On 10/1/2017 4:52 PM, Martin Vignali wrote:
> Hello,
>
> in attach new patch
>
> pass fate test for me (X86_64 osX)
>
> Check asm (Kaby Lake)
>
> checkasm: all 5 tests passed
> predictor_c: 11042.9
> predictor_ssse3: 1736.4
> predictor_avx: 1675.4
> predictor_avx2: 1245.4
> ...
>
> Martin
Pus
Hello,
in attach new patch
pass fate test for me (X86_64 osX)
Check asm (Kaby Lake)
checkasm: all 5 tests passed
predictor_c: 11042.9
predictor_ssse3: 1736.4
predictor_avx: 1675.4
predictor_avx2: 1245.4
...
Martin
0001-libavcodec-exr-add-x86-SIMD-for-predictor.patch
Description: Binary data
On 10/1/2017 11:35 AM, Henrik Gramner wrote:
> On Sun, Oct 1, 2017 at 4:14 PM, James Almer wrote:
>> We normally use int for counters, and don't mix declaration and statements.
>> And in any case ptrdiff_t would be "more correct" for this.
>
> Ah right. C90, ugh. Too used to C99.
No, we're c99.
On Sun, Oct 1, 2017 at 4:14 PM, James Almer wrote:
> We normally use int for counters, and don't mix declaration and statements.
> And in any case ptrdiff_t would be "more correct" for this.
Ah right. C90, ugh. Too used to C99.
Yeah, feel free to use whatever datatype that's most appropriate for
On 10/1/2017 9:47 AM, Henrik Gramner wrote:
> On Fri, Sep 22, 2017 at 11:12 PM, Martin Vignali
> wrote:
>> +static void predictor_scalar(uint8_t *src, ptrdiff_t size)
>> +{
>> +uint8_t *t= src + 1;
>> +uint8_t *stop = src + size;
>> +
>> +while (t < stop) {
>> +int d = (int
On Fri, Sep 22, 2017 at 11:12 PM, Martin Vignali
wrote:
> +static void predictor_scalar(uint8_t *src, ptrdiff_t size)
> +{
> +uint8_t *t= src + 1;
> +uint8_t *stop = src + size;
> +
> +while (t < stop) {
> +int d = (int) t[-1] + (int) t[0] - 128;
> +t[0] = d;
> +
2017-09-22 23:12 GMT+02:00 Martin Vignali :
> Hello,
>
> in attach a patch
> with a port to asm of the predictor part of this patch :
>
> https://github.com/openexr/openexr/pull/229/commits/
> 4198128397c033d4f69e5cc0833195da500c31cf
>
> Tested on OSX, pass fate test for me
> Check asm also pass f
Hello,
in attach a patch
with a port to asm of the predictor part of this patch :
https://github.com/openexr/openexr/pull/229/commits/4198128397c033d4f69e5cc0833195da500c31cf
Tested on OSX, pass fate test for me
Check asm also pass for me
Results with reorder simd disable :
SSSE3 : 94.5s
103675
