| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | build: Enable SSSE3 sc12 converters by build switch only | Tom Tsou | 2017-07-26 | 1 | -0/+2 |
| | | | | | | | | | | | | | | | | The existence of SSSE3 intrinsic headers is not a sufficient condition that SSSE3 support is available, which may lead to 'illegal instruction' runtime failuire on some platforms. Major OS distributions (Ubuntu, Fedora, etc.) include x86_64 intrinsic headers, though the underlying architecture may or may not support the instruction set. Assuming SSE2 availability is safe as instructions are present on all x86_64 architectures for which instrinsic headers would be present. The same cannot be said for SSSE3. Issue: #1761 | ||||
| * | convert: Add SSE implementation for sc12 | Tom Tsou | 2017-07-25 | 1 | -0/+17 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implementation uses SSSE3 intructions to perform 12-bit sample pack/unpack operations to/from standard 16 and 32 bit host values. Input/output shuffle orderings for a single 128-bit SSE register with 16-bit integers shown below. 16-bit interleaved I/Q --------------------------------------- | Q3 | I3 | Q2 | I2 | Q1 | I1 | Q0 | I0 | Input --------------------------------------- | 127 0 | 12-bit packed I/Q byteswapped ----------------------- | I0 | Q0 | I1 | 0 |-----------------------| | I1 | Q1 | I2 | Q2 | Output |-----------------------| | Q2 | I3 | Q3 | |-----------------------| | Unused | 3 ----------------------- 31 0 Fixes: #1740, #966 Related: #1739 | ||||
| * | cmake: Checked for ARMv8 to avoid building ARMv7 converters | Martin Braun | 2015-09-11 | 1 | -1/+1 |
| | | |||||
| * | uhd: Removed the ORC dependency | Martin Braun | 2015-07-01 | 1 | -34/+0 |
| | | |||||
| * | convert: Add sc16-sc16 SSE converter | Tom Tsou | 2015-05-14 | 1 | -0/+1 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The sc16-sc16 wire to host type converter is effectively an I/Q swap or 16-bit byteswap for little and big endian cases respectively. This implmentation is a subset of fc32 and fc64 converters without the floating point portion and scaling. The resulting byte ordering is as follows: ----------------- | A | B | C | D | Wire ----------------- 0 1 2 3 ----------------- | C | D | A | B | Litte-endian ----------------- 0 1 2 3 ----------------- | B | A | D | C | Big-endian ----------------- 0 1 2 3 Signed-off-by: Tom Tsou <tom.tsou@ettus.com> | ||||
| * | Initial commit E300 support. | Martin Braun | 2014-10-07 | 1 | -0/+3 |
| | | |||||
| * | Restoring compatibility with CMake 2.6 | Nicholas Corgan | 2014-08-14 | 1 | -1/+1 |
| | | | | | | * The UNSET command didn't exist back then, but using SET with no value does the same thing * CMake 2.6 doesn't like nested parantheses in IF statements, so tweak IF/ELSE statements | ||||
| * | Do not set the mfloat-soft flag during the test for arm_neon.h. | Philip Balister | 2014-06-03 | 1 | -7/+0 |
| | | | | | | | | Use the flags passed in from the toolchain. If this test runs on a hard-float system, bad things happen. Signed-off-by: Philip Balister <philip@opensdr.com> | ||||
| * | convert: added sc12 and fc32 converters | Josh Blum | 2013-08-28 | 1 | -1/+4 |
| | | |||||
| * | orc: added std cmake finder script for orc | Josh Blum | 2013-03-29 | 1 | -5/+4 |
| | | |||||
| * | convert: squashed converter and sse2 work | Josh Blum | 2012-05-09 | 1 | -4/+9 |
| | | |||||
| * | uhd: added sse2 conversions for fc32 to sc8 | Josh Blum | 2012-02-08 | 1 | -0/+1 |
| | | |||||
| * | uhd: added sse2 conversions for fc64 to sc8 | Josh Blum | 2012-02-08 | 1 | -1/+2 |
| | | |||||
| * | convert: move priorities to implementation, different for arm | Josh Blum | 2011-11-15 | 1 | -5/+1 |
| | | |||||
| * | convert: added table conversion routine for sc16 to floats | Josh Blum | 2011-11-12 | 1 | -0/+1 |
| | | |||||
| * | convert: reworked convert to use new identification standard | Josh Blum | 2011-11-03 | 1 | -11/+0 |
| | | |||||
| * | uhd: fill in other fields of pkg-config file | Josh Blum | 2011-09-01 | 1 | -8/+8 |
| | | |||||
| * | uhd: if found, require a liborc version orc-0.4 > 0.4.11 | Josh Blum | 2011-08-04 | 1 | -1/+1 |
| | | |||||
| * | e100: perfer orc if available and dont build neon intrinsic support | Josh Blum | 2011-07-22 | 1 | -41/+48 |
| | | |||||
| * | uhd: created SSE2 conversion routines for fc64 | Josh Blum | 2011-07-17 | 1 | -4/+6 |
| | | |||||
| * | NEON detection for E100 in convert/ | Nick Foster | 2011-06-14 | 1 | -4/+13 |
| | | |||||
| * | UHD: Orc conversion routine works | Nick Foster | 2011-06-14 | 1 | -0/+2 |
| | | |||||
| * | UHD: Orc implementation added and CMake magic put in. Won't link. | Nick Foster | 2011-06-14 | 1 | -0/+31 |
| | | |||||
| * | uhd: fixed include in safe call, added quotes for SET_SOURCE_FILES_PROPERTIES | Josh Blum | 2011-03-10 | 1 | -1/+1 |
| | | |||||
| * | uhd: use source properties to set flags and defs not globally, but only for ↵ | Josh Blum | 2011-02-17 | 1 | -1/+4 |
| | | | | | the source | ||||
| * | uhd: added arch flags for sse2 (was not implicit on x32) | Josh Blum | 2011-02-16 | 1 | -1/+14 |
| | | |||||
| * | uhd: more useful prints for component macro | Josh Blum | 2011-01-14 | 1 | -1/+0 |
| | | | | | | | made libuhd a component so we can just build the docs do the python tests in the top level cmakelists misc other tweaks | ||||
| * | uhd: renamed and tweaked some of the convert files | Josh Blum | 2011-01-05 | 1 | -5/+5 |
| | | |||||
| * | uhd: added new convert directory with type conversion registry (needs testing) | Josh Blum | 2011-01-04 | 1 | -0/+66 |
 |
index : uhd | |
| Ettus' UHD Repository |
| aboutsummaryrefslogtreecommitdiffstats |