in HandleGTest.cmake (#703)" (#704)
This reverts commit 609752306f.
2018-10-13 00:53:25 -07:00
Olzhas Kaiyrakhmet
609752306f Fix SOURCE_DIR in HandleGTest.cmake (#703)
* Fix SOURCE_DIR in HandleGTest.cmake

If benchmark added as cmake subproject, HandleGTest throws an error as  does return absolute source dir.
Change it to , so it will be refering to it's own source dir.
2018-10-13 00:51:51 -07:00
Ilya A. Kriveshko
8503dfe537 benchmark_color: fix auto option (#559) (#699)
As prevously written, "--benchmark_color=auto" was treated as true,
because IsTruthyFlagValue("auto") returned true.  The fix is to
rely on IsColorTerminal test only if the flag value is "auto",
and fall back to IsTruthyFlagValue otherwise.  I also integrated
force_no_color check into the same block.
2018-10-08 09:33:21 +01:00
Gregorio Litenstein
9ffb8df6c5 Fix Clang Detection (#697)
For several versions now, CMake by default refers to macOS’ Clang as AppleClang instead of just Clang, which would fail STREQUAL. Fixed by changing it to MATCHES.
2018-10-05 16:44:02 +01:00
Roman Lebedev
a8082de5df
[NFC] Refactor RunBenchmark() (#690)
Ok, so, i'm still trying to get to the state when it will be a trivial change to report all the separate iterations.
The old code (LHS of the diff) was rather convoluted i'd say.
I have tried to refactor it a bit into *small* logical chunks, with proper comments.
As far as i can tell, i preserved the intent of the code, what it was doing before.
The road forward still isn't clear, but i'm quite sure it's not with the old code :)
2018-10-01 17:51:08 +03:00
Victor Costan
d8c0f27448 Fix possible loss of data warnings in MSVC. (#694) 2018-10-01 13:00:13 +01:00
Dominic Hamon
edc77a3669
Make State constructor private. (#650)
The State constructor should not be part of the public API. Adding a
utility method to BenchmarkInstance allows us to avoid leaking the
RunInThread method into the public API.
2018-09-28 12:28:43 +01:00
Roman Lebedev
eb8cbec077 appveyor ci: drop Visual Studio 12 2013 - unsupported by Google Test master branch. (#691)
See https://github.com/google/googletest/pull/1815

Fixes #689.
2018-09-26 10:11:54 +01:00
Roman Lebedev
aad33aab3c
[Tooling] Rewrite generate_difference_report(). (#678)
My knowledge of python is not great, so this is kinda horrible.

Two things:
1. If there were repetitions, for the RHS (i.e. the new value) we were always using the first repetition,
    which naturally results in incorrect change reports for the second and following repetitions.
    And what is even worse, that completely broke U test. :(
2. A better support for different repetition count for U test was missing.
    It's important if we are to be able to report 'iteration as repetition',
    since it is rather likely that the iteration count will mismatch.

Now, the rough idea on how this is implemented now. I think this is the right solution.
1. Get all benchmark names (in order) from the lhs benchmark.
2. While preserving the order, keep the unique names
3. Get all benchmark names (in order) from the rhs benchmark.
4. While preserving the order, keep the unique names
5. Intersect `2.` and `4.`, get the list of unique benchmark names that exist on both sides.
6. Now, we want to group (partition) all the benchmarks with the same name.
   ```
   BM_FOO:
       [lhs]: BM_FOO/repetition0 BM_FOO/repetition1
       [rhs]: BM_FOO/repetition0 BM_FOO/repetition1 BM_FOO/repetition2
   ...
   ```
   We also drop mismatches in `time_unit` here.
   _(whose bright idea was it to store arbitrarily scaled timers in json **?!** )_
7. Iterate for each partition
7.1. Conditionally, diff the overlapping repetitions (the count of repetitions may be different.)
7.2. Conditionally, do the U test:
7.2.1. Get **all** the values of `"real_time"` field from the lhs benchmark
7.2.2. Get **all** the values of `"cpu_time"` field from the lhs benchmark
7.2.3. Get **all** the values of `"real_time"` field from the rhs benchmark
7.2.4. Get **all** the values of `"cpu_time"` field from the rhs benchmark
          NOTE: the repetition count may be different, but we want *all* the values!
7.2.5. Do the rest of the u test stuff
7.2.6. Print u test
8. ???
9. **PROFIT**!

Fixes #677
2018-09-19 15:59:13 +03:00
Martin Storsjö
439d6b1c2a Include sys/time.h for cycleclock.h when building on MinGW (#680)
When building for ARM, there is a fallback codepath that uses
gettimeofday, which requires sys/time.h.

The Windows SDK doesn't have this header, but MinGW does have it.
Thus, this fixes building for Windows on ARM with MinGW
headers/libraries, while Windows on ARM with the Windows SDK still
is broken.
2018-09-19 11:52:05 +01:00
Martin Storsjö
5261307982 [benchmark] Lowercase windows specific includes (#679)
The windows SDK headers don't have self-consistent casing anyway,
and many projects consistently use lowercase for them, in order
to fix crosscompilation with mingw headers.
2018-09-18 09:42:20 +01:00
Roman Lebedev
a5e9c061d9
[Tooling] 'display aggregates only' support. (#674)
Works as you'd expect, both for the benchmark binaries, and
the jsons (naturally, since the tests need to work):
```
$ ~/src/googlebenchmark/tools/compare.py benchmarks ~/rawspeed/build-{0,1}/src/utilities/rsbench/rsbench --benchmark_repetitions=3 *
RUNNING: /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench --benchmark_repetitions=3 2K4A9927.CR2 2K4A9928.CR2 2K4A9929.CR2 --benchmark_out=/tmp/tmpYoui5H
2018-09-12 20:23:47
Running /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
  L1 Data 16K (x8)
  L1 Instruction 64K (x4)
  L2 Unified 2048K (x4)
  L3 Unified 8192K (x1)
-----------------------------------------------------------------------------------------------
Benchmark                                        Time           CPU Iterations UserCounters...
-----------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time               447 ms        447 ms          2 CPUTime,s=0.447302 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=117.738M Pixels/WallTime=117.738M Raws/CPUTime=2.23562 Raws/WallTime=2.23564 WallTime,s=0.4473
2K4A9927.CR2/threads:8/real_time               444 ms        444 ms          2 CPUTime,s=0.444228 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=118.552M Pixels/WallTime=118.553M Raws/CPUTime=2.2511 Raws/WallTime=2.25111 WallTime,s=0.444226
2K4A9927.CR2/threads:8/real_time               447 ms        447 ms          2 CPUTime,s=0.446983 CPUTime/WallTime=0.999999 Pixels=52.6643M Pixels/CPUTime=117.822M Pixels/WallTime=117.822M Raws/CPUTime=2.23722 Raws/WallTime=2.23722 WallTime,s=0.446984
2K4A9927.CR2/threads:8/real_time_mean          446 ms        446 ms          2 CPUTime,s=0.446171 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=118.037M Pixels/WallTime=118.038M Raws/CPUTime=2.24131 Raws/WallTime=2.24132 WallTime,s=0.44617
2K4A9927.CR2/threads:8/real_time_median        447 ms        447 ms          2 CPUTime,s=0.446983 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=117.822M Pixels/WallTime=117.822M Raws/CPUTime=2.23722 Raws/WallTime=2.23722 WallTime,s=0.446984
2K4A9927.CR2/threads:8/real_time_stddev          2 ms          2 ms          2 CPUTime,s=1.69052m CPUTime/WallTime=3.53737u Pixels=0 Pixels/CPUTime=448.178k Pixels/WallTime=448.336k Raws/CPUTime=8.51008m Raws/WallTime=8.51308m WallTime,s=1.6911m
2K4A9928.CR2/threads:8/real_time               563 ms        563 ms          1 CPUTime,s=0.562511 CPUTime/WallTime=0.999824 Pixels=27.9936M Pixels/CPUTime=49.7654M Pixels/WallTime=49.7567M Raws/CPUTime=1.77774 Raws/WallTime=1.77743 WallTime,s=0.56261
2K4A9928.CR2/threads:8/real_time               561 ms        561 ms          1 CPUTime,s=0.561328 CPUTime/WallTime=0.999917 Pixels=27.9936M Pixels/CPUTime=49.8703M Pixels/WallTime=49.8662M Raws/CPUTime=1.78149 Raws/WallTime=1.78134 WallTime,s=0.561375
2K4A9928.CR2/threads:8/real_time               570 ms        570 ms          1 CPUTime,s=0.570423 CPUTime/WallTime=0.999876 Pixels=27.9936M Pixels/CPUTime=49.0752M Pixels/WallTime=49.0691M Raws/CPUTime=1.75308 Raws/WallTime=1.75287 WallTime,s=0.570493
2K4A9928.CR2/threads:8/real_time_mean          565 ms        565 ms          1 CPUTime,s=0.564754 CPUTime/WallTime=0.999872 Pixels=27.9936M Pixels/CPUTime=49.5703M Pixels/WallTime=49.564M Raws/CPUTime=1.77077 Raws/WallTime=1.77055 WallTime,s=0.564826
2K4A9928.CR2/threads:8/real_time_median        563 ms        563 ms          1 CPUTime,s=0.562511 CPUTime/WallTime=0.999876 Pixels=27.9936M Pixels/CPUTime=49.7654M Pixels/WallTime=49.7567M Raws/CPUTime=1.77774 Raws/WallTime=1.77743 WallTime,s=0.56261
2K4A9928.CR2/threads:8/real_time_stddev          5 ms          5 ms          1 CPUTime,s=4.945m CPUTime/WallTime=46.3459u Pixels=0 Pixels/CPUTime=431.997k Pixels/WallTime=432.061k Raws/CPUTime=0.015432 Raws/WallTime=0.0154343 WallTime,s=4.94686m
2K4A9929.CR2/threads:8/real_time               306 ms        306 ms          2 CPUTime,s=0.306476 CPUTime/WallTime=0.999961 Pixels=12.4416M Pixels/CPUTime=40.5957M Pixels/WallTime=40.5941M Raws/CPUTime=3.2629 Raws/WallTime=3.26277 WallTime,s=0.306488
2K4A9929.CR2/threads:8/real_time               310 ms        310 ms          2 CPUTime,s=0.309978 CPUTime/WallTime=0.999939 Pixels=12.4416M Pixels/CPUTime=40.1371M Pixels/WallTime=40.1347M Raws/CPUTime=3.22604 Raws/WallTime=3.22584 WallTime,s=0.309996
2K4A9929.CR2/threads:8/real_time               309 ms        309 ms          2 CPUTime,s=0.30943 CPUTime/WallTime=0.999987 Pixels=12.4416M Pixels/CPUTime=40.2081M Pixels/WallTime=40.2076M Raws/CPUTime=3.23175 Raws/WallTime=3.23171 WallTime,s=0.309434
2K4A9929.CR2/threads:8/real_time_mean          309 ms        309 ms          2 CPUTime,s=0.308628 CPUTime/WallTime=0.999962 Pixels=12.4416M Pixels/CPUTime=40.3136M Pixels/WallTime=40.3121M Raws/CPUTime=3.24023 Raws/WallTime=3.24011 WallTime,s=0.308639
2K4A9929.CR2/threads:8/real_time_median        309 ms        309 ms          2 CPUTime,s=0.30943 CPUTime/WallTime=0.999961 Pixels=12.4416M Pixels/CPUTime=40.2081M Pixels/WallTime=40.2076M Raws/CPUTime=3.23175 Raws/WallTime=3.23171 WallTime,s=0.309434
2K4A9929.CR2/threads:8/real_time_stddev          2 ms          2 ms          2 CPUTime,s=1.88354m CPUTime/WallTime=23.7788u Pixels=0 Pixels/CPUTime=246.821k Pixels/WallTime=246.914k Raws/CPUTime=0.0198384 Raws/WallTime=0.0198458 WallTime,s=1.88442m
RUNNING: /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench --benchmark_repetitions=3 2K4A9927.CR2 2K4A9928.CR2 2K4A9929.CR2 --benchmark_out=/tmp/tmpRShmmf
2018-09-12 20:23:55
Running /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
  L1 Data 16K (x8)
  L1 Instruction 64K (x4)
  L2 Unified 2048K (x4)
  L3 Unified 8192K (x1)
-----------------------------------------------------------------------------------------------
Benchmark                                        Time           CPU Iterations UserCounters...
-----------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time               446 ms        446 ms          2 CPUTime,s=0.445589 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=118.19M Pixels/WallTime=118.19M Raws/CPUTime=2.24422 Raws/WallTime=2.24422 WallTime,s=0.445589
2K4A9927.CR2/threads:8/real_time               446 ms        446 ms          2 CPUTime,s=0.446008 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=118.079M Pixels/WallTime=118.08M Raws/CPUTime=2.24211 Raws/WallTime=2.24213 WallTime,s=0.446005
2K4A9927.CR2/threads:8/real_time               448 ms        448 ms          2 CPUTime,s=0.447763 CPUTime/WallTime=0.999994 Pixels=52.6643M Pixels/CPUTime=117.616M Pixels/WallTime=117.616M Raws/CPUTime=2.23332 Raws/WallTime=2.23331 WallTime,s=0.447766
2K4A9927.CR2/threads:8/real_time_mean          446 ms        446 ms          2 CPUTime,s=0.446453 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=117.962M Pixels/WallTime=117.962M Raws/CPUTime=2.23988 Raws/WallTime=2.23989 WallTime,s=0.446453
2K4A9927.CR2/threads:8/real_time_median        446 ms        446 ms          2 CPUTime,s=0.446008 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=118.079M Pixels/WallTime=118.08M Raws/CPUTime=2.24211 Raws/WallTime=2.24213 WallTime,s=0.446005
2K4A9927.CR2/threads:8/real_time_stddev          1 ms          1 ms          2 CPUTime,s=1.15367m CPUTime/WallTime=6.48501u Pixels=0 Pixels/CPUTime=304.437k Pixels/WallTime=305.025k Raws/CPUTime=5.7807m Raws/WallTime=5.79188m WallTime,s=1.15591m
2K4A9928.CR2/threads:8/real_time               561 ms        561 ms          1 CPUTime,s=0.560856 CPUTime/WallTime=0.999996 Pixels=27.9936M Pixels/CPUTime=49.9123M Pixels/WallTime=49.9121M Raws/CPUTime=1.78299 Raws/WallTime=1.78298 WallTime,s=0.560858
2K4A9928.CR2/threads:8/real_time               560 ms        560 ms          1 CPUTime,s=0.560023 CPUTime/WallTime=1.00001 Pixels=27.9936M Pixels/CPUTime=49.9865M Pixels/WallTime=49.9872M Raws/CPUTime=1.78564 Raws/WallTime=1.78567 WallTime,s=0.560015
2K4A9928.CR2/threads:8/real_time               562 ms        562 ms          1 CPUTime,s=0.562337 CPUTime/WallTime=0.999994 Pixels=27.9936M Pixels/CPUTime=49.7808M Pixels/WallTime=49.7805M Raws/CPUTime=1.77829 Raws/WallTime=1.77828 WallTime,s=0.56234
2K4A9928.CR2/threads:8/real_time_mean          561 ms        561 ms          1 CPUTime,s=0.561072 CPUTime/WallTime=1 Pixels=27.9936M Pixels/CPUTime=49.8932M Pixels/WallTime=49.8933M Raws/CPUTime=1.78231 Raws/WallTime=1.78231 WallTime,s=0.561071
2K4A9928.CR2/threads:8/real_time_median        561 ms        561 ms          1 CPUTime,s=0.560856 CPUTime/WallTime=0.999996 Pixels=27.9936M Pixels/CPUTime=49.9123M Pixels/WallTime=49.9121M Raws/CPUTime=1.78299 Raws/WallTime=1.78298 WallTime,s=0.560858
2K4A9928.CR2/threads:8/real_time_stddev          1 ms          1 ms          1 CPUTime,s=1.17202m CPUTime/WallTime=10.7929u Pixels=0 Pixels/CPUTime=104.164k Pixels/WallTime=104.612k Raws/CPUTime=3.721m Raws/WallTime=3.73701m WallTime,s=1.17706m
2K4A9929.CR2/threads:8/real_time               305 ms        305 ms          2 CPUTime,s=0.305436 CPUTime/WallTime=0.999926 Pixels=12.4416M Pixels/CPUTime=40.7339M Pixels/WallTime=40.7309M Raws/CPUTime=3.27401 Raws/WallTime=3.27376 WallTime,s=0.305459
2K4A9929.CR2/threads:8/real_time               306 ms        306 ms          2 CPUTime,s=0.30576 CPUTime/WallTime=0.999999 Pixels=12.4416M Pixels/CPUTime=40.6908M Pixels/WallTime=40.6908M Raws/CPUTime=3.27054 Raws/WallTime=3.27054 WallTime,s=0.30576
2K4A9929.CR2/threads:8/real_time               307 ms        307 ms          2 CPUTime,s=0.30724 CPUTime/WallTime=0.999991 Pixels=12.4416M Pixels/CPUTime=40.4947M Pixels/WallTime=40.4944M Raws/CPUTime=3.25478 Raws/WallTime=3.25475 WallTime,s=0.307243
2K4A9929.CR2/threads:8/real_time_mean          306 ms        306 ms          2 CPUTime,s=0.306145 CPUTime/WallTime=0.999972 Pixels=12.4416M Pixels/CPUTime=40.6398M Pixels/WallTime=40.6387M Raws/CPUTime=3.26645 Raws/WallTime=3.26635 WallTime,s=0.306154
2K4A9929.CR2/threads:8/real_time_median        306 ms        306 ms          2 CPUTime,s=0.30576 CPUTime/WallTime=0.999991 Pixels=12.4416M Pixels/CPUTime=40.6908M Pixels/WallTime=40.6908M Raws/CPUTime=3.27054 Raws/WallTime=3.27054 WallTime,s=0.30576
2K4A9929.CR2/threads:8/real_time_stddev          1 ms          1 ms          2 CPUTime,s=961.851u CPUTime/WallTime=40.2708u Pixels=0 Pixels/CPUTime=127.481k Pixels/WallTime=126.577k Raws/CPUTime=0.0102463 Raws/WallTime=0.0101737 WallTime,s=955.105u
Comparing /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench to /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench
Benchmark                                                 Time             CPU      Time Old      Time New       CPU Old       CPU New
--------------------------------------------------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time                       -0.0038         -0.0038           447           446           447           446
2K4A9927.CR2/threads:8/real_time                       +0.0031         +0.0031           444           446           444           446
2K4A9927.CR2/threads:8/real_time                       -0.0031         -0.0031           447           446           447           446
2K4A9927.CR2/threads:8/real_time_pvalue                 0.6428          0.6428      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9927.CR2/threads:8/real_time_mean                  +0.0006         +0.0006           446           446           446           446
2K4A9927.CR2/threads:8/real_time_median                -0.0022         -0.0022           447           446           447           446
2K4A9927.CR2/threads:8/real_time_stddev                -0.3161         -0.3175             2             1             2             1
2K4A9928.CR2/threads:8/real_time                       -0.0031         -0.0029           563           561           563           561
2K4A9928.CR2/threads:8/real_time                       -0.0009         -0.0008           561           561           561           561
2K4A9928.CR2/threads:8/real_time                       -0.0169         -0.0168           570           561           570           561
2K4A9928.CR2/threads:8/real_time_pvalue                 0.0636          0.0636      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9928.CR2/threads:8/real_time_mean                  -0.0066         -0.0065           565           561           565           561
2K4A9928.CR2/threads:8/real_time_median                -0.0031         -0.0029           563           561           563           561
2K4A9928.CR2/threads:8/real_time_stddev                -0.7620         -0.7630             5             1             5             1
2K4A9929.CR2/threads:8/real_time                       -0.0034         -0.0034           306           305           306           305
2K4A9929.CR2/threads:8/real_time                       -0.0146         -0.0146           310           305           310           305
2K4A9929.CR2/threads:8/real_time                       -0.0128         -0.0129           309           305           309           305
2K4A9929.CR2/threads:8/real_time_pvalue                 0.0636          0.0636      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9929.CR2/threads:8/real_time_mean                  -0.0081         -0.0080           309           306           309           306
2K4A9929.CR2/threads:8/real_time_median                -0.0119         -0.0119           309           306           309           306
2K4A9929.CR2/threads:8/real_time_stddev                -0.4931         -0.4894             2             1             2             1
$ ~/src/googlebenchmark/tools/compare.py -a benchmarks ~/rawspeed/build-{0,1}/src/utilities/rsbench/rsbench --benchmark_repetitions=3 *
RUNNING: /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench --benchmark_repetitions=3 2K4A9927.CR2 2K4A9928.CR2 2K4A9929.CR2 --benchmark_display_aggregates_only=true --benchmark_out=/tmp/tmpjrD2I0
2018-09-12 20:24:11
Running /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
  L1 Data 16K (x8)
  L1 Instruction 64K (x4)
  L2 Unified 2048K (x4)
  L3 Unified 8192K (x1)
-----------------------------------------------------------------------------------------------
Benchmark                                        Time           CPU Iterations UserCounters...
-----------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time_mean          446 ms        446 ms          2 CPUTime,s=0.446077 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=118.061M Pixels/WallTime=118.062M Raws/CPUTime=2.24177 Raws/WallTime=2.24178 WallTime,s=0.446076
2K4A9927.CR2/threads:8/real_time_median        446 ms        446 ms          2 CPUTime,s=0.445676 CPUTime/WallTime=1 Pixels=52.6643M Pixels/CPUTime=118.167M Pixels/WallTime=118.168M Raws/CPUTime=2.24378 Raws/WallTime=2.2438 WallTime,s=0.445673
2K4A9927.CR2/threads:8/real_time_stddev          1 ms          1 ms          2 CPUTime,s=820.275u CPUTime/WallTime=3.51513u Pixels=0 Pixels/CPUTime=216.876k Pixels/WallTime=217.229k Raws/CPUTime=4.11809m Raws/WallTime=4.12478m WallTime,s=821.607u
2K4A9928.CR2/threads:8/real_time_mean          562 ms        562 ms          1 CPUTime,s=0.561843 CPUTime/WallTime=0.999983 Pixels=27.9936M Pixels/CPUTime=49.8247M Pixels/WallTime=49.8238M Raws/CPUTime=1.77986 Raws/WallTime=1.77983 WallTime,s=0.561852
2K4A9928.CR2/threads:8/real_time_median        562 ms        562 ms          1 CPUTime,s=0.561745 CPUTime/WallTime=0.999995 Pixels=27.9936M Pixels/CPUTime=49.8333M Pixels/WallTime=49.8307M Raws/CPUTime=1.78017 Raws/WallTime=1.78008 WallTime,s=0.561774
2K4A9928.CR2/threads:8/real_time_stddev          1 ms          1 ms          1 CPUTime,s=788.58u CPUTime/WallTime=30.2578u Pixels=0 Pixels/CPUTime=69.914k Pixels/WallTime=69.4978k Raws/CPUTime=2.4975m Raws/WallTime=2.48263m WallTime,s=783.873u
2K4A9929.CR2/threads:8/real_time_mean          306 ms        306 ms          2 CPUTime,s=0.305718 CPUTime/WallTime=1.00001 Pixels=12.4416M Pixels/CPUTime=40.6964M Pixels/WallTime=40.6967M Raws/CPUTime=3.271 Raws/WallTime=3.27102 WallTime,s=0.305716
2K4A9929.CR2/threads:8/real_time_median        306 ms        306 ms          2 CPUTime,s=0.305737 CPUTime/WallTime=1 Pixels=12.4416M Pixels/CPUTime=40.6939M Pixels/WallTime=40.6945M Raws/CPUTime=3.27079 Raws/WallTime=3.27084 WallTime,s=0.305732
2K4A9929.CR2/threads:8/real_time_stddev          1 ms          1 ms          2 CPUTime,s=584.969u CPUTime/WallTime=7.87539u Pixels=0 Pixels/CPUTime=77.8769k Pixels/WallTime=77.9118k Raws/CPUTime=6.2594m Raws/WallTime=6.2622m WallTime,s=585.232u
RUNNING: /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench --benchmark_repetitions=3 2K4A9927.CR2 2K4A9928.CR2 2K4A9929.CR2 --benchmark_display_aggregates_only=true --benchmark_out=/tmp/tmpN9Xhk2
2018-09-12 20:24:18
Running /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
  L1 Data 16K (x8)
  L1 Instruction 64K (x4)
  L2 Unified 2048K (x4)
  L3 Unified 8192K (x1)
-----------------------------------------------------------------------------------------------
Benchmark                                        Time           CPU Iterations UserCounters...
-----------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time_mean          446 ms        446 ms          2 CPUTime,s=0.445771 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=118.142M Pixels/WallTime=118.143M Raws/CPUTime=2.2433 Raws/WallTime=2.24332 WallTime,s=0.445769
2K4A9927.CR2/threads:8/real_time_median        446 ms        446 ms          2 CPUTime,s=0.445719 CPUTime/WallTime=1.00001 Pixels=52.6643M Pixels/CPUTime=118.156M Pixels/WallTime=118.156M Raws/CPUTime=2.24356 Raws/WallTime=2.24358 WallTime,s=0.445717
2K4A9927.CR2/threads:8/real_time_stddev          0 ms          0 ms          2 CPUTime,s=184.23u CPUTime/WallTime=1.69441u Pixels=0 Pixels/CPUTime=48.8185k Pixels/WallTime=49.0086k Raws/CPUTime=926.975u Raws/WallTime=930.585u WallTime,s=184.946u
2K4A9928.CR2/threads:8/real_time_mean          562 ms        562 ms          1 CPUTime,s=0.562071 CPUTime/WallTime=0.999969 Pixels=27.9936M Pixels/CPUTime=49.8045M Pixels/WallTime=49.803M Raws/CPUTime=1.77914 Raws/WallTime=1.77908 WallTime,s=0.562088
2K4A9928.CR2/threads:8/real_time_median        562 ms        562 ms          1 CPUTime,s=0.56237 CPUTime/WallTime=0.999986 Pixels=27.9936M Pixels/CPUTime=49.7779M Pixels/WallTime=49.7772M Raws/CPUTime=1.77819 Raws/WallTime=1.77816 WallTime,s=0.562378
2K4A9928.CR2/threads:8/real_time_stddev          1 ms          1 ms          1 CPUTime,s=967.38u CPUTime/WallTime=35.0024u Pixels=0 Pixels/CPUTime=85.7806k Pixels/WallTime=84.0545k Raws/CPUTime=3.06429m Raws/WallTime=3.00263m WallTime,s=947.993u
2K4A9929.CR2/threads:8/real_time_mean          307 ms        307 ms          2 CPUTime,s=0.306511 CPUTime/WallTime=0.999995 Pixels=12.4416M Pixels/CPUTime=40.5924M Pixels/WallTime=40.5922M Raws/CPUTime=3.26264 Raws/WallTime=3.26262 WallTime,s=0.306513
2K4A9929.CR2/threads:8/real_time_median        306 ms        306 ms          2 CPUTime,s=0.306169 CPUTime/WallTime=0.999999 Pixels=12.4416M Pixels/CPUTime=40.6364M Pixels/WallTime=40.637M Raws/CPUTime=3.26618 Raws/WallTime=3.26622 WallTime,s=0.306164
2K4A9929.CR2/threads:8/real_time_stddev          2 ms          2 ms          2 CPUTime,s=2.25763m CPUTime/WallTime=21.4306u Pixels=0 Pixels/CPUTime=298.503k Pixels/WallTime=299.126k Raws/CPUTime=0.0239924 Raws/WallTime=0.0240424 WallTime,s=2.26242m
Comparing /home/lebedevri/rawspeed/build-0/src/utilities/rsbench/rsbench to /home/lebedevri/rawspeed/build-1/src/utilities/rsbench/rsbench
Benchmark                                                 Time             CPU      Time Old      Time New       CPU Old       CPU New
--------------------------------------------------------------------------------------------------------------------------------------
2K4A9927.CR2/threads:8/real_time_pvalue                 0.6428          0.6428      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9927.CR2/threads:8/real_time_mean                  -0.0007         -0.0007           446           446           446           446
2K4A9927.CR2/threads:8/real_time_median                +0.0001         +0.0001           446           446           446           446
2K4A9927.CR2/threads:8/real_time_stddev                -0.7746         -0.7749             1             0             1             0
2K4A9928.CR2/threads:8/real_time_pvalue                 0.0636          0.0636      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9928.CR2/threads:8/real_time_mean                  +0.0004         +0.0004           562           562           562           562
2K4A9928.CR2/threads:8/real_time_median                +0.0011         +0.0011           562           562           562           562
2K4A9928.CR2/threads:8/real_time_stddev                +0.2091         +0.2270             1             1             1             1
2K4A9929.CR2/threads:8/real_time_pvalue                 0.0636          0.0636      U Test, Repetitions: 3. WARNING: Results unreliable! 9+ repetitions recommended.
2K4A9929.CR2/threads:8/real_time_mean                  +0.0026         +0.0026           306           307           306           307
2K4A9929.CR2/threads:8/real_time_median                +0.0014         +0.0014           306           306           306           306
2K4A9929.CR2/threads:8/real_time_stddev                +2.8652         +2.8585             1             2             1             2
```
2018-09-17 11:59:39 +03:00
Roman Lebedev
1b44120cd1
Un-deprecate [SG]et{Item,Byte}sProcessed, re-implement as custom counters. (#676)
As discussed with @dominichamon and @dbabokin, sugar is nice.
Well, maybe not for the health, but it's sweet.
Alright, enough puns.

A special care needs to be applied not to break csv reporter. UGH.
We end up shedding some code over this.
We no longer specially pretty-print them, they are printed just like the rest of custom counters.

Fixes #627.
2018-09-13 22:03:47 +03:00
Roman Lebedev
58588476ce
Track two more details about runs - the aggregate name, and run name. (#675)
This is related to @BaaMeow's work in https://github.com/google/benchmark/pull/616 but is not based on it.

Two new fields are tracked, and dumped into JSON:
* If the run is an aggregate, the aggregate's name is stored.
  It can be RMS, BigO, mean, median, stddev, or any custom stat name.
* The aggregate-name-less run name is additionally stored.
  I.e. not some name of the benchmark function, but the actual
  name, but without the 'aggregate name' suffix.

This way one can group/filter all the runs,
and filter by the particular aggregate type.

I *might* need this for further tooling improvement.
Or maybe not.
But this is certainly worthwhile for custom tooling.
2018-09-13 15:08:15 +03:00
Roman Lebedev
c614dfc0d4
*Display* aggregates only. (#665)
There is a flag 
d9cab612e4/src/benchmark.cc (L75-L78)
and a call
d9cab612e4/include/benchmark/benchmark.h (L837-L840)
But that affects everything, every reporter, destination:
d9cab612e4/src/benchmark.cc (L316)


It would be quite useful to have an ability to be more picky.


More specifically, i would like to be able to only see the aggregates in the on-screen output,
but for the file output to still contain everything. The former is useful in case of a lot of repetition
(or even more so if every iteration is reported separately), while the former is **great** for tooling.

Fixes https://github.com/google/benchmark/issues/664
2018-09-12 16:26:17 +03:00
Roman Lebedev
f274c503e1 Backport LLVM's r341717 "Fix flags used to compile benchmark library with clang-cl" (#673)
`MSVC` is true for clang-cl, but `"${CMAKE_CXX_COMPILER_ID}" STREQUAL
"MSVC"` is false, so we would enable -Wall, which means -Weverything
with clang-cl, and we get tons of undesired warnings.

Use the simpler condition to fix things.

Patch by: Reid Kleckner @rnk
2018-09-10 16:30:40 -04:00
Roman Lebedev
f0901417c8 GetCacheSizesMacOSX(): use consistent types. (#667)
I have absolutely no way to test this, but this looks obviously-good.

This was reported by Tim Northover @TNorthover in
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20180903/584223.html

> I think this breaks some 32-bit configurations (well, mine at least).
> I was using Clang (from Xcode 10 beta) on macOS and got a bunch of
> errors referencing sysinfo.cc:292 and onwards:

> /Users/tim/llvm/llvm-project/llvm/utils/benchmark/src/sysinfo.cc:292:47:
> error: non-constant-expression cannot be narrowed from type
> 'std::__1::array<unsigned long long, 4>::value_type' (aka 'unsigned
> long long') to 'size_t' (aka 'unsigned long') in initializer list
> [-Wc++11-narrowing]
>   } Cases[] = {{"hw.l1dcachesize", "Data", 1, CacheCounts[1]},
>                                               ^~~~~~~~~~~~~~
>
> The same happens when self-hosting ToT. Unfortunately I couldn't
> reproduce the issue on Debian (Clang 6.0.1) even with libc++; I'm not
> sure what the difference is.
2018-09-05 12:20:18 +01:00
Roman Lebedev
a7ed76ad78 Travis-ci: attempt to add 32-bit osx xcode build (#669)
Maybe will show https://github.com/google/benchmark/pull/667
or maybe this is completely wrong.
2018-09-05 12:19:54 +01:00
Changming Sun
305ba313be Pass name by const-reference instead of by value in class Statistics' constructor (#668) 2018-09-04 23:46:40 +03:00
pseyfert
fbfc495d7f add missing closing bracket in --help message (#666) 2018-09-03 19:45:09 +03:00
Roman Lebedev
5159967520
Mark Set{Items,Bytes}Processed()/{items,bytes}_processed() as deprecated. (#654)
They are basically proto-version of custom user counters.
It does not seem that they do anything that custom user counters
don't do. And having two similar entities is not good for generalization.

Migration plan:
* ```
  SetItemsProcessed(<val>)
    =>
  state.counters.insert({
    {"<Name>", benchmark::Counter(<val>, benchmark::Counter::kIsRate)},
    ...
  });
  ```
* ```
  SetBytesProcessed(<val>)
    =>
  state.counters.insert({
    {"<Name>", benchmark::Counter(<val>, benchmark::Counter::kIsRate,
                                  benchmark::Counter::OneK::kIs1024)},
    ...
  });
  ```
* ```
  <Name>_processed()
    =>
  state.counters["<Name>"]
  ```

One thing the custom user counters miss is better support
for units of measurement.

Refs. https://github.com/google/benchmark/issues/627
2018-08-30 11:59:50 +03:00