devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,220 Commits 15 Branches 93 Tags
6c1411e5213ed5c015e1c0f063654e9e2de99f13
Commit Graph

163 Commits

Author SHA1 Message Date
Charles Schlosser
8999525c29 AVX2: Packet4ul has pmul, abs2 2023-04-26 16:22:16 +00:00
Charles Schlosser
f6cf5dca80 Packet4ul does not have Abs2 2023-04-21 19:48:01 +00:00
Charles Schlosser
29c8e3c754 fix pow for uint32_t, disable pmul<Packet4ul> 2023-04-21 05:47:56 +00:00
Pedro Gonnet
17b5b4de58 Add Packet4ui, Packet8ui, and Packet4ul to the SSE/AVX PacketMath.h headers 2023-04-17 23:33:59 +00:00
Rasmus Munk Larsen
df1049ddf4 Small packet math cleanup. 2023-04-04 16:14:32 +00:00
Rasmus Munk Larsen
0488b708b4 Vectorize tensor.isnan() by using typed predicates. 2023-03-16 04:04:22 +00:00
Antonio Sánchez
394aabb0a3 Fix failing MSVC tests due to compiler bugs. 2023-03-10 22:36:57 +00:00
Rasmus Munk Larsen
ce62177b5b Vectorize atanh & add a missing definition and unit test for atan. 2023-02-21 03:14:05 +00:00
Sean McBride
d70b4864d9 issue #2581: review and cleanup of compiler version checks 2023-01-17 18:58:34 +00:00
Charles Schlosser
02805bd56c Fix AVX2 psignbit 2022-11-16 13:43:11 +00:00
Antonio Sánchez
8588d8c74b Correct pnegate for floating-point zero. 2022-11-15 18:07:23 +00:00
Charles Schlosser
82b152dbe7 Add signbit function 2022-11-04 00:31:20 +00:00
Rasmus Munk Larsen
c475228b28 Vectorize atan() for double. 2022-10-01 01:49:30 +00:00
Rasmus Munk Larsen
7b2901e2aa Add vectorized integer division for int32 with AVX512, AVX or SSE. 2022-09-21 00:27:23 +00:00
Rasmus Munk Larsen
f913a40678 Revert "Add AVX int32_t pdiv" 
This reverts commit ea84e7ad63
 2022-09-16 22:48:08 +00:00
Charles Schlosser
ea84e7ad63 Add AVX int32_t pdiv 2022-09-16 17:06:29 +00:00
Rasmus Munk Larsen
bd393e15c3 Vectorize acos, asin, and atan for float. 2022-08-29 19:49:33 +00:00
Charles Schlosser
e5af9f87f2 Vectorize pow for integer base / exponent types 2022-08-29 19:23:54 +00:00
Rasmus Munk Larsen
7064ed1345 Specialize psign<Packet8i> for AVX2, don't vectorize psign<bool>. 2022-08-26 17:02:37 +00:00
Rasmus Munk Larsen
1a09defce7 Protect new pblend implementation with EIGEN_VECTORIZE_AVX2 2022-08-22 18:28:03 +00:00
Matthew Sterrett
7a3b667c43 Add support for AVX512-FP16 for vectorizing half precision math 2022-08-17 18:15:21 +00:00
Ilya Tokar
e618c4a5e9 Improve pblend AVX implementation 2022-07-29 18:45:33 +00:00
Shi, Brian
fc1d888415 Remove AVX512VL dependency in trsm 2022-04-14 12:44:24 -07:00
Antonio Sánchez
07db964bde Restrict new AVX512 trsm to AVX512VL, rename files for consistency. 2022-04-14 16:58:32 +00:00
b-shi
518fc321cb AVX512 Optimizations for Triangular Solve 2022-03-16 18:04:50 +00:00
Erik Schultheis
7197b577fb Remove unused macros in AVX packetmath. 
The following macros are removed:

* EIGEN_DECLARE_CONST_Packet8f
* EIGEN_DECLARE_CONST_Packet4d
* EIGEN_DECLARE_CONST_Packet8f_FROM_INT
* EIGEN_DECLARE_CONST_Packet8i
 2022-02-14 10:34:23 +00:00
Rasmus Munk Larsen
51311ec651 Remove inline assembly for FMA (AVX) and add remaining extensions as packet ops: pmsub, pnmadd, and pnmsub. 2022-01-26 04:25:41 +00:00
Rasmus Munk Larsen
ea2c02060c Add reciprocal packet op and fast specializations for float with SSE, AVX, and AVX512. 2022-01-21 23:49:18 +00:00
Ilya Tokar
a0fc640c18 Add support for packets of int64 on x86 2022-01-21 19:55:23 +00:00
Kolja Brix
8d81a2339c Reduce usage of reserved names 2022-01-10 20:53:29 +00:00
Ilya Tokar
e1cb6369b0 Add AVX vector path to float2half/half2float 
Makes e. g. matrix multiplication 2x faster:
name         old cpu/op  new cpu/op  delta
BM_convers   181ms ± 1%    62ms ± 9%  -65.82%  (p=0.016 n=4+5)

Tested on all possible input values (not adding tests, since they
take a long time).
 2021-10-28 13:59:01 -04:00
Rasmus Munk Larsen
da027fa20a Remove unused variable. 2021-09-16 20:02:42 +00:00
Rasmus Munk Larsen
d7d0bf832d Issue an error in case of direct inclusion of internal headers. 2021-09-10 19:12:26 +00:00
Antonio Sanchez
7792b1e909 Fix AVX2 PacketMath.h. 
There were a couple typos ps -> epi32, and an unaligned load issue.
 2021-09-03 19:47:57 +00:00
Antonio Sanchez
def145547f Add missing packet types in pset1 call. 
Oops, introduced this when "fixing" integer packets.
 2021-09-02 16:21:07 -07:00
Antonio Sanchez
3d4ba855e0 Fix AVX integer packet issues. 
Most are instances of AVX2 functions not protected by
`EIGEN_VECTORIZE_AVX2`.  There was also a missing semi-colon
for AVX512.
 2021-09-01 14:14:43 -07:00
Jakub Lichman
dc5b1f7d75 AVX512 and AVX2 support for Packet16i and Packet8i added 2021-08-25 19:38:23 +00:00
Gauri Deshpande
e6a5a594a7 remove denormal flushing in fp32tobf16 for avx & avx512 2021-08-09 22:15:21 +00:00
Antonio Sanchez
0845df7f77 Fix uninitialized warning on AVX. 2021-02-17 13:13:39 -08:00
Antonio Sanchez
7ff0b7a980 Updated pfrexp implementation. 
The original implementation fails for 0, denormals, inf, and NaN.

See #2150
 2021-02-17 02:23:24 +00:00
Antonio Sanchez
4cb563a01e Fix ldexp implementations. 
The previous implementations produced garbage values if the exponent did
not fit within the exponent bits.  See #2131 for a complete discussion,
and !375 for other possible implementations.

Here we implement the 4-factor version. See `pldexp_impl` in
`GenericPacketMathFunctions.h` for a full description.

The SSE `pcmp*` methods were moved down since `pcmp_le<Packet4i>`
requires `por`.

Left as a "TODO" is to delegate to a faster version if we know the
exponent does fit within the exponent bits.

Fixes #2131.
 2021-02-10 22:45:41 +00:00
David Tellenbach
751f18f2c0 Remove comma at the end of enumeration list to silence C++03 warnings 2020-12-13 18:11:02 +01:00
Antonio Sanchez
8c9976d7f0 Fix more SSE/AVX packet conversions for peven. 
MSVC doesn't like function-style casts and forces us to use intrinsics.
 2020-12-11 15:46:42 -08:00
Rasmus Munk Larsen
125cc9a5df Implement vectorized complex square root. 
Closes #1905

Measured speedup for sqrt of `complex<float>` on Skylake:

SSE:
```
name                      old time/op             new time/op  delta
BM_eigen_sqrt_ctype/1     49.4ns ± 0%             54.3ns ± 0%  +10.01%
BM_eigen_sqrt_ctype/8      332ns ± 0%               50ns ± 1%  -84.97%
BM_eigen_sqrt_ctype/64    2.81µs ± 1%             0.38µs ± 0%  -86.49%
BM_eigen_sqrt_ctype/512   23.8µs ± 0%              3.0µs ± 0%  -87.32%
BM_eigen_sqrt_ctype/4k     202µs ± 0%               24µs ± 2%  -88.03%
BM_eigen_sqrt_ctype/32k   1.63ms ± 0%             0.19ms ± 0%  -88.18%
BM_eigen_sqrt_ctype/256k  13.0ms ± 0%              1.5ms ± 1%  -88.20%
BM_eigen_sqrt_ctype/1M    52.1ms ± 0%              6.2ms ± 0%  -88.18%
```

AVX2:
```
name                      old cpu/op  new cpu/op  delta
BM_eigen_sqrt_ctype/1     53.6ns ± 0%  55.6ns ± 0%   +3.71%
BM_eigen_sqrt_ctype/8      334ns ± 0%    27ns ± 0%  -91.86%
BM_eigen_sqrt_ctype/64    2.79µs ± 0%  0.22µs ± 2%  -92.28%
BM_eigen_sqrt_ctype/512   23.8µs ± 1%   1.7µs ± 1%  -92.81%
BM_eigen_sqrt_ctype/4k     201µs ± 0%    14µs ± 1%  -93.24%
BM_eigen_sqrt_ctype/32k   1.62ms ± 0%  0.11ms ± 1%  -93.29%
BM_eigen_sqrt_ctype/256k  13.0ms ± 0%   0.9ms ± 1%  -93.31%
BM_eigen_sqrt_ctype/1M    52.0ms ± 0%   3.5ms ± 1%  -93.31%
```

AVX512:
```
name                      old cpu/op  new cpu/op  delta
BM_eigen_sqrt_ctype/1     53.7ns ± 0%  56.2ns ± 1%   +4.75%
BM_eigen_sqrt_ctype/8      334ns ± 0%    18ns ± 2%  -94.63%
BM_eigen_sqrt_ctype/64    2.79µs ± 0%  0.12µs ± 1%  -95.54%
BM_eigen_sqrt_ctype/512   23.9µs ± 1%   1.0µs ± 1%  -95.89%
BM_eigen_sqrt_ctype/4k     202µs ± 0%     8µs ± 1%  -96.13%
BM_eigen_sqrt_ctype/32k   1.63ms ± 0%  0.06ms ± 1%  -96.15%
BM_eigen_sqrt_ctype/256k  13.0ms ± 0%   0.5ms ± 4%  -96.11%
BM_eigen_sqrt_ctype/1M    52.1ms ± 0%   2.0ms ± 1%  -96.13%
```
 2020-12-08 18:13:35 -08:00
Antonio Sanchez
e2f21465fe Special function implementations for half/bfloat16 packets. 
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.
 2020-12-04 10:16:29 -08:00
Rasmus Munk Larsen
e57281a741 Fix a few issues for AVX512. This change enables vectorized versions of log, exp, log1p, expm1 when AVX512DQ is not available. 2020-12-01 11:31:47 -08:00
Antonio Sanchez
89f90b585d AVX512 missing ops. 
This allows the `packetmath` tests to pass for AVX512 on skylake.
Made `half` and `bfloat16` consistent in terms of ops they support.

Note the `log` tests are currently disabled for `bfloat16` since
they fail due to poor precision (they were previously disabled for
`Packet8bf` via test function specialization -- I just removed that
specialization and disabled it in the generic test).
 2020-11-30 16:28:57 +00:00
Antonio Sanchez
a3b300f1af Implement missing AVX half ops. 
Minimal implementation of AVX `Eigen::half` ops to bring in line
with `bfloat16`.  Allows `packetmath_13` to pass.

Also adjusted `bfloat16` packet traits to match the supported set
of ops (e.g. Bessel is not actually implemented).
 2020-11-24 16:46:41 +00:00
Antonio Sanchez
4cf01d2cf5 Update AVX half packets, disable test. 
The AVX half implementation is incomplete, causing the `packetmath_13` test
to fail.  This disables the test.

Also refactored the existing AVX implementation to use `bit_cast`
instead of direct access to `.x`.
 2020-11-21 09:05:10 -08:00
guoqiangqi
82fe059f35 Fix issue2045 which get a error case _mm256_set_m128d op not supported by gcc 7.x 2020-11-04 09:21:39 +08:00