diff options
author | Thomas Tsou <tom@tsou.cc> | 2013-10-30 21:18:55 -0400 |
---|---|---|
committer | Thomas Tsou <tom@tsou.cc> | 2013-11-15 23:32:35 -0500 |
commit | 7e4e536b1bfc9b20df6b30d427de29e3cc5bf5cf (patch) | |
tree | 31b73f9d77cc616c57cd9cc61ca9d608533205e9 /Transceiver52M/x86 | |
parent | 204a9f135ac2408dd62b55462ebe4b2d10be4f56 (diff) |
Transceiver52M: Add ARM NEON support
Similar to the existing Intel SSE cases, add support for NEON vector
floating point SIMD processing. In this case, use ARM assembly
directly as the NEON intrinsics do not generate preferential code
output.
Currently support NEON vectorized convolution and floating point
integer conversions.
Signed-off-by: Thomas Tsou <tom@tsou.cc>
Diffstat (limited to 'Transceiver52M/x86')
-rw-r--r-- | Transceiver52M/x86/Makefile.am | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/Transceiver52M/x86/Makefile.am b/Transceiver52M/x86/Makefile.am index 0621b17..e880351 100644 --- a/Transceiver52M/x86/Makefile.am +++ b/Transceiver52M/x86/Makefile.am @@ -1,3 +1,4 @@ +if !ARCH_ARM AM_CFLAGS = -Wall -std=gnu99 -march=native -I../common noinst_LTLIBRARIES = libarch.la @@ -6,3 +7,4 @@ libarch_la_SOURCES = \ ../common/convolve_base.c \ convert.c \ convolve.c +endif |