summaryrefslogtreecommitdiff
path: root/volk
Commit message (Collapse)AuthorAgeFilesLines
...
* volk: make orc a normal arch with overruleJosh Blum2012-04-195-24/+20
|
* volk: added compile utils and cleanup cmakelistsJosh Blum2012-04-1912-412/+179
|
* volk: working build w/ cmakelistsJosh Blum2012-04-199-146/+60
|
* volk: created other templates for runtime + machinesJosh Blum2012-04-1910-7/+336
|
* volk: added kernel defs and typedefsJosh Blum2012-04-196-7/+361
|
* volk: work on template stuffJosh Blum2012-04-197-4/+439
|
* Merge branch 'maint'Johnathan Corgan2012-04-192-15/+34
|\
| * volk: gcc version check without __GNUC_PREREQJosh Blum2012-04-181-1/+1
| |
| * volk: added xgetbv stuff from volk_work to maintJosh Blum2012-04-182-15/+34
| | | | | | | | | | | | This ensures that the compiler has support for xgetbv. This also fixes MSVC by checking for _xgetbv. Also, restored copy of cpuid.h, this should not be modified.
* | Merge branch 'maint'Johnathan Corgan2012-04-163-11/+48
|\| | | | | | | | | Conflicts: volk/gen/make_cpuid_c.py
| * Volk: also check to make sure OSXSAVE is enabled so you don't check XGETBV ↵Nick Foster2012-04-162-1/+8
| | | | | | | | when OS has it disabled.
| * Volk: add support for checking AVX enable state of OS.Nick Foster2012-04-163-12/+42
| | | | | | | | Some systems (notably Xen hypervisor) appear to use XSETBV to disable AVX. This causes SIGILL when running AVX instructions. This commit makes Volk check XCR0 on the AVX arch before proceeding.
* | Removed whitespace and added dtools/bin/remove-whitespace as a tool to do ↵Tom Rondeau2012-04-13140-1385/+1385
| | | | | | | | | | | | this in the future. The sed script was provided by Moritz Fischer.
* | Merge branch 'master' into nextJohnathan Corgan2012-03-223-5/+13
|\|
| * volk: fix for load prefs (config path)Josh Blum2012-03-221-1/+9
| | | | | | | | | | 1) add APPDATA to search path for windows 2) graceful fail and env vars not defined
| * volk: add include for config.h to cc fileJosh Blum2012-03-212-4/+4
| | | | | | | | | | | | | | volk_32f_s32f_convert_16i_a was also a problem, previously volk_32f_s32f_convert_16i_u was fixed to have config.h. I heard putting config h stuff into public headers was bad practice. Including config.h into the generated cc file should fix this issue from now on.
* | Merge branch 'master' into nextTom Rondeau2012-03-191-1/+1
|\| | | | | | | | | Conflicts: volk/config/orc.m4
| * volk: change minimum acceptable ORC version to 4.12 (in cmake and updating ↵Tom Rondeau2012-03-192-2/+2
| | | | | | | | version in autotools).
* | Merge branch 'master' into nextTom Rondeau2012-03-153-13/+9
|\|
| * Merge branch 'volk_32bit_fixes_maint' into maintTom Rondeau2012-03-153-13/+9
| |\
| | * volk: turning off sse implementation of complex dot product for 32-bit ↵Tom Rondeau2012-03-151-7/+5
| | | | | | | | | | | | machines until it's fixed.
| | * volk: makes the float-to-int conversion consistent and fixes an overflow bug ↵Tom Rondeau2012-03-152-6/+4
| | | | | | | | | | | | | | | | | | on 32-bit machines. Not currently used in GNU Radio, so no change in behavior there.
* | | Merge branch 'master' into nextJohnathan Corgan2012-03-151-12/+10
|\| |
| * | volk: set local includes first for precedenceJosh Blum2012-03-151-12/+10
| |/
| * volk: include config.h to have rintf in windows/msvc.Tom Rondeau2012-03-031-0/+4
| |
* | volk: include config.h to have rintf in windows/msvc.Tom Rondeau2012-03-031-0/+4
| |
* | Merge branch 'master' into nextJohnathan Corgan2012-03-0128-76/+1631
|\| | | | | | | | | | | | | | | | | | | | | | | Conflicts: config/grc_volk.m4 gnuradio-core/src/guile/tests/gengen_ctors.test gnuradio-core/src/lib/Makefile.am gnuradio-core/src/lib/general/.gitignore gnuradio-core/src/lib/general/Makefile.am gnuradio-core/src/lib/gengen/.gitignore gnuradio-core/src/python/gnuradio/gr/Makefile.am volk/include/volk/Makefile.am
| * volk: float to short conversion is consistent between archs and tail cases. ↵Tom Rondeau2012-02-232-14/+16
| | | | | | | | Rounds to nearest number.
| * Merge remote branch 'bistromath/volk_fix' into safe_alignTom Rondeau2012-02-234-21/+35
| |\ | | | | | | | | | | | | Conflicts: volk/apps/volk_profile.cc
| | * Remove ORC invocation since // doesn't dissuade the generator.Nick Foster2012-02-221-14/+0
| | |
| | * Volk: add scalar const support to the profiler/QA code. Disabled ↵Nick Foster2012-02-214-10/+37
| | | | | | | | | | | | volk_32fc_s32fc_multiply_32fc_a's Orc impl due to it not working.
| * | build: fix autotools for gnuradio-core volkificationJohnathan Corgan2012-02-141-2/+2
| | |
| * | Merge branch 'master' into safe_alignJohnathan Corgan2012-02-141-2/+3
| |\| | | | | | | | | | | | | | | | Conflicts: gnuradio-core/src/lib/filter/gr_fft_filter_ccc.cc gnuradio-core/src/lib/filter/gr_fft_filter_fff.cc
| * | volk: adding complex conjugate kernel.Tom Rondeau2012-02-135-1/+136
| | |
| * | volk: fixed complex multiply and conjugate kernel to use xor for conjugation.Tom Rondeau2012-02-132-4/+3
| | |
| * | volk: added a 32fc multiply conjugate kernel.Tom Rondeau2012-02-135-0/+169
| | |
| * | volk: added unaligned version of adding 2 vectors.Tom Rondeau2012-02-134-0/+69
| | |
| * | volk: new unaligned versions of float multipliers.Tom Rondeau2012-02-136-14/+231
| | |
| * | core: moving multiply_const_ff from gengen to general to take advantage of volk.Tom Rondeau2012-02-133-6/+82
| | | | | | | | | | | | Also adds SSE and AVX and unaligned Volk versions for this.
| * | volk: adding new functions to Makefile.Tom Rondeau2012-02-021-0/+2
| | |
| * | volk: adding new Volk functions added in this branch to the volk_profile ↵Tom Rondeau2012-02-022-0/+13
| | | | | | | | | | | | tool and installing it into $prefix/bin.
| * | volk: improving performance of multiply_const and multiply two streams.Tom Rondeau2012-02-023-3/+106
| | |
| * | volk: adding unaligned versions of complex multiply a constant and complex ↵Tom Rondeau2012-02-022-0/+119
| | | | | | | | | | | | multiply 2 streams.
| * | volk: adding complex to imag kernel.Tom Rondeau2012-01-302-0/+69
| | |
| * | volk: added volk magnitiude squared functions (aligned/unaligned) for ↵Tom Rondeau2012-01-293-0/+231
| | | | | | | | | | | | complex numbers.
| * | volk: added unaligned volk function for magnitude of a complex number.Tom Rondeau2012-01-291-0/+118
| | |
| * | volk: fix lower bound of int conversion.Tom Rondeau2012-01-281-2/+2
| | |
| * | volk: float_to_int and float_to_char updated to clip instead of wrap around. ↵Tom Rondeau2012-01-264-28/+183
| | | | | | | | | | | | The float to int clips at smaller than 2^32 because of the limits of the float representation.
| * | volk: fix a warning.Tom Rondeau2012-01-261-3/+5
| | |
| * | volk: float_to_short now clips the values instead of wrapping around.Tom Rondeau2012-01-262-14/+90
| | |