Home
last modified time | relevance | path

Searched refs:speedup (Results 1 – 25 of 35) sorted by relevance

12

/external/opencv3/samples/gpu/performance/
Dperformance.cpp67 double speedup = static_cast<double>(cpu_elapsed_) / std::max(1.0, gpu_elapsed_); in finishCurrentSubtest() local
68 speedup_total_ += speedup; in finishCurrentSubtest()
70 printMetrics(cpu_time, gpu_time, speedup); in finishCurrentSubtest()
107 void TestSystem::printMetrics(double cpu_time, double gpu_time, double speedup) in printMetrics() argument
120 stream << "x" << setprecision(3) << speedup; in printMetrics()
Dperformance.h118 void printMetrics(double cpu_time, double gpu_time, double speedup);
/external/opencv3/modules/ts/misc/
Dxls-report.py357 speedup = cmp_from / cmp_to
358 sheet.write(row, col, speedup, good_speedup_style if speedup > 1.1 else
359 bad_speedup_style if speedup < 0.9 else
/external/zlib/src/contrib/asm686/
DREADME.6868 The speedup that this patch provides varies, depending on whether the
10 PPro's speed traps. My own tests show a speedup of around 10-20% at
/external/valgrind/docs/internals/
Dperformance.txt33 gives about 40% speedup on artificial programs which just do
34 realloc() and nothing else, and about a 3-4% speedup on starting
D3_8_BUGSTATUS.txt352 318030 addHRegUse takes a lot of CPU time; band-aid speedup
/external/bison/lib/
Dstrchrnul.valgrind2 # This use is OK because it provides only a speedup.
Drawmemchr.valgrind2 # This use is OK because it provides only a speedup.
Dmemchr.valgrind4 # implement strnlen). However, we use a safe word read to provide a speedup.
/external/opencv3/modules/flann/include/opencv2/flann/
Dautotuned_index.h496 float speedup = 0; in estimateSearchParams() local
547 speedup = linear / searchTime; in estimateSearchParams()
553 return speedup; in estimateSearchParams()
/external/mesa3d/docs/
DREADME.MITS45 to be done the extra overhead outweighs any speedup from using
46 dual processors. You will not for example see any speedup when
DRELNOTES-3.1120 It's impossible to give a speedup factor. You'll just have to
/external/valgrind/perf/
Dvg_perf.in378 my $speedup = 100 - (100 * $tTool / $first_tTool{$tool});
379 printf("%5.1f%%)", $speedup);
/external/chromium-trace/catapult/third_party/gsutil/third_party/rsa/
DCHANGELOG.txt16 - Massive speedup
/external/sonic/samples/
DREADME33 useful for making sure the flush function works correctly. A 2-X speedup should
/external/clang/docs/
DSanitizerSpecialCaseList.rst22 * speedup hot function, which is known to be correct;
/external/opencv3/doc/py_tutorials/py_imgproc/py_contours/py_contours_more_functions/
Dpy_contours_more_functions.markdown79 time consuming process. So, making it False gives about 2-3X speedup.
/external/harfbuzz_ng/
DNEWS116 - Minor speedup.
161 with HarfBuzz >= 1.1.2. This results in a tiny speedup.
734 - Major speedup in OpenType lookup processing. With the Amiri
736 release. All scripts / languages should see this speedup.
1064 - Major optimization and speedup.
/external/libmtp/
DTODO80 speedup caches.
/external/eigen/doc/
DSparseLinearSystems.dox26 <td>To speedup the convergence, try it with the \ref IncompleteLUT preconditioner.</td></tr>
121 …his step. Remember that, basically, the goal of the preconditioner is to speedup the convergence o…
/external/libvncserver/
DNEWS77 speedup on 64-bit architechtures.
/external/libvncserver/webclients/java-applet/ssl/
DREADME174 This is to speedup/make more robust, the single port HTTPS and VNC
/external/tagsoup/
DCHANGES5 Leo Sutic's 2x-4x speedup by precompiling HTMLScanner table
/external/opencv3/doc/py_tutorials/py_imgproc/py_transforms/py_fourier_transform/
Dpy_fourier_transform.markdown218 It shows a 4x speedup. Now we will try the same with OpenCV functions.
/external/libxml2/
DNEWS1247 - improvement: speedup parsing comments and DTDs, dictionnary support for
1271 (William), xmlUTF8Strpos speedup (William), unicode Python strings
1672 - a lot of profiling and tuning of the code, speedup patch for
1752 - Performances: removed excessive malloc() calls, speedup of the push and
1833 drv_libxml2.py Python xml.sax driver (Stéphane Bidoul), fixes, speedup
1987 - speedup patch to XPath very effective for DocBook stylesheets
2600 - Integrated various patches, especially a speedup improvement for large

12