Displaying 7 results from an estimated 7 matches for "pipe_usage_staging".
2014 Nov 19
1
[PATCH v2 2/3] nvc0: use NV_VRAM_DOMAIN() macro
...39;d have to do staging transfers to avoid sync
> * with this usage, and GART -> GART copies would be suboptimal.
> */
> - buffer->domain = NOUVEAU_BO_VRAM;
> + buffer->domain = NV_VRAM_DOMAIN(screen);
> break;
> case PIPE_USAGE_STAGING:
> case PIPE_USAGE_STREAM:
> @@ -676,7 +674,7 @@ nouveau_buffer_create(struct pipe_screen *pscreen,
> }
> } else {
> if (buffer->base.bind & screen->vidmem_bindings)
> - buffer->domain = NOUVEAU_BO_VRAM;
> + buffer->domai...
2014 Nov 19
5
[PATCH v2 0/3] nouveau: support for custom VRAM domains
This series is to allow NVIDIA chips with shared memory to operate more
efficiently (and to operate at all once we disable VRAM from the kernel
driver) by allowing nouveau_screen to specify a domain to use for objects
originally allocated into VRAM. If the domain is not overridden, the default
NOUVEAU_BO_VRAM is used. A NV_VRAM_DOMAIN() macro is then introduced to be
used in place of
2014 Nov 19
0
[PATCH v2 2/3] nvc0: use NV_VRAM_DOMAIN() macro
.../* For most apps, we'd have to do staging transfers to avoid sync
* with this usage, and GART -> GART copies would be suboptimal.
*/
- buffer->domain = NOUVEAU_BO_VRAM;
+ buffer->domain = NV_VRAM_DOMAIN(screen);
break;
case PIPE_USAGE_STAGING:
case PIPE_USAGE_STREAM:
@@ -676,7 +674,7 @@ nouveau_buffer_create(struct pipe_screen *pscreen,
}
} else {
if (buffer->base.bind & screen->vidmem_bindings)
- buffer->domain = NOUVEAU_BO_VRAM;
+ buffer->domain = NV_VRAM_DOMAIN(screen);...
2014 Nov 19
1
[PATCH v2 2/3] nvc0: use NV_VRAM_DOMAIN() macro
...have to do staging transfers to avoid sync
> * with this usage, and GART -> GART copies would be suboptimal.
> */
> - buffer->domain = NOUVEAU_BO_VRAM;
> + buffer->domain = NV_VRAM_DOMAIN(screen);
> break;
> case PIPE_USAGE_STAGING:
> case PIPE_USAGE_STREAM:
> @@ -676,7 +674,7 @@ nouveau_buffer_create(struct pipe_screen *pscreen,
> }
> } else {
> if (buffer->base.bind & screen->vidmem_bindings)
> - buffer->domain = NOUVEAU_BO_VRAM;
> + buffer->d...
2014 Sep 01
0
[PATCH] nvc0: don't make 1d staging textures linear
...0/nvc0_miptree.c b/src/gallium/drivers/nouveau/nvc0/nvc0_miptree.c
index 2f3cba8..3baa752 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_miptree.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_miptree.c
@@ -261,7 +261,6 @@ nvc0_miptree_create(struct pipe_screen *pscreen,
if (pt->usage == PIPE_USAGE_STAGING) {
switch (pt->target) {
- case PIPE_TEXTURE_1D:
case PIPE_TEXTURE_2D:
case PIPE_TEXTURE_RECT:
if (pt->last_level == 0 &&
--
1.8.5.5
2014 Oct 27
4
[PATCH 0/3] nouveau: support for custom VRAM domains
This series is to allow NVIDIA chips with shared memory to operate more
efficiently (and to operate at all once we disable VRAM from the kernel
driver) by allowing nouveau_screen to specify a domain to use for objects
originally allocated into VRAM. If the domain is not overridden, the default
NOUVEAU_BO_VRAM is used. A NV_VRAM_DOMAIN() macro is then introduced to be
used in place of
2015 Jun 19
5
[PATCH v3 0/2] nouveau: support for custom VRAM domains
New revision of this patchset that prevents VRAM objects from being
allocated on VRAM-less systems like Tegra. This is required for Mesa
to work on such systems.
Changes since v2:
- Use vram_size to detect systems without VRAM and set the correct
domain instead of expecting each chip to set its domain explicitly.
Alexandre Courbot (2):
nouveau: support for custom VRAM domains
nvc0: use