search for: nv50_compute

...| 29 +++++++++-- src/gallium/drivers/nouveau/nouveau_fence.c | 18 +++++++ src/gallium/drivers/nouveau/nouveau_fence.h | 5 +- src/gallium/drivers/nouveau/nouveau_screen.c | 12 ++++- src/gallium/drivers/nouveau/nouveau_screen.h | 3 ++ src/gallium/drivers/nouveau/nv50/nv50_compute.c | 4 ++ src/gallium/drivers/nouveau/nv50/nv50_context.c | 11 +++++ src/gallium/drivers/nouveau/nv50/nv50_context.h | 5 ++ src/gallium/drivers/nouveau/nv50/nv50_query.c | 14 +++++- src/gallium/drivers/nouveau/nv50/nv50_query_hw.c | 20 ++++++-- .../drivers/nouveau/nv50/nv50_qu...

...s for using the new MEMORY keyword look as intended to you? 2) This only solves the accessing of the global memory, it does not solve getting to the kernel input kernel parameters, how would I deal with those ? Currently the kernel input parameters are uploaded by src/gallium/drivers/nouveau/nv50/nv50_compute.c: nv50_compute_upload_input() Are we going to change how these parameters get uploaded ? And if not how do we get to these parameters from TGSI now that we no longer have RES[#] to do so ? I think we should also keep in mind that what works for nouveau may not work for other GPU-s, so we should...

...rid. You just have to fill the pipe_grid_info::input array with your parameters and they will be uploaded by nvXX_compute_upload_input(). I will have a look at the test_input_global(). Thanks! > > Currently the kernel input parameters are uploaded by > src/gallium/drivers/nouveau/nv50/nv50_compute.c: > nv50_compute_upload_input() > > Are we going to change how these parameters get uploaded ? And if not > how do we > get to these parameters from TGSI now that we no longer have RES[#] to > do so ? > > I think we should also keep in mind that what works for nouveau may n...

Hi, On 18-02-16 17:39, Ilia Mirkin wrote: > On Thu, Feb 18, 2016 at 9:45 AM, Hans de Goede <hdegoede at redhat.com> wrote: >> But this does not seem to be hooked up yet for nouveau. > > Samuel has patches. See > https://cgit.freedesktop.org/~hakzsam/mesa/log/?h=arb_compute_shader_v3 Cool, I will take a look at those. >> So some questions: >> -The commit by

...b/src/gallium/drivers/nv50/nv50_winsys.h index 145ee70..e04247b 100644 --- a/src/gallium/drivers/nv50/nv50_winsys.h +++ b/src/gallium/drivers/nv50/nv50_winsys.h @@ -60,6 +60,10 @@ PUSH_REFN(struct nouveau_pushbuf *push, struct nouveau_bo *bo, uint32_t flags) #define SUBC_COMPUTE(m) 6, (m) #define NV50_COMPUTE(n) SUBC_COMPUTE(NV50_COMPUTE_##n) +/* These are expected to be on their own pushbufs */ +#define SUBC_BSP(m) 2, (m) +#define SUBC_VP(m) 2, (m) + static INLINE uint32_t NV50_FIFO_PKHDR(int subc, int mthd, unsigned size) diff --git a/src/gallium/drivers/nv50/nv84_video.c b/src/gallium/drivers/n...

...db/nv30-40_3d.xml ( 31987 bytes, from 2011-10-22 08:01:09) -- /home/skeggsb/git/envytools/rnndb/nv50_2d.xml ( 11113 bytes, from 2011-10-22 08:01:09) -- /home/skeggsb/git/envytools/rnndb/nv50_3d.xml ( 65233 bytes, from 2011-11-30 05:49:35) -- /home/skeggsb/git/envytools/rnndb/nv50_compute.xml ( 14012 bytes, from 2011-10-22 08:01:09) -- /home/skeggsb/git/envytools/rnndb/nv84_crypt.xml ( 2071 bytes, from 2011-11-30 05:49:35) -- /home/skeggsb/git/envytools/rnndb/nv31_mpeg.xml ( 2269 bytes, from 2011-10-22 08:01:09) -- /home/skeggsb/git/envytools/rnndb/nvc0_3d.xml...

...b/src/gallium/drivers/nv50/nv50_winsys.h index 145ee70..e04247b 100644 --- a/src/gallium/drivers/nv50/nv50_winsys.h +++ b/src/gallium/drivers/nv50/nv50_winsys.h @@ -60,6 +60,10 @@ PUSH_REFN(struct nouveau_pushbuf *push, struct nouveau_bo *bo, uint32_t flags) #define SUBC_COMPUTE(m) 6, (m) #define NV50_COMPUTE(n) SUBC_COMPUTE(NV50_COMPUTE_##n) +/* These are expected to be on their own pushbufs */ +#define SUBC_BSP(m) 2, (m) +#define SUBC_VP(m) 2, (m) + static INLINE uint32_t NV50_FIFO_PKHDR(int subc, int mthd, unsigned size) diff --git a/src/gallium/drivers/nv50/nv84_video.c b/src/gallium/drivers/n...

Hello there, This series exposes NVIDIA's global performance counters for Tesla through the Gallium's HUD and the GL_AMD_performance_monitor extension. This adds support for 24 hardware events which have been reverse engineered with PerfKit (Windows) and CUPTI (Linux). These hardware events will allow developers to profile OpenGL applications. To reduce latency and to improve accuracy,

I believe I've addressed all the feedback from the first time around, and also made fixes necessary for GM20x based on testing results. I believe now it should actually work for all GM10x and GM20x. Further, GP10x should be very easy to add, but without someone to actually test I didn't want to claim support for it. Ilia Mirkin (7): exa: add GM10x acceleration support hwdefs: update

As it turns out, with the proprietary firmware, the VP3 and VP4 interfaces are identical. Furthermore, this is all already implemented for nvc0. So these patches (a) move the easily sharable bits of the nvc0 implementation into the nouveau directory, and then (b) implement the other parts in nv50. The non-shared parts are still largely copies, but there are some differences, not the least of which