itsscb/rust
1
0
Fork 0
mirror of https://github.com/rust-lang/rust.git synced 2025-12-03 17:39:32 +00:00
Code Issues Packages Projects Releases Wiki Activity
231 Commits 10 Branches 151 Tags
Commit Graph

224 Commits

Author SHA1 Message Date
Tony Sifkarovski
60c2608cce [avx2] add _mm_256_cvtepu{8,16,32}_epi{16,32,64} (#192) 2017-11-17 09:22:18 +01:00
crypto-universe
1842e36d00 [x86][sse4.1] Add phminposuw & pmul* instructions 
pmulld is implemented via multiplication.
 2017-11-16 07:12:14 -05:00
gnzlbg
955fd849ff implement missing std::ops 2017-11-13 06:42:49 -05:00
gnzlbg
6ed424a848 syn API breaking change (#189) 2017-11-11 23:35:00 +01:00
crypto-universe
bdaea04f2b [x86][sse4.1] Add pmin* instructions (#186) 2017-11-08 23:05:27 -06:00
Caio
545a2a8e2a Add _mm_unpackhi_pd and _mm_unpacklo_pd (#184) 
* Add _mm_unpackhi_pd and _mm_unpacklo_pd
 2017-11-08 11:22:21 +01:00
gnzlbg
20324666f5 [ci] fix formatting and clippy (#182) 2017-11-07 09:00:55 -06:00
Malo Jaffré
664395e25e Fix a confusing typo in a cast name. (#179) 2017-11-06 12:45:31 -06:00
André Oliveira
a05fb1b292 Add the necessary SIMD types for sign extend intrinsics 2017-11-06 07:17:27 -05:00
André Oliveira
bab1c7b16a Avoid using simd_cast directly 2017-11-06 07:17:27 -05:00
André Oliveira
866596cd53 Add _mm_cvtepi16_epi32 and _mm_cvtepi16_epi64 (commented) 2017-11-06 07:17:27 -05:00
André Oliveira
fa240f2477 Add commented implementation of _mm_cvtepi8_epi64 2017-11-06 07:17:27 -05:00
André Oliveira
37396f3471 Add _mm_cvtepi8_epi32 
- This might be wrong since the cast and the shuffle nedded to be inverted
 2017-11-06 07:17:27 -05:00
André Oliveira
f9caf376b2 Add _mm_cvtepi8_epi16 2017-11-06 07:17:27 -05:00
André Oliveira
d6c990967b Add _mm_packus_epi32 and _mm_cmpeq_epi64 intrinsics 2017-11-06 07:17:27 -05:00
Adam Niederer
a6d9d0c100 Fix mm256_round_epi* return types (#173) 
From the Intel intrinsics manual (emphasis mine):

> Compute the absolute value of packed 16-bit integers in a, and store the
> *unsigned* results in dst.
 2017-11-05 20:56:07 -06:00
gwenn
6d4ea09a21 Avx (#172) 
* avx: _mm256_load_pd, _mm256_store_pd, _mm256_load_ps, _mm256_store_ps

* avx: _mm256_load_si256, _mm256_store_si256
 2017-11-05 20:55:32 -06:00
Malo Jaffré
74870635e5 Add SSE2 trivial aliases and conversions. (#165) 
`_mm_cvtsd_f64`, `_mm_cvtsd_si64x` and `_mm_cvttsd_si64x`.
See #40.
 2017-11-02 14:10:50 -04:00
gnzlbg
542aac988a [ci] enable clippy (#62) 
* [ci] enable clippy

* [clippy] fix clippy issues
 2017-11-02 13:43:12 -04:00
gwenn
96111d548e Avx (#163) 
* avx: _mm256_testnzc_si256

* avx: _mm256_shuffle_ps

8 levels of macro expansion takes too long to compile.

* avx: remove useless 0 in tests

* avx: _mm256_shuffle_ps

Macro expansion can be reduced to four levels

* avx: _mm256_blend_ps

Copy/paste from avx2::_mm256_blend_epi32
 2017-11-01 08:47:40 -05:00
Alex Crichton
5cb3986530 Bump to 0.0.3 2017-10-30 15:53:07 -07:00
gnzlbg
d6aefaabea [aarch64] refactor AArch64 intrinsics into its own architecture module (#162) 2017-10-29 11:37:43 -05:00
gnzlbg
7f35e50563 [runtime-detection-x86] detect avx and avx2 only if osxsave is true (#154) 2017-10-28 16:34:09 -04:00
Mrowqa
0c9ac36595 x86: implemented roundings for SSE4.1 (#158) 
* x86: implemented roundings for SSE4.1

* x86: sse41 roundings - added docs and fixed assert__* tests
 2017-10-28 16:32:14 -04:00
gnzlbg
46c6e9beb6 [fmt] use cargo fmt --all (#161) 2017-10-28 16:29:52 -04:00
gnzlbg
69d2ad85f3 [ci] check formatting (#64) 
* [ci] check formatting

* [rustfmt] reformat the whole library
 2017-10-27 11:55:29 -04:00
Mrowqa
5869eca3e9 x86: implemented _mm{,256}_maskstore_epi{32,64} (#155) 
* x86: implemented maskloads for avx2

* x86: added docs and tests for avx2 maskloads

* x86: refactor - changed `a` to `mem_addr` in avx2 mask loads for consistency

* x86: implemented _mm{,256}_maskstore_epi{32,64}
 2017-10-27 11:40:48 -04:00
Henry de Valence
1c67fc00e7 avx2: add _mm256_shuffle_epi32 reusing _mm_shuffle_epi32 code (#156) 2017-10-27 11:10:11 -04:00
gnzlbg
ad48780fca [arm] vadd, vaddd, vaddq, vaddl 2017-10-26 10:18:00 -04:00
Mrowqa
ae0688c7fa x86: fixed testing equality of floating point numbers (#150) 
* x86: fixed testing equality of floating point numbers

* x86: removed unused macro branch

* x86: marked assert_approx_eq as used only in tests
 2017-10-25 09:57:35 -04:00
gwenn
ea51cbcf25 avx: fix *si256 methods (#145) 
* avx: fix *si256 methods

* avx: _mm256_setr_m128

* avx: _mm256_setr_m128d

* avx: _mm256_setr_m128i

* avx: _mm256_loadu2_m128

* avx: _mm256_loadu2_m128d

* avx: _mm256_loadu2_m128i

* avx: _mm256_storeu2_m128

* sse2: _mm_storeu_pd

* avx: _mm256_storeu2_m128d

* sse2: _mm_undefined_si128

* avx: _mm256_storeu2_m128i

* Try to fix i586 build
 2017-10-25 01:26:19 -04:00
Henry de Valence
0f33ca5518 avx2: add _mm256_unpack{hi,lo}_epi{8,16,32,64} (#147) 2017-10-24 20:12:23 -04:00
gnzlbg
3e1e52f413 update readme and crates.io badges, categories, etc. (#141) 
* [readme] badges

* [crates.io] add badges, categories, etc.
 2017-10-23 08:37:41 -05:00
Steven Fackler
6f134c3dfa Make vector constructors const functions (#137) 2017-10-23 08:35:43 -05:00
Thomas Schilling
8b6f5d183e Add some SSE _mm_cvt* instructions (#136) 
* Add single output _mm_cvt[t]ss_* variants

The *_pi variants are currently blocked by
https://github.com/rust-lang-nursery/stdsimd/issues/74

* Add _mm_cvtsi*_ss

The _mm_cvtpi*_ps intrinsics are blocked by
https://github.com/rust-lang-nursery/stdsimd/issues/74

* Fix Linux builds

Also the si64 variants are only available on x86_64
 2017-10-23 08:35:28 -05:00
Steven Fackler
76d9b89ab2 Implement _mm256_permute4x64_epi64 (#144) 2017-10-23 08:35:03 -05:00
gnzlbg
1f44e3166e Deny all warnings and fix errors (#135) 
* [travis-ci] deny warnings

* fix all warnings
 2017-10-22 12:30:26 -05:00
gnzlbg
8fa5e7bcf5 [travis-ci] allow testing on all branches (#134) 2017-10-22 07:43:48 -05:00
jneem
192c4ac4fd avx2: signed extensions (#132) 
_mm256_cvtepi8_epi16
_mm256_cvtepi8_epi32
_mm256_cvtepi8_epi64
_mm256_cvtepi16_epi32
_mm256_cvtepi16_epi64
_mm256_cvtepi32_epi64
 2017-10-21 15:00:13 -05:00
Steven Fackler
5fb563aabc Add _mm256_shuffle_epi8 and _mm256_permutevar8x32_epi32 (#133) 
* Add _mm256_shuffle_epi8

* Add _mm256_permutevar8x32_epi32
 2017-10-21 14:59:37 -05:00
pythoneer
d5fd2b09a7 sse2 (#131) 
* added missing doc _mm_cvtps_pd
added missing doc & test _mm_load_pd
added missing doc & test _mm_store_pd
added _mm_store1_pd
added _mm_store_pd1
added _mm_storer_pd
added _mm_load_pd1
added _mm_loadr_pd
added _mm_loadu_pd

* correct alignments
 2017-10-21 10:46:55 -05:00
jneem
3ec870078a avx2: _mm256_blend_epi32 and _mm256_blend_epi16. (#130) 2017-10-18 17:29:23 -05:00
gnzlbg
a3a703d83e [example] nbody (#117) 2017-10-18 17:19:19 -05:00
Dan Robertson
4782ffadee [x86] Implement avx2 broadcast intrinsics (#97) 
Implement
 - _mm_broadcastb_epi8
 - _mm256_broadcastb_epi8
 - _mm_broadcastd_epi32
 - _mm256_broadcastd_epi32
 - _mm_bradcastq_epi64
 - _mm256_broadcastq_epi64
 - _mm_broadcastsd_pd
 - _mm256_broadcastsd_pd
 - _mm256_broadcastsi128_si256
 - _mm_broadcastss_ps
 - _mm256_broadcastss_ps
 - _mm_broadcastw_epi16
 - _mm256_broadcast2_epi16
 2017-10-18 14:36:17 -05:00
Alex Crichton
7b249298c0 Uncomment _mm256_mpsadbw_epu8 (#128) 
Just needed some `constify_imm8!` treatment

Closes #59
 2017-10-18 13:17:09 -05:00
gnzlbg
2dc965b69a [neon] reciprocal square-root estimate (#121) 2017-10-18 13:16:34 -05:00
Alex Crichton
13bc6b8517 Add CI in Intel's instruction emulator (#113) 
This commit adds a new builder on CI for running tests in Intel's own emulator
and also adds an assertion that on this emulator no tests are skipped due to
missing CPU features by accident.

Closes #92
 2017-10-18 11:35:11 -04:00
André Oliveira
02c89b24ba sse4.1 instructions (#98) 
* sse4.1: _mm_blendv_ps and _mm_blendv_pd

* sse4.1: _mm_blend_ps and _mm_blend_pd

- HACK warning: messing with the constify macros
- Selecting only one buffer gets optimized away and tests need to take this into account

* sse4.1: _mm_blend_epi16

* sse4.1: _mm_extract_ps

* sse4.1: _mm_extract_epi8

* see4.1: _mm_extract_epi32

* sse4.1: _mm_extract_epi64

* sse4.1: _mm_insert_ps

* sse4.1: _mm_insert_epi8

* sse4.1: _mm_insert_epi32 and _mm_insert_epi64

* Formmating

* sse4.1: _mm_max_epi8, _mm_max_epu16, _mm_max_epi32 and _mm_max_epu32

* Fix wrong compiler flag

- avx -> sse4.1

* Fix intrinsics that only work with x86-64

* sse4.1: use appropriate types

* Revert '_mm_extract_ps' to return i32

* sse4.1: Use the v128 types for consistency

* Try fix for windows

* Try "vectorcall" calling convention

* Revert "Try "vectorcall" calling convention"

This reverts commit 12936e9976bc6b0e4e538d82f55f0ee2d87a7f25.

* Revert "Try fix for windows"

This reverts commit 9c473808d334acedd46060b32ceea116662bf6a3.

* Change tests for windows

* Remove useless Windows test
 2017-10-18 11:34:51 -04:00
jneem
acf919f960 avx2: _mm_blend_epi32 (#127) 2017-10-17 10:16:15 -04:00
Thomas Schilling
64c7f7ec56 Add SSE _mm_store* intrinsics and _mm_move_ss (#115) 
* Add _mm_store* intrinsics and _mm_move_ss

* Fix Win64 & Linux i586 failures

* Make i586 codegen happy without breaking x86_64
 2017-10-17 10:15:37 -04:00