Searched refs:speedup (Results 1 – 25 of 45) sorted by relevance
12
| /external/toolchain-utils/deprecated/ |
| D | compare_benchmarks.py | 156 speedup = (basestats[key] - stats[key]) / basestats[key]
157 speedup = speedup * 100.0
159 print('%s,%f,%f,%f' % (key, basestats[key], stats[key], speedup))
162 stats[key], speedup))
|
| /external/v8/tools/perf/ |
| D | statistics-for-json.R | 96 speedup <- ggplot(df2, aes(x = x, y = E, colour=p.value.sig)) + globalVar
110 print(speedup)
112 plot=speedup, width=7, height=7)
|
| /external/zlib/src/contrib/asm686/ |
| D | README.686 | 8 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/ |
| D | performance.txt | 33 gives about 40% speedup on artificial programs which just do
34 realloc() and nothing else, and about a 3-4% speedup on starting
|
| D | 3_8_BUGSTATUS.txt | 352 318030 addHRegUse takes a lot of CPU time; band-aid speedup
|
| /external/bison/lib/ |
| D | strchrnul.valgrind | 2 # This use is OK because it provides only a speedup.
|
| D | rawmemchr.valgrind | 2 # This use is OK because it provides only a speedup.
|
| D | memchr.valgrind | 4 # implement strnlen). However, we use a safe word read to provide a speedup.
|
| /external/valgrind/perf/ |
| D | vg_perf | 384 my $speedup = 100 - (100 * $tTool / $first_tTool{$tool});
385 printf("%5.1f%%)", $speedup);
|
| D | vg_perf.in | 384 my $speedup = 100 - (100 * $tTool / $first_tTool{$tool});
385 printf("%5.1f%%)", $speedup);
|
| /external/mesa3d/src/gallium/docs/source/drivers/ |
| D | openswr.rst | 6 geometry heavy workloads there is a considerable speedup over llvmpipe,
|
| /external/sonic/samples/ |
| D | README | 33 useful for making sure the flush function works correctly. A 2-X speedup should
|
| /external/clang/docs/ |
| D | SanitizerSpecialCaseList.rst | 22 * speedup hot function, which is known to be correct;
|
| /external/mesa3d/docs/relnotes/ |
| D | 3.1 | 120 It's impossible to give a speedup factor. You'll just have to
|
| /external/harfbuzz_ng/ |
| D | NEWS | 266 - Minor speedup.
311 with HarfBuzz >= 1.1.2. This results in a tiny speedup.
884 - Major speedup in OpenType lookup processing. With the Amiri
886 release. All scripts / languages should see this speedup.
1214 - Major optimization and speedup.
|
| /external/libmtp/ |
| D | TODO | 81 speedup caches.
|
| /external/eigen/doc/ |
| D | SparseLinearSystems.dox | 56 <td>To speedup the convergence, try it with the \ref IncompleteLUT preconditioner.</td></tr>
158 …his step. Remember that, basically, the goal of the preconditioner is to speedup the convergence o…
|
| /external/libvncserver/ |
| D | NEWS | 77 speedup on 64-bit architechtures.
|
| /external/libvncserver/webclients/java-applet/ssl/ |
| D | README | 174 This is to speedup/make more robust, the single port HTTPS and VNC
|
| /external/tagsoup/ |
| D | CHANGES | 5 Leo Sutic's 2x-4x speedup by precompiling HTMLScanner table
|
| /external/gemmlowp/doc/ |
| D | less-than-8-bit.txt | 148 we still get quite close to a 2x speedup. See internal/kernel_neon.h,
|
| D | less-than-8-bit.md | 173 speedup. See internal/kernel_neon.h, specifically
|
| /external/swiftshader/docs/ |
| D | Reactor.md | 35 …ribution of specialization for a single parameter is small, the combined speedup can be huge. As a…
|
| /external/libxml2/ |
| D | NEWS | 1247 - improvement: speedup parsing comments and DTDs, dictionary 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
|
| /external/kmod/ |
| D | NEWS | 537 - Indexes can be loaded on startup to speedup lookups later
|
12