aboutsummaryrefslogtreecommitdiffhomepage
path: root/Eigen/src/Core/arch/NEON
Commit message (Collapse)AuthorAge
* Disable fast psqrt for NEON.Gravatar Antonio Sanchez2021-02-23
| | | | | | | Accuracy is too poor - requires at least two Newton iterations, but then it is no longer significantly faster than `vsqrt`. Fixes #2094.
* Updated pfrexp implementation.Gravatar Antonio Sanchez2021-02-17
| | | | | | The original implementation fails for 0, denormals, inf, and NaN. See #2150
* missing method in packetmath.h void ptranspose(PacketBlock<Packet16uc, 4>& ↵Gravatar Ashutosh Sharma2021-02-16
| | | | kernel)
* Use vrsqrts for rsqrt Newton iterations.Gravatar Antonio Sanchez2021-02-11
| | | | | It's slightly faster and slightly more accurate, allowing our current packetmath tests to pass for sqrt with a single iteration.
* loop less ptransposeGravatar Ashutosh Sharma2021-02-10
|
* Fix excessive GEBP register spilling for 32-bit NEON.Gravatar Antonio Sanchez2021-02-03
| | | | | | | | | | | | | | | | | | | | | Clang does a poor job of optimizing the GEBP microkernel on 32-bit ARM, leading to excessive 16-byte register spills, slowing down basic f32 matrix multiplication by approx 50%. By specializing `gebp_traits`, we can eliminate the register spills. Volatile inline ASM both acts as a barrier to prevent reordering and enforces strict register use. In a simple f32 matrix multiply example, this modification reduces 16-byte spills from 109 instances to zero, leading to a 1.5x speed increase (search for `16-byte Spill` in the assembly in https://godbolt.org/z/chsPbE). This is a replacement of !379. See there for further discussion. Also moved `gebp_traits` specializations for NEON to `Eigen/src/Core/arch/NEON/GeneralBlockPanelKernel.h` to be alongside other NEON-specific code. Fixes #2138.
* Fix pfrexp/pldexp for half.Gravatar Antonio Sanchez2021-01-21
| | | | | | | | | | The recent addition of vectorized pow (!330) relies on `pfrexp` and `pldexp`. This was missing for `Eigen::half` and `Eigen::bfloat16`. Adding tests for these packet ops also exposed an issue with handling negative values in `pfrexp`, returning an incorrect exponent. Added the missing implementations, corrected the exponent in `pfrexp1`, and added `packetmath` tests.
* 1)provide a better generic paddsub op implementationGravatar Guoqiang QI2021-01-13
| | | | | 2)make paddsub op support the Packet2cf/Packet4f/Packet2f in NEON 3)make paddsub op support the Packet2cf/Packet4f in SSE
* * Add iterative psqrt<double> for AVX and SSE when FMA is available. This ↵Gravatar Rasmus Munk Larsen2020-12-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | provides a ~10% speedup. * Write iterative sqrt explicitly in terms of pmadd. This gives up to 7% speedup for psqrt<float> with AVX & SSE with FMA. * Remove iterative psqrt<double> for NEON, because the initial rsqrt apprimation is not accurate enough for convergence in 2 Newton-Raphson steps and with 3 steps, just calling the builtin sqrt insn is faster. The following benchmarks were compiled with clang "-O2 -fast-math -mfma" and with and without -mavx. AVX+FMA (float) name old cpu/op new cpu/op delta BM_eigen_sqrt_float/1 1.08ns ± 0% 1.09ns ± 1% ~ BM_eigen_sqrt_float/8 2.07ns ± 0% 2.08ns ± 1% ~ BM_eigen_sqrt_float/64 12.4ns ± 0% 12.4ns ± 1% ~ BM_eigen_sqrt_float/512 95.7ns ± 0% 95.5ns ± 0% ~ BM_eigen_sqrt_float/4k 776ns ± 0% 763ns ± 0% -1.67% BM_eigen_sqrt_float/32k 6.57µs ± 1% 6.13µs ± 0% -6.69% BM_eigen_sqrt_float/256k 83.7µs ± 3% 83.3µs ± 2% ~ BM_eigen_sqrt_float/1M 335µs ± 2% 332µs ± 2% ~ SSE+FMA (float) name old cpu/op new cpu/op delta BM_eigen_sqrt_float/1 1.08ns ± 0% 1.09ns ± 0% ~ BM_eigen_sqrt_float/8 2.07ns ± 0% 2.06ns ± 0% ~ BM_eigen_sqrt_float/64 12.4ns ± 0% 12.4ns ± 1% ~ BM_eigen_sqrt_float/512 95.7ns ± 0% 96.3ns ± 4% ~ BM_eigen_sqrt_float/4k 774ns ± 0% 763ns ± 0% -1.50% BM_eigen_sqrt_float/32k 6.58µs ± 2% 6.11µs ± 0% -7.06% BM_eigen_sqrt_float/256k 82.7µs ± 1% 82.6µs ± 1% ~ BM_eigen_sqrt_float/1M 330µs ± 1% 329µs ± 2% ~ SSE+FMA (double) BM_eigen_sqrt_double/1 1.63ns ± 0% 1.63ns ± 0% ~ BM_eigen_sqrt_double/8 6.51ns ± 0% 6.08ns ± 0% -6.68% BM_eigen_sqrt_double/64 52.1ns ± 0% 46.5ns ± 1% -10.65% BM_eigen_sqrt_double/512 417ns ± 0% 374ns ± 1% -10.29% BM_eigen_sqrt_double/4k 3.33µs ± 0% 2.97µs ± 1% -11.00% BM_eigen_sqrt_double/32k 26.7µs ± 0% 23.7µs ± 0% -11.07% BM_eigen_sqrt_double/256k 213µs ± 0% 206µs ± 1% -3.31% BM_eigen_sqrt_double/1M 862µs ± 0% 870µs ± 2% +0.96% AVX+FMA (double) name old cpu/op new cpu/op delta BM_eigen_sqrt_double/1 1.63ns ± 0% 1.63ns ± 0% ~ BM_eigen_sqrt_double/8 6.51ns ± 0% 6.06ns ± 0% -6.95% BM_eigen_sqrt_double/64 52.1ns ± 0% 46.5ns ± 1% -10.80% BM_eigen_sqrt_double/512 417ns ± 0% 373ns ± 1% -10.59% BM_eigen_sqrt_double/4k 3.33µs ± 0% 2.97µs ± 1% -10.79% BM_eigen_sqrt_double/32k 26.7µs ± 0% 23.8µs ± 0% -10.94% BM_eigen_sqrt_double/256k 214µs ± 0% 208µs ± 2% -2.76% BM_eigen_sqrt_double/1M 866µs ± 3% 923µs ± 7% ~
* Add an additional step of Newton-Raphson for `psqrt<double>` on Arm, which ↵Gravatar Rasmus Munk Larsen2020-12-15
| | | | otherwise has an error of ~1000 ulps.
* Fix NEON pmax<PropagateNumbers,Packet4bf>.Gravatar Antonio Sanchez2020-12-11
| | | | Simple typo, the max impl called pmin instead of pmax for floats.
* Don't guard psqrt for std::complex<float> with EIGEN_ARCH_ARM64Gravatar David Tellenbach2020-12-11
|
* Add Armv8 guard on PropagateNumbers implementation.Gravatar Everton Constantino2020-12-10
|
* Fix vectorization of complex sqrt on NEONGravatar David Tellenbach2020-12-10
|
* Remove comma at end of enumerator list in NEON PacketMathGravatar David Tellenbach2020-12-10
|
* - Enabling PropagateNaN and PropagateNumbers for NEON.Gravatar Everton Constantino2020-12-08
| | | | - Adding propagate tests to bfloat16.
* Special function implementations for half/bfloat16 packets.Gravatar Antonio Sanchez2020-12-04
| | | | | | | | | | | | | Current implementations fail to consider half-float packets, only half-float scalars. Added specializations for packets on AVX, AVX512 and NEON. Added tests to `special_packetmath`. The current `special_functions` tests would fail for half and bfloat16 due to lack of precision. The NEON tests also fail with precision issues and due to different handling of `sqrt(inf)`, so special functions bessel, ndtri have been disabled. Tested with AVX, AVX512.
* Fix typo in `F32MaskToBf16Mask`.Gravatar Antonio Sanchez2020-12-02
|
* Fix neon cmp* functions for bf16.Gravatar Antonio Sanchez2020-12-02
| | | | | | | | | | | The current impl corrupts the comparison masks when converting from float back to bfloat16. The resulting masks are then no longer all zeros or all ones, which breaks when used with `pselect` (e.g. in `pmin<PropagateNumbers>`). This was causing `packetmath_15` to fail on arm. Introducing a simple `F32MaskToBf16Mask` corrects this (takes the lower 16-bits for each float mask).
* Fixes duplicate symbol when building blasGravatar Antonio Sanchez2020-11-20
| | | | | | | Missing inline breaks blas, since symbol generated in `complex_single.cpp`, `complex_double.cpp`, `single.cpp`, `double.cpp` Changed rest of inlines to `EIGEN_STRONG_INLINE`.
* Re-enable Arm Neon Eigen::half packets of size 8Gravatar David Tellenbach2020-11-18
| | | | | | - Add predux_half_dowto4 - Remove explicit casts in Half.h to match the behaviour of BFloat16.h - Enable more packetmath tests for Eigen::half
* Avoid promotion of Arm __fp16 to float in Neon PacketMathGravatar David Tellenbach2020-11-17
| | | | | | Using overloaded arithmetic operators for Arm __fp16 always causes a promotion to float. We replace operator* by vmulh_f16 to avoid this.
* Unify Inverse_SSE.h and Inverse_NEON.h into a single generic implementation ↵Gravatar Guoqiang QI2020-11-17
| | | | using PacketMath.
* Fix typo in NEON/PacketMath.hGravatar guoqiangqi2020-11-13
|
* Add support for Armv8.2-a __fp16Gravatar David Tellenbach2020-10-28
| | | | | | | | | | | | | | | Armv8.2-a provides a native half-precision floating point (__fp16 aka. float16_t). This patch introduces * __fp16 as underlying type of Eigen::half if this type is available * the packet types Packet4hf and Packet8hf representing float16x4_t and float16x8_t respectively * packet-math for the above packets with corresponding scalar type Eigen::half The packet-math functionality has been implemented by Ashutosh Sharma <ashutosh.sharma@amperecomputing.com>. This closes #1940.
* Clean up packetmath tests and fix various bugs to make bfloat16 pass ↵Gravatar Rasmus Munk Larsen2020-10-09
| | | | (almost) all packetmath tests with SSE, AVX, and AVX512.
* Fix undefined reference to pset1frombits bug on different platformsGravatar guoqiangqi2020-09-19
|
* Fix more mildly embarrassing typos in ARM intrinsics in PacketMath.h.Gravatar Rasmus Munk Larsen2020-09-18
| | | 'vmvnq_u64' does not exist for some reason.
* Fix typo in PacketMath.hGravatar Rasmus Munk Larsen2020-09-18
|
* Add missing packet op pcmp_lt_or_nan for Packet2d on ARM.Gravatar Rasmus Munk Larsen2020-09-18
|
* Add support for CastXML on ARM aarch64Gravatar Brad King2020-09-16
| | | | | | | | CastXML simulates the preprocessors of other compilers, but actually parses the translation unit with an internal Clang compiler. Use the same `vld1q_u64` workaround that we do for Clang. Fixes: #1979
* Remove old Clang compiler bug work-arounds. The two LLVM bugs referenced in ↵Gravatar Benoit Jacob2020-09-15
| | | | the comments here have long been fixed. The workarounds were now detrimental because (1) they prevented using fused mul-add on Clang/ARM32 and (2) the unnecessary 'volatile' in 'asm volatile' prevented legitimate reordering by the compiler.
* Add plog ops support packet2d for NEONGravatar Guoqiang QI2020-09-15
|
* Add Neon psqrt<Packet2d> and pexp<Packet2d>Gravatar Guoqiang QI2020-09-08
|
* add psqrt ops support packet2f/packet4f for NEONGravatar Guoqiang QI2020-08-21
|
* bfloat16 packetmath for Arm Neon backendGravatar David Tellenbach2020-08-13
|
* Temporarily turn off the NEON implementation of pfloor as it does not work ↵Gravatar Zachary Garrett2020-08-04
| | | | | | for large values. The NEON implementation mimics the SSE implementation, but didn't mention the caveat that due to the unsigned of signed integer conversions, not all values in the original floating point represented are supported.
* Fix packetmath_1 float tests for arm/aarch64.Gravatar Antonio Sanchez2020-06-24
| | | | | | | | | | | | | | | | | | | Added missing `pmadd<Packet2f>` for NEON. This leads to significant improvement in precision than previous `pmul+padd`, which was causing the `pcos` tests to fail. Also added an approx test with `std::sin`/`std::cos` since otherwise returning any `a^2+b^2=1` would pass. Modified `log(denorm)` tests. Denorms are not always supported by all systems (returns `::min`), are always flushed to zero on 32-bit arm, and configurably flush to zero on sse/avx/aarch64. This leads to inconsistent results across different systems (i.e. `-inf` vs `nan`). Added a check for existence and exclude ARM. Removed logistic exactness test, since scalar and vectorized versions follow different code-paths due to differences in `pexp` and `pmadd`, which result in slightly different values. For example, exactness always fails on arm, aarch64, and altivec.
* Add missing Packet2l/Packet2ul ops for NEON.Gravatar Antonio Sanchez2020-06-22
| | | | | | | | | | | | | | | | | | | | | | | | | | The current multiply (`pmul`) and comparison operators (`pcmp_lt`, `pcmp_le`, `pcmp_eq`) are missing for packets `Packet2l` and `Packet2ul`. This leads to compile errors for the `packetmath.cpp` tests in clang. Here we add and test the missing ops. Tested: ``` $ aarch64-linux-gnu-g++ -static -I./ '-DEIGEN_TEST_PART_9=1' '-DEIGEN_TEST_PART_10=1' test/packetmath.cpp -o packetmath $ adb push packetmath /data/local/tmp/ $ adb shell "/data/local/tmp/packetmath" $ arm-linux-gnueabihf-g++ -mfpu=neon -static -I./ '-DEIGEN_TEST_PART_9=1' '-DEIGEN_TEST_PART_10=1' test/packetmath.cpp -o packetmath $ adb push packetmath /data/local/tmp/ $ adb shell "/data/local/tmp/packetmath" $ clang++ -target aarch64-linux-android21 -static -I./ '-DEIGEN_TEST_PART_9=1' '-DEIGEN_TEST_PART_10=1' test/packetmath.cpp -o packetmath $ adb push packetmath /data/local/tmp/ $ adb shell "/data/local/tmp/packetmath" $ clang++ -target armv7-linux-android21 -static -mfpu=neon -I./ '-DEIGEN_TEST_PART_9=1' '-DEIGEN_TEST_PART_10=1' test/packetmath.cpp -o packetmath $ adb push packetmath /data/local/tmp/ $ adb shell "/data/local/tmp/packetmath" ```
* Added missing NEON pcasts, update packetmath tests.Gravatar Antonio Sanchez2020-06-21
| | | | | | | | | | | | | | | | | | | | | | | | | The NEON `pcast` operators are all implemented and tested for existing packets. This requires adding a `pcast(a,b,c,d,e,f,g,h)` for casting between `int64_t` and `int8_t` in `GenericPacketMath.h`. Removed incorrect `HasHalfPacket` definition for NEON's `Packet2l`/`Packet2ul`. Adjustments were also made to the `packetmath` tests. These include - minor bug fixes for cast tests (i.e. 4:1 casts, only casting for packets that are vectorizable) - added 8:1 cast tests - random number generation - original had uninteresting 0 to 0 casts for many casts between floating-point and integers, and exhibited signed overflow undefined behavior Tested: ``` $ aarch64-linux-gnu-g++ -static -I./ '-DEIGEN_TEST_PART_ALL=1' test/packetmath.cpp -o packetmath $ adb push packetmath /data/local/tmp/ $ adb shell "/data/local/tmp/packetmath" ```
* Remove HasCast and fix packetmath cast tests.Gravatar Antonio Sanchez2020-06-11
| | | | | | | | | | | The use of the `packet_traits<>::HasCast` field is currently inconsistent with `type_casting_traits<>`, and is unused apart from within `test/packetmath.cpp`. In addition, those packetmath cast tests do not currently reflect how casts are performed in practice: they ignore the `SrcCoeffRatio` and `TgtCoeffRatio` fields, assuming a 1:1 ratio. Here we remove the unsed `HasCast`, and modify the packet cast tests to better reflect their usage.
* Add support for PacketBlock<Packet8s,4> and PacketBlock<Packet16uc,4> ↵Gravatar Kan Chen2020-05-29
| | | | ptranspose on NEON
* Add missing packet ops for bool, and make it pass the same packet op unit ↵Gravatar Rasmus Munk Larsen2020-05-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tests as other arithmetic types. This change also contains a few minor cleanups: 1. Remove packet op pnot, which is not needed for anything other than pcmp_le_or_nan, which can be done in other ways. 2. Remove the "HasInsert" enum, which is no longer needed since we removed the corresponding packet ops. 3. Add faster pselect op for Packet4i when SSE4.1 is supported. Among other things, this makes the fast transposeInPlace() method available for Matrix<bool>. Run on ************** (72 X 2994 MHz CPUs); 2020-05-09T10:51:02.372347913-07:00 CPU: Intel Skylake Xeon with HyperThreading (36 cores) dL1:32KB dL2:1024KB dL3:24MB Benchmark Time(ns) CPU(ns) Iterations ----------------------------------------------------------------------- BM_TransposeInPlace<float>/4 9.77 9.77 71670320 BM_TransposeInPlace<float>/8 21.9 21.9 31929525 BM_TransposeInPlace<float>/16 66.6 66.6 10000000 BM_TransposeInPlace<float>/32 243 243 2879561 BM_TransposeInPlace<float>/59 844 844 829767 BM_TransposeInPlace<float>/64 933 933 750567 BM_TransposeInPlace<float>/128 3944 3945 177405 BM_TransposeInPlace<float>/256 16853 16853 41457 BM_TransposeInPlace<float>/512 204952 204968 3448 BM_TransposeInPlace<float>/1k 1053889 1053861 664 BM_TransposeInPlace<bool>/4 14.4 14.4 48637301 BM_TransposeInPlace<bool>/8 36.0 36.0 19370222 BM_TransposeInPlace<bool>/16 31.5 31.5 22178902 BM_TransposeInPlace<bool>/32 111 111 6272048 BM_TransposeInPlace<bool>/59 626 626 1000000 BM_TransposeInPlace<bool>/64 428 428 1632689 BM_TransposeInPlace<bool>/128 1677 1677 417377 BM_TransposeInPlace<bool>/256 7126 7126 96264 BM_TransposeInPlace<bool>/512 29021 29024 24165 BM_TransposeInPlace<bool>/1k 116321 116330 6068
* Remove packet ops pinsertfirst and pinsertlast that are only used in a ↵Gravatar Rasmus Munk Larsen2020-05-08
| | | | | | | | | | | | | | | | single place, and can be replaced by other ops when constructing the first/final packet in linspaced_op_impl::packetOp. I cannot measure any performance changes for SSE, AVX, or AVX512. name old time/op new time/op delta BM_LinSpace<float>/1 1.63ns ± 0% 1.63ns ± 0% ~ (p=0.762 n=5+5) BM_LinSpace<float>/8 4.92ns ± 3% 4.89ns ± 3% ~ (p=0.421 n=5+5) BM_LinSpace<float>/64 34.6ns ± 0% 34.6ns ± 0% ~ (p=0.841 n=5+5) BM_LinSpace<float>/512 217ns ± 0% 217ns ± 0% ~ (p=0.421 n=5+5) BM_LinSpace<float>/4k 1.68µs ± 0% 1.68µs ± 0% ~ (p=1.000 n=5+5) BM_LinSpace<float>/32k 13.3µs ± 0% 13.3µs ± 0% ~ (p=0.905 n=5+4) BM_LinSpace<float>/256k 107µs ± 0% 107µs ± 0% ~ (p=0.841 n=5+5) BM_LinSpace<float>/1M 427µs ± 0% 427µs ± 0% ~ (p=0.690 n=5+5)
* Remove unused packet op "palign".Gravatar Rasmus Munk Larsen2020-05-07
| | | | Clean up a compiler warning in c++03 mode in AVX512/Complex.h.
* Remove traits declaring NEON vectorized casts that do not actually have ↵Gravatar Rasmus Munk Larsen2020-05-07
| | | | packet op implementations.
* Remove unused packet op "preduxp".Gravatar Rasmus Munk Larsen2020-04-23
|
* Move eigen_packet_wrapper to GenericPacketMath.h and use it for ↵Gravatar Rasmus Munk Larsen2020-04-15
| | | | | | | SSE/AVX/AVX512 as it is already used for NEON. This will allow us to define multiple packet types backed by the same vector type, e.g., __m128i. Use this machanism to define packets for half and clean up the packet op implementations.
* Fix typo in TypeCasting.hGravatar Rasmus Munk Larsen2020-04-14
|
* Fix big in vectorized casting ofGravatar Rasmus Munk Larsen2020-04-14
| | | | | | {uint8, int8} -> {int16, uint16, int32, uint32, float} {uint16, int16} -> {int32, uint32, int64, uint64, float} for NEON. These conversions were advertised as vectorized, but not actually implemented.
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-09 16:57:18 +0000