On Wed, 19 Feb 2003, Abramo Bagnara wrote:
> The results are amazing and I'd say Jaroslav has done some mistakes in
> his handmade asm.
I don't think so. It seems that my brain still remembers assembler ;-)
You passed wrong values to my code so it did unaligned accesses.
Fixes to make things same:
--- sum.c 2003-02-19 18:55:20.000000000 +0100
+++ a.c 2003-02-19 19:31:00.000000000 +0100
@@ -11,6 +11,8 @@
typedef short int s16;
typedef int s32;
+#define CONFIG_SMP
+
#ifdef CONFIG_SMP
#define LOCK_PREFIX "lock ; "
#else
@@ -54,7 +56,7 @@
static inline void atomic_add(volatile int *dst, int v)
{
__asm__ __volatile__(
- LOCK_PREFIX "addl %0,%1"
+ LOCK_PREFIX "addl %1,%0"
:"=m" (*dst)
:"ir" (v));
}
@@ -62,7 +64,9 @@
void mix_areas0(unsigned int size,
volatile s16 *dst, s16 *src,
volatile s32 *sum,
- unsigned int dst_step, unsigned int src_step)
+ unsigned int dst_step,
+ unsigned int src_step,
+ unsigned int sum_step)
{
while (size-- > 0) {
s32 sample = *dst + *src;
@@ -70,8 +74,8 @@
*dst = sample > 0 ? 0x7fff : -0x8000;
else
*dst = sample;
- dst += dst_step;
- src += src_step;
+ ((char *)dst) += dst_step;
+ ((char *)src) += src_step;
}
}
@@ -194,7 +198,9 @@
void mix_areas2(unsigned int size,
volatile s16 *dst, s16 *src,
volatile s32 *sum,
- unsigned int dst_step, unsigned int src_step)
+ unsigned int dst_step,
+ unsigned int src_step,
+ unsigned int sum_step)
{
while (size-- > 0) {
s32 sample = *src;
@@ -204,15 +210,15 @@
do {
sample = *sum;
s16 s;
- if (unlikely(sample & 0xffff0000))
+ if (unlikely(sample & 0x7fff0000))
s = sample > 0 ? 0x7fff : -0x8000;
else
s = sample;
*dst = s;
} while (unlikely(sample != *sum));
- sum++;
- dst += dst_step;
- src += src_step;
+ ((char *)sum) += sum_step;
+ ((char *)dst) += dst_step;
+ ((char *)src) += src_step;
}
}
@@ -236,19 +242,19 @@
}
rdtscll(begin);
for (i = 0; i < n; i++) {
- mix_areas0(size, dst, srcs[i], sum, 1, 1);
+ mix_areas0(size, dst, srcs[i], sum, 2, 2, 4);
}
rdtscll(end);
printf("mix_areas0: %lld\n", end - begin);
rdtscll(begin);
for (i = 0; i < n; i++) {
- mix_areas1(size, dst, srcs[i], sum, 1, 1, 1);
+ mix_areas1(size, dst, srcs[i], sum, 2, 2, 4);
}
rdtscll(end);
printf("mix_areas1: %lld\n", end - begin);
rdtscll(begin);
for (i = 0; i < n; i++) {
- mix_areas2(size, dst, srcs[i], sum, 1, 1);
+ mix_areas2(size, dst, srcs[i], sum, 2, 2, 4);
}
rdtscll(end);
printf("mix_areas2: %lld\n", end - begin);
perex@pnote:~> cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 8
model name : Pentium III (Coppermine)
stepping : 6
cpu MHz : 847.473
cache size : 256 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 2
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov
pat pse36 mmx fxsr sse
bogomips : 1679.36
perex@pnote:~> ./a.out 2048 4 32267
mix_areas0: 170691
mix_areas1: 675795
mix_areas2: 708995
Have fun,
Jaroslav
-----
Jaroslav Kysela <[EMAIL PROTECTED]>
Linux Kernel Sound Maintainer
ALSA Project, SuSE Labs
-------------------------------------------------------
This SF.net email is sponsored by: SlickEdit Inc. Develop an edge.
The most comprehensive and flexible code editor you can use.
Code faster. C/C++, C#, Java, HTML, XML, many more. FREE 30-Day Trial.
www.slickedit.com/sourceforge
_______________________________________________
Alsa-devel mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/alsa-devel
