Displaying 7 results from an estimated 7 matches for "vqmovn".
Did you mean:
vmovd
2016 Jul 30
2
Cannot compile speexdsp 1.2rc3 on ARM64
..."=&r" (ret)
> : [a] "w" (a)
> : "v0" );
> return ret;
> }
> #elif defined(__ARM_NEON__)
> static inline int32_t saturate_32bit_to_16bit(int32_t a) {
> int32_t ret;
> asm volatile ("vmov.s32 d24[0], %[a]\n"
> "vqmovn.s32 d24, q12\n"
> "vmov.s16 %[ret], d24[0]\n"
> : [ret] "=&r" (ret)
> : [a] "r" (a)
> : "q12", "d24", "d25" );
> return ret;
> }
> #else
> static inline int32_t saturate_32bit_to_16bit(i...
2015 Mar 28
4
Cannot compile speexdsp 1.2rc3 on ARM64
Hi all,
I build successfully with speex-1.2rc2. And with speexdsp 1.2rc3, I
build with i386, X86_64, armv7 and armv7s all passed.
But when I build for ARM64 (for iPhone 6), it failed with:
/Applications/Xcode.app/Contents/Developer/usr/bin/make all-recursive
Making all in libspeexdsp
CC preprocess.lo
CC jitter.lo
CC mdf.lo
CC fftwrap.lo
CC
2016 Apr 19
0
Cannot compile speexdsp 1.2rc3 on ARM64
..."fmov %w[ret], s0\n"
: [ret] "=&r" (ret)
: [a] "w" (a)
: "v0" );
return ret;
}
#elif defined(__ARM_NEON__)
static inline int32_t saturate_32bit_to_16bit(int32_t a) {
int32_t ret;
asm volatile ("vmov.s32 d24[0], %[a]\n"
"vqmovn.s32 d24, q12\n"
"vmov.s16 %[ret], d24[0]\n"
: [ret] "=&r" (ret)
: [a] "r" (a)
: "q12", "d24", "d25" );
return ret;
}
#else
static inline int32_t saturate_32bit_to_16bit(int32_t a) {
return max(-32768, min(32767...
2011 Sep 01
0
[PATCH 5/5] resample: Add NEON optimized inner_product_single for floating point
...asm ("ssat %[ret], #16, %[a]"
+ : [ret] "=&r" (ret)
+ : [a] "r" (a)
+ : );
+ return ret;
+}
+#else
+static inline int32_t saturate_32bit_to_16bit(int32_t a) {
+ int32_t ret;
+ asm ("vmov.s32 d0[0], %[a]\n"
+ "vqmovn.s32 d0, q0\n"
+ "vmov.s16 %[ret], d0[0]\n"
+ : [ret] "=&r" (ret)
+ : [a] "r" (a)
+ : "q0");
+ return ret;
+}
+#endif
+#undef WORD2INT
+#define WORD2INT(x) (saturate_32bit_to_16bit(x))
+
#define OVERRIDE_INNER_PRODU...
2016 Aug 09
0
Cannot compile speexdsp 1.2rc3 on ARM64
...: [a] "w" (a)
>> : "v0" );
>> return ret;
>> }
>> #elif defined(__ARM_NEON__)
>> static inline int32_t saturate_32bit_to_16bit(int32_t a) {
>> int32_t ret;
>> asm volatile ("vmov.s32 d24[0], %[a]\n"
>> "vqmovn.s32 d24, q12\n"
>> "vmov.s16 %[ret], d24[0]\n"
>> : [ret] "=&r" (ret)
>> : [a] "r" (a)
>> : "q12", "d24", "d25" );
>> return ret;
>> }
>> #else
>> static inline i...
2011 Sep 01
6
[PATCH 0/5] ARM NEON optimization for samplerate converter
From: Jyri Sarha <jsarha at ti.com>
I optimized Speex resampler for NEON capable ARM CPUs. The first patch
should speed up resampling on any platform that can spare the
increased memory usage. It would be nice to have these merged to the
master branch. Please let me know if there is anything I can do to
help the the merge. The patches have been rebased on top of master
branch in
2011 Sep 01
0
[PATCH 3/5] resample: Add NEON optimized inner_product_single for fixed point
...]!\n"
+ " vld1.16 {d20}, [%[a]]!\n"
+ " subs %[remainder], %[remainder], #4\n"
+ " vmlal.s16 q0, d16, d20\n"
+ " bne 4b\n"
+ "5:"
+ " vaddl.s32 q0, d0, d1\n"
+ " vadd.s64 d0, d0, d1\n"
+ " vqmovn.s64 d0, q0\n"
+ " vqrshrn.s32 d0, q0, #15\n"
+ " vmov.s16 %[ret], d0[0]\n"
+ : [ret] "=&r" (ret), [a] "+r" (a), [b] "+r" (b),
+ [len] "+r" (len), [remainder] "+r" (remainder)
+ :
+ : "cc",...