| /aosp_15_r20/hardware/google/gfxstream/third-party/glm/include/glm/gtx/ |
| D | fast_exponential.hpp | 28 /// Faster than the common pow function but less accurate.
33 /// Faster than the common pow function but less accurate.
38 /// Faster than the common pow function but less accurate.
43 /// Faster than the common pow function but less accurate.
48 /// Faster than the common exp function but less accurate.
53 /// Faster than the common exp function but less accurate.
58 /// Faster than the common log function but less accurate.
63 /// Faster than the common exp2 function but less accurate.
68 /// Faster than the common exp2 function but less accurate.
73 /// Faster than the common exp2 function but less accurate.
[all …]
|
| D | fast_square_root.hpp | 31 /// Faster than the common sqrt function but less accurate.
37 /// Faster than the common sqrt function but less accurate.
43 /// Faster than the common inversesqrt function but less accurate.
49 /// Faster than the common inversesqrt function but less accurate.
55 /// Faster than the common length function but less accurate.
61 /// Faster than the common length function but less accurate.
67 /// Faster than the common distance function but less accurate.
73 /// Faster than the common distance function but less accurate.
79 /// Faster than the common normalize function but less accurate.
|
| D | fast_trigonometry.hpp | 32 /// Faster than the common sin function but less accurate.
37 /// Faster than the common cos function but less accurate.
42 /// Faster than the common tan function but less accurate.
48 /// Faster than the common asin function but less accurate.
54 /// Faster than the common acos function but less accurate.
60 /// Faster than the common atan function but less accurate.
66 /// Faster than the common atan function but less accurate.
|
| /aosp_15_r20/external/oboe/samples/RhythmGame/third_party/glm/gtx/ |
| H A D | fast_exponential.hpp | 28 /// Faster than the common pow function but less accurate.
33 /// Faster than the common pow function but less accurate.
38 /// Faster than the common pow function but less accurate.
43 /// Faster than the common pow function but less accurate.
48 /// Faster than the common exp function but less accurate.
53 /// Faster than the common exp function but less accurate.
58 /// Faster than the common log function but less accurate.
63 /// Faster than the common exp2 function but less accurate.
68 /// Faster than the common exp2 function but less accurate.
73 /// Faster than the common exp2 function but less accurate.
[all …]
|
| H A D | fast_square_root.hpp | 31 /// Faster than the common sqrt function but less accurate.
37 /// Faster than the common sqrt function but less accurate.
43 /// Faster than the common inversesqrt function but less accurate.
49 /// Faster than the common inversesqrt function but less accurate.
55 /// Faster than the common length function but less accurate.
61 /// Faster than the common length function but less accurate.
67 /// Faster than the common distance function but less accurate.
73 /// Faster than the common distance function but less accurate.
79 /// Faster than the common normalize function but less accurate.
|
| H A D | fast_trigonometry.hpp | 32 /// Faster than the common sin function but less accurate.
37 /// Faster than the common cos function but less accurate.
42 /// Faster than the common tan function but less accurate.
48 /// Faster than the common asin function but less accurate.
54 /// Faster than the common acos function but less accurate.
60 /// Faster than the common atan function but less accurate.
66 /// Faster than the common atan function but less accurate.
|
| /aosp_15_r20/external/python/pyasn1/pyasn1/type/ |
| D | char.py | 171 # Optimization for faster codec lookup
186 # Optimization for faster codec lookup
201 # Optimization for faster codec lookup
208 # Optimization for faster codec lookup
223 # Optimization for faster codec lookup
238 # Optimization for faster codec lookup
253 # Optimization for faster codec lookup
268 # Optimization for faster codec lookup
275 # Optimization for faster codec lookup
289 # Optimization for faster codec lookup
[all …]
|
| /aosp_15_r20/external/zstd/ |
| H A D | CHANGELOG | 58 perf: +20% faster huffman decompression for targets that can't compile x64 assembly (#3449, @terrel…
59 perf: up to +10% faster streaming compression at levels 1-2 (#3114, @embg)
62 perf: +5-30% faster dictionary compression at levels 1-4 (#3086, #3114, #3152, @embg)
64 perf: +1% faster compression by removing a branch in ZSTD_fast_noDict (#3129, @felixhandte)
124 perf: faster huffman decoder, using x64 assembly, by @terrelln
125 perf: slightly faster high speed modes (strategies fast & dfast), by @felixhandte
126 perf: improved binary size and faster compilation times, by @terrelln
128 perf: faster mid-level compression speed in presence of highly repetitive patterns, by @senhuang42
131 perf: faster compression speed on incompressible data, by @bindhvo
228 perf: faster dictionary compression at medium compression levels, by @felixhandte
[all …]
|
| /aosp_15_r20/external/libaom/ |
| H A D | CHANGELOG | 10 * Faster quality ramp-up for static content after scene change
194 resolutions <= VGA: ~30% faster than speed 10.
408 faster encoding with ~3% bdrate loss with 16% IC (instruction count)
632 o Improve av1_quantize_fp_32x32_neon() 1.05x to 1.24x faster
634 faster than "C"
635 o Improve av1_quantize_fp_64x64_neon() 1.17x to 1.66x faster
636 o Add aom_quantize_b_avx2() 1.4x to 1.7x faster than aom_quantize_b_avx()
637 o Add aom_quantize_b_32x32_avx2() 1.4x to 2.3x faster than
639 o Add aom_quantize_b_64x64_avx2() 2.0x to 2.4x faster than
641 o Add aom_highbd_quantize_b_32x32_avx2() 9.0x to 10.5x faster than
[all …]
|
| /aosp_15_r20/external/webp/ |
| H A D | ChangeLog | 616 01b38ee1 faster CollectColorXXXTransforms_SSE41
620 fae41617 faster CombinedShannonEntropy_SSE2
1278 5cfd4ebc LZ77 interval speedups. Faster, smaller, simpler.
1345 0d55f60c 40% faster ApplyAlphaMultiply_SSE2
1347 48b1e85f SSE2: 15% faster alpha-processing functions
1349 28fe054e SSE2: 30% faster ApplyAlphaMultiply()
1357 00b08c88 Merge "NEON: 5% faster conversion to RGB565 and RGBA4444"
1358 0e7f4447 Merge "NEON: faster fancy upsampling"
1359 b016cb91 NEON: faster fancy upsampling
1364 341d711c NEON: 5% faster conversion to RGB565 and RGBA4444
[all …]
|
| /aosp_15_r20/external/cronet/third_party/rust/chromium_crates_io/vendor/regex-1.10.4/ |
| H A D | README.md | 236 * When given the choice between faster regex searches and faster _Rust compile
237 times_, this crate will generally choose faster regex searches.
238 * When given the choice between faster regex searches and faster _regex compile
239 times_, this crate will generally choose faster regex searches. That is, it is
241 searches get faster. (This is a somewhat delicate balance to strike, because
244 * When given the choice between faster regex searches and simpler API
245 design, this crate will generally choose faster regex searches. For example,
|
| /aosp_15_r20/external/lz4/ |
| H A D | NEWS | 11 lib : Slightly faster (+5%) HC compression speed (levels 3-9), by @JunHe77
26 perf : faster decoding speed (~+20%) on aarch64 platforms
27 perf : faster decoding speed (~+70%) for -BD4 setting in CLI
49 perf: faster speed with Visual Studio, thanks to @wolfpld and @remittor
112 perf: *much* faster dictionary compression on small files, by @felixhandte
114 perf: slightly faster HC compression and decompression speed
124 perf : faster and stronger ultra modes (levels 10+)
125 perf : slightly faster compression and decompression speed
177 Makefile: Generates object files (*.o) for faster (re)compilation on low power systems
|
| /aosp_15_r20/external/libvpx/ |
| H A D | CHANGELOG | 401 is about 10-20% faster than speed 8.
444 Faster VP9 encoding and decoding.
493 Faster VP9 encoding and decoding
508 Faster VP9 encoding and decoding
660 faster (ARM) depending on the number of threads and bitrate
719 same content at different resolutions faster than encoding them
772 Our third named release, focused on a faster, higher quality, encoder.
797 telephony content is 35% faster than Bali on single core and 48%
798 faster on multi-core. On the NVidia Tegra2 platform, real time
799 encoding is 40% faster than Bali.
[all …]
|
| /aosp_15_r20/external/cronet/build/android/incremental_install/ |
| H A D | README.md | 32 Faster Builds:
36 * Apks sign faster because they are smaller.
38 Faster Installs:
40 * The .apk is smaller, and so faster to verify.
50 * DexOpt results are cached, so subsequent runs are faster.
|
| /aosp_15_r20/external/angle/build/android/incremental_install/ |
| H A D | README.md | 32 Faster Builds:
36 * Apks sign faster because they are smaller.
38 Faster Installs:
40 * The .apk is smaller, and so faster to verify.
50 * DexOpt results are cached, so subsequent runs are faster.
|
| /aosp_15_r20/external/toybox/www/ |
| H A D | design.html | 89 I wouldn't have to say this, and yet. Trying to find a faster sorting
101 <p>Understand the difference between throughput and latency. Faster
120 but it's just as true that a loop which stays in L1 cache is many times faster
122 about whether "&" is faster than "%" until your executable loop stays in L1
167 is faster than read() because it avoids a copy, but twiddling with the memory
171 blocks waiting for), the read can be many times faster. On the other hand, the
173 comes from the page cache (allocated anyway), and it can be faster if you're
177 on underneath is a big help to making it happen faster.)</p>
182 faster because processors were so slow. Then processors got faster and grew
183 math coprocessors, and calculating the value each time became faster than
[all …]
|
| /aosp_15_r20/external/cronet/base/third_party/cityhash/ |
| H A D | README | 19 and hardware, it's likely faster than CityHash64() on sufficiently long
48 (CityHashCrc256 in v1.0.3 was even faster, but we decided it wasn't as thorough
56 faster on AMD x86-64 CPUs. For hashing long strings on AMD CPUs
63 For short strings, e.g., most hash table keys, CityHash64 is faster than
64 CityHash128, and probably faster than all the aforementioned functions,
84 We don't know of anything faster that has comparable quality. The speed rankings
|
| H A D | city.h | 29 // For 64-bit x86 code, on short strings, we don't know of anything faster than
36 // CityHashCrc128 appears to be faster than all competitors of comparable
40 // faster than CityHash on some relatively recent AMD x86-64 CPUs, for example.
43 // For 32-bit x86 code, we don't know of anything faster than CityHash32 that
45 // (On 64-bit CPUs, it is typically faster to use the other CityHash variants.)
|
| /aosp_15_r20/external/libevent/ |
| H A D | whatsnew-2.1.txt | 524 2.2. Faster activations and timeouts
569 The EVBUFFER_EOL_CRLF line-ending type is now much faster, thanks to
583 has approximately the resolution corresponding to epoll, and is much faster
596 code run a little faster on change-heavy loads.
608 significantly faster and more accurate than our old ftime()-based approach.
638 3.6. Faster cross-thread notification on kqueue
646 thread from kqueue. This should be a tiny bit faster than the
651 4.1. Faster tests
653 I've spent some time to try to make the unit tests run faster in
663 Faster unit tests are great, since they let programmers test their
|
| /aosp_15_r20/external/python/cpython3/Doc/whatsnew/ |
| D | 3.11.rst | 62 * Python 3.11 is between 10-60% faster than Python 3.10.
64 See :ref:`whatsnew311-faster-cpython` for details.
504 but it is slightly faster for long inputs.
1262 :ref:`whatsnew311-faster-cpython` project, which is covered in its own section.
1271 It is now around 20% faster on x86-64 when dividing an :class:`int`
1275 * :func:`sum` is now nearly 30% faster for integers smaller than ``2**30``.
1289 * Using :class:`asyncio.DatagramProtocol` is now orders of magnitude faster
1295 ≈10 times faster for large arguments (with a larger speedup for larger *k*).
1309 .. _whatsnew311-faster-cpython:
1311 Faster CPython
[all …]
|
| /aosp_15_r20/external/pffft/ |
| H A D | fftpack.h | 193 transforms can be obtained faster than the first.
253 transforms can be obtained faster than the first.
339 transforms can be obtained faster than the first.
411 transforms can be obtained faster than the first.
487 transforms can be obtained faster than the first.
539 transforms can be obtained faster than the first.
613 transforms can be obtained faster than the first.
663 transforms can be obtained faster than the first.
736 transforms can be obtained faster than the first.
783 transforms can be obtained faster than the first.
|
| /aosp_15_r20/external/mesa3d/src/intel/isl/ |
| H A D | isl_tiled_memcpy.c | 1011 * Copy texture data from linear to X tile layout, faster.
1013 * Same as \ref linear_to_xtiled but faster, because it passes constant
1056 * Copy texture data from linear to Y tile layout, faster.
1058 * Same as \ref linear_to_ytiled but faster, because it passes constant
1100 * Copy texture data from linear to tile 4 layout, faster.
1102 * Same as \ref linear_to_tile4 but faster, because it passes constant
1143 * Copy texture data from X tile layout to linear, faster.
1145 * Same as \ref xtile_to_linear but faster, because it passes constant
1199 * Copy texture data from Y tile layout to linear, faster.
1201 * Same as \ref ytile_to_linear but faster, because it passes constant
[all …]
|
| /aosp_15_r20/external/tensorflow/tensorflow/lite/g3doc/performance/ |
| H A D | best_practices.md | 14 also generally faster and more energy efficient. For example, graphs below show
52 write a faster version of a custom op if you know the constraints in which the
58 Model optimization aims to create smaller models that are generally faster and
86 the Java API is a lot faster if `ByteBuffers` are used as
101 TensorFlow Lite has added new ways to accelerate models with faster hardware
|
| /aosp_15_r20/prebuilts/rust/linux-musl-x86/1.81.0/lib/rustlib/src/rust/library/core/src/slice/iter/ |
| H A D | macros.rs | 246 // faster to compile.
260 // faster to compile.
277 // faster to compile.
294 // faster to compile.
311 // faster to compile.
328 // faster to compile. Also, the `assume` avoids a bounds check.
351 // faster to compile. Also, the `assume` avoids a bounds check.
|
| /aosp_15_r20/prebuilts/rust/linux-x86/1.80.1/lib/rustlib/src/rust/library/core/src/slice/iter/ |
| H A D | macros.rs | 244 // faster to compile.
258 // faster to compile.
275 // faster to compile.
292 // faster to compile.
309 // faster to compile.
326 // faster to compile. Also, the `assume` avoids a bounds check.
349 // faster to compile. Also, the `assume` avoids a bounds check.
|