Xavier Arteaga
06a9d8eb6f
Added vector estimate frequency
2019-04-30 14:52:16 +02:00
Andre Puschmann
4b01a2e4a0
update copyright notice
2019-04-29 09:20:02 +02:00
yagoda
69dc16c4c8
changes to fix arm compilation
2018-11-27 14:27:59 +01:00
Xavier Arteaga
8c3a0153b9
Added missing AVX512 intrinsics and flags. Fixes #291 .
2018-11-21 18:09:09 +01:00
Andre Puschmann
d981f129e0
Merge branch 'master' into next
2018-09-20 12:54:05 +02:00
IgnasJ
67c8bf1368
Fixes for srsLTE on ARM ( #229 )
...
* Fix ARM NEON code compilation
Fix LV_HAVE_NEON defintion incorrecly used instead of HAVE_NEON in some places
Replace vqabsq_s32 with vabsq_f32 as vqabsq_s32 requires int type (fails to compile)
Fix missing NEON code path in mat.h in srslte_mat_2x2_mmse_csi_simd()
* Fix timestamp overflow issue on 32-bit systems with Soapy driver
'time_t secs' can be 32-bit on some systems. This causes calculation:
'secs * 1000000000;' to overflow.
2018-09-19 17:34:59 +02:00
Ismael Gomez
bc9d342959
New optimization on the PHY for both UE and eNodeB ( #251 )
...
* New parallel Turbodecoder implementation in SSE/AVX 16-bit and 8-bit
* Optimised UL Interleaver
* Include TB CRC calculation in FEC encoder
* New threading priorities
2018-09-04 17:51:35 +02:00
Xavier Arteaga
f01f7b4945
Added Vector max abs SIMD function
2018-06-28 09:28:17 +02:00
Xavier Arteaga
681b98ae50
Added vector CFO
2018-05-25 16:06:32 +02:00
Xavier Arteaga
0bc3be7abb
Added DL CSI decoding to TM2 and TM3
2018-04-20 11:27:39 +02:00
Andre Puschmann
e7a268d79b
fix SIMD compile issue on NEON
2018-04-04 12:20:32 +02:00
David Rupprecht
9d71bec7b6
Unified include guards
2018-03-31 19:04:04 +02:00
Xavier Arteaga
ec901373d4
Correction ofo simd.h for AVX512
2018-03-01 14:01:36 +01:00
Xavier Arteaga
6fc9c96c58
Added CSI softbits weightening for Single antenna transmission
2018-02-28 12:07:31 +01:00
Xavier Arteaga
c4247c7aca
Fix coverity for complex 16bit
2018-01-31 10:44:52 +01:00
Ismael Gomez
821d5595c5
Fixed AVX compilation
2017-12-20 12:35:28 +01:00
Ismael Gomez
a3a1d268b7
Improved CFO estimation/correction by filtering central 6 PRB. Cleaned ue_sync/sync/pss objects. Used const attr in vector and other objects
2017-11-29 18:30:21 +01:00
yagoda
38903de07c
adding simd xor functionality
2017-11-27 11:10:50 +00:00
Xavier Arteaga
91e706d4d1
Fixes #107 : srslte_simd_f_sqrt NaN solved if input is 0
2017-11-22 12:23:46 +01:00
yagoda
3292f9c269
simd.h tidy up & small fix for eMBMS
2017-10-19 16:38:58 +00:00
Xavier Arteaga
0504e7a51b
Fixed test for abs value. Solved compilation Neon warnings and SSE errors
2017-10-18 12:49:43 +02:00
yagoda
f4b9e7311a
adding neon support to new vector structure
2017-10-17 15:51:27 +00:00
yagoda
2019ca31ef
adding neon support for new kernel structure
2017-10-13 15:35:48 +01:00
Xavier Arteaga
1a5cf45dda
Solved compilation error for SSE (Tested in Atom)
2017-10-09 16:30:32 +02:00
Xavier Arteaga
94a06867a3
Optimized SIMD includes and solved AVX512 bugs
2017-09-29 16:42:46 +02:00
Xavier Arteaga
9e5f999666
Added more functions
2017-09-28 11:04:26 +02:00
Xavier Arteaga
c41ad5453c
Solved bugs and compilation error in simd and vector_simd
2017-09-25 17:08:11 +02:00
Xavier Arteaga
1c3b5552be
added c16 type and architecture independent inline SIMD calls
2017-09-25 13:15:59 +02:00
Xavier Arteaga
d933f1b817
Renamed module algebra (it is now named mat) and moved usefl math SIMD macros to simd.h
2017-08-31 12:24:26 +02:00