On 24 July 2017 at 15:51, Kenneth Graunke wrote:
> On Monday, July 24, 2017 3:54:11 AM PDT Emil Velikov wrote:
>> Hi Ken,
>>
>> Admittedly I'm not an expert in the area, so perhaps a rather silly question.
>>
>> On 22 July 2017 at 00:17, Kenneth Graunke wrote:
>>
>> > +#ifdef USE_SSE41
>> > +
On Monday, July 24, 2017 3:54:11 AM PDT Emil Velikov wrote:
> Hi Ken,
>
> Admittedly I'm not an expert in the area, so perhaps a rather silly question.
>
> On 22 July 2017 at 00:17, Kenneth Graunke wrote:
>
> > +#ifdef USE_SSE41
> > + if (!cache->bo->cache_coherent && cpu_has_sse4_1)
> > +
Hi Ken,
Admittedly I'm not an expert in the area, so perhaps a rather silly question.
On 22 July 2017 at 00:17, Kenneth Graunke wrote:
> +#ifdef USE_SSE41
> + if (!cache->bo->cache_coherent && cpu_has_sse4_1)
> + _mesa_streaming_load_memcpy(map, cache->map, cache->next_offset);
> +
Quoting Kenneth Graunke (2017-07-24 02:03:23)
> On Saturday, July 22, 2017 2:28:06 AM PDT Chris Wilson wrote:
> > Considering the prevalence of sse4.1, another candidate is
> > brw_get_buffer_subdata(), we could use a WC map there as well.
>
> Your thinking is...avoid polluting the CPU cache, sinc
On Saturday, July 22, 2017 2:28:06 AM PDT Chris Wilson wrote:
> Considering the prevalence of sse4.1, another candidate is
> brw_get_buffer_subdata(), we could use a WC map there as well.
Your thinking is...avoid polluting the CPU cache, since we're basically
going to be reading a continuous chunk
On Saturday, July 22, 2017 2:14:28 AM PDT Chris Wilson wrote:
> Quoting Kenneth Graunke (2017-07-22 00:17:47)
> > The non-LLC story was a horror show. We uploaded data via pwrite
> > (drm_intel_bo_subdata), which would stall if the cache BO was in
> > use (being read) by the GPU. Obviously, we wa
Quoting Kenneth Graunke (2017-07-22 00:17:47)
> src/mesa/drivers/dri/i965/brw_program_cache.c | 83
> +++
> 1 file changed, 21 insertions(+), 62 deletions(-)
>
> diff --git a/src/mesa/drivers/dri/i965/brw_program_cache.c
> b/src/mesa/drivers/dri/i965/brw_program_cache.c
Quoting Kenneth Graunke (2017-07-22 00:17:47)
> The non-LLC story was a horror show. We uploaded data via pwrite
> (drm_intel_bo_subdata), which would stall if the cache BO was in
> use (being read) by the GPU. Obviously, we wanted to avoid that.
> So, we tried to detect whether the buffer was bu
The non-LLC story was a horror show. We uploaded data via pwrite
(drm_intel_bo_subdata), which would stall if the cache BO was in
use (being read) by the GPU. Obviously, we wanted to avoid that.
So, we tried to detect whether the buffer was busy, and if so, we'd
allocate a new BO, map the old one
