Displaying 2 results from an estimated 2 matches for "arch_x86".
2015 Jan 20
0
[RFC PATCH v1 1/2] Optimize repeated calls to opus_select_arch
...+}
+
#endif
diff --git a/celt/x86/x86cpu.c b/celt/x86/x86cpu.c
index c82a4b7..ddf3cf3 100644
--- a/celt/x86/x86cpu.c
+++ b/celt/x86/x86cpu.c
@@ -87,7 +87,10 @@ static void opus_cpu_feature_check(CPU_Feature *cpu_feature)
}
}
-int opus_select_arch(void)
+static int detected = 0;
+static int arch_x86 = 0;
+
+static int opus_select_arch_real(void)
{
CPU_Feature cpu_feature = {0};
int arch;
@@ -96,16 +99,19 @@ int opus_select_arch(void)
arch = 0;
if (!cpu_feature.HW_SSE2)
- {
- return arch;
- }
+ goto final;
arch++;
if (!cpu_feature.HW_SSE41)
-...
2015 Jan 20
6
[RFC PATCH v1 0/2] Encode optimize using libNE10
Hello opus-dev,
I've been cooking up this patchset to integrate NE10 library into opus.
Current patchset focuses on encode use case mainly effecting performance of
clt_mdct_forward() and opus_fft() (for float only)
Glad to report the following on Encode use case:
(Measured on my Beaglebone Black Cortex-A8 board)
- Performance improvement for encode use case ~= 12.34% (Based on time -p