Displaying 5 results from an estimated 5 matches for "__sse2__".
Did you mean:
__os2__
2013 Jul 29
3
[PATCH 1/2] xv: fix last pixel for big-endian machines in YV12 -> NV12 conversion
Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/nouveau_xv.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/src/nouveau_xv.c b/src/nouveau_xv.c
index 8eafcf0..567e30c 100644
--- a/src/nouveau_xv.c
+++ b/src/nouveau_xv.c
@@ -552,8 +552,11 @@ NVCopyNV12ColorPlanes(unsigned char *src1, unsigned char *src2,
if (e) {
unsigned short *vud = (unsigned
2013 Jul 29
0
[PATCH 2/2] xv: speed up YV12 -> NV12 conversion using SSE2 if available
...#include "config.h"
#endif
+#include <immintrin.h>
+
#include "xf86xv.h"
#include <X11/extensions/Xv.h>
#include "exa.h"
@@ -532,30 +534,47 @@ NVCopyNV12ColorPlanes(unsigned char *src1, unsigned char *src2,
w >>= 1;
h >>= 1;
+#ifdef __SSE2__
+ l = w >> 3;
+ e = w & 7;
+#else
l = w >> 1;
e = w & 1;
+#endif
for (j = 0; j < h; j++) {
unsigned char *us = src1;
unsigned char *vs = src2;
unsigned int *vuvud = (unsigned int *) dst;
+ unsigned short *vud;
for (i = 0; i < l; i++) {
-#if X_BYTE_OR...
2020 May 18
6
[PATCH] SSE2/SSSE3 optimized version of get_checksum1() for x86-64
...S=popt/findme.o popt/popt.o popt/poptconfig.o \
popt/popthelp.o popt/poptparse.o
diff --git a/checksum.c b/checksum.c
index cd234038..4e696f3d 100644
--- a/checksum.c
+++ b/checksum.c
@@ -99,6 +99,7 @@ int canonical_checksum(int csum_type)
return csum_type >= CSUM_MD4 ? 1 : 0;
}
+#ifndef __SSE2__ // see checksum_sse2.c for SSE2/SSSE3 version
/*
a simple 32 bit checksum that can be updated from either end
(inspired by Mark Adler's Adler-32 checksum)
@@ -119,6 +120,7 @@ uint32 get_checksum1(char *buf1, int32 len)
}
return (s1 & 0xffff) + (s2 << 16);
}
+#endif
void...
2020 May 18
0
[PATCH] SSE2/SSSE3 optimized version of get_checksum1() for x86-64
...> popt/popthelp.o popt/poptparse.o
> diff --git a/checksum.c b/checksum.c
> index cd234038..4e696f3d 100644
> --- a/checksum.c
> +++ b/checksum.c
> @@ -99,6 +99,7 @@ int canonical_checksum(int csum_type)
> return csum_type >= CSUM_MD4 ? 1 : 0;
> }
>
> +#ifndef __SSE2__ // see checksum_sse2.c for SSE2/SSSE3 version
> /*
> a simple 32 bit checksum that can be updated from either end
> (inspired by Mark Adler's Adler-32 checksum)
> @@ -119,6 +120,7 @@ uint32 get_checksum1(char *buf1, int32 len)
> }
> return (s1 & 0xffff) + (s2 &...
2020 May 18
2
[PATCH] SSE2/SSSE3 optimized version of get_checksum1() for x86-64
...se.o
>> diff --git a/checksum.c b/checksum.c
>> index cd234038..4e696f3d 100644
>> --- a/checksum.c
>> +++ b/checksum.c
>> @@ -99,6 +99,7 @@ int canonical_checksum(int csum_type)
>> return csum_type >= CSUM_MD4 ? 1 : 0;
>> }
>>
>> +#ifndef __SSE2__ // see checksum_sse2.c for SSE2/SSSE3 version
>> /*
>> a simple 32 bit checksum that can be updated from either end
>> (inspired by Mark Adler's Adler-32 checksum)
>> @@ -119,6 +120,7 @@ uint32 get_checksum1(char *buf1, int32 len)
>> }
>> return (...