nv50,nvc0: add ARB_clear_texture support

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
This commit is contained in:
Ilia Mirkin 2015-11-09 12:39:05 -05:00
parent ae39b0fda8
commit c4182bb9b0
7 changed files with 103 additions and 8 deletions

View File

@ -177,7 +177,7 @@ GL 4.4, GLSL 4.40:
GL_MAX_VERTEX_ATTRIB_STRIDE DONE (all drivers) GL_MAX_VERTEX_ATTRIB_STRIDE DONE (all drivers)
GL_ARB_buffer_storage DONE (i965, nv50, nvc0, r600, radeonsi) GL_ARB_buffer_storage DONE (i965, nv50, nvc0, r600, radeonsi)
GL_ARB_clear_texture DONE (i965) (gallium - in progress, VMware) GL_ARB_clear_texture DONE (i965, nv50, nvc0)
GL_ARB_enhanced_layouts in progress (Timothy) GL_ARB_enhanced_layouts in progress (Timothy)
- compile-time constant expressions in progress - compile-time constant expressions in progress
- explicit byte offsets for blocks in progress - explicit byte offsets for blocks in progress

View File

@ -46,6 +46,7 @@ Note: some of the new features are only available with certain drivers.
<ul> <ul>
<li>GL_ARB_arrays_of_arrays on i965</li> <li>GL_ARB_arrays_of_arrays on i965</li>
<li>GL_ARB_blend_func_extended on freedreno (a3xx)</li> <li>GL_ARB_blend_func_extended on freedreno (a3xx)</li>
<li>GL_ARB_clear_texture on nv50, nvc0</li>
<li>GL_ARB_copy_image on nv50, nvc0, radeonsi</li> <li>GL_ARB_copy_image on nv50, nvc0, radeonsi</li>
<li>GL_ARB_gpu_shader_fp64 on r600 for Cypress/Cayman/Aruba chips</li> <li>GL_ARB_gpu_shader_fp64 on r600 for Cypress/Cayman/Aruba chips</li>
<li>GL_ARB_gpu_shader5 on r600 for Evergreen and later chips</li> <li>GL_ARB_gpu_shader5 on r600 for Evergreen and later chips</li>

View File

@ -151,4 +151,11 @@ nv50_surface_from_buffer(struct pipe_context *pipe,
void void
nv50_surface_destroy(struct pipe_context *, struct pipe_surface *); nv50_surface_destroy(struct pipe_context *, struct pipe_surface *);
void
nv50_clear_texture(struct pipe_context *pipe,
struct pipe_resource *res,
unsigned level,
const struct pipe_box *box,
const void *data);
#endif /* __NV50_RESOURCE_H__ */ #endif /* __NV50_RESOURCE_H__ */

View File

@ -182,6 +182,7 @@ nv50_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
case PIPE_CAP_TGSI_TXQS: case PIPE_CAP_TGSI_TXQS:
case PIPE_CAP_COPY_BETWEEN_COMPRESSED_AND_PLAIN_FORMATS: case PIPE_CAP_COPY_BETWEEN_COMPRESSED_AND_PLAIN_FORMATS:
case PIPE_CAP_SHAREABLE_SHADERS: case PIPE_CAP_SHAREABLE_SHADERS:
case PIPE_CAP_CLEAR_TEXTURE:
return 1; return 1;
case PIPE_CAP_SEAMLESS_CUBE_MAP: case PIPE_CAP_SEAMLESS_CUBE_MAP:
return 1; /* class_3d >= NVA0_3D_CLASS; */ return 1; /* class_3d >= NVA0_3D_CLASS; */
@ -218,7 +219,6 @@ nv50_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
case PIPE_CAP_RESOURCE_FROM_USER_MEMORY: case PIPE_CAP_RESOURCE_FROM_USER_MEMORY:
case PIPE_CAP_DEVICE_RESET_STATUS_QUERY: case PIPE_CAP_DEVICE_RESET_STATUS_QUERY:
case PIPE_CAP_MAX_SHADER_PATCH_VARYINGS: case PIPE_CAP_MAX_SHADER_PATCH_VARYINGS:
case PIPE_CAP_CLEAR_TEXTURE:
return 0; return 0;
case PIPE_CAP_VENDOR_ID: case PIPE_CAP_VENDOR_ID:

View File

@ -27,6 +27,7 @@
#include "util/u_inlines.h" #include "util/u_inlines.h"
#include "util/u_pack_color.h" #include "util/u_pack_color.h"
#include "util/u_format.h" #include "util/u_format.h"
#include "util/u_math.h"
#include "util/u_surface.h" #include "util/u_surface.h"
#include "tgsi/tgsi_ureg.h" #include "tgsi/tgsi_ureg.h"
@ -324,6 +325,9 @@ nv50_clear_render_target(struct pipe_context *pipe,
else else
PUSH_DATA(push, 512); PUSH_DATA(push, 512);
BEGIN_NV04(push, NV50_3D(MULTISAMPLE_MODE), 1);
PUSH_DATA (push, mt->ms_mode);
if (!nouveau_bo_memtype(bo)) { if (!nouveau_bo_memtype(bo)) {
BEGIN_NV04(push, NV50_3D(ZETA_ENABLE), 1); BEGIN_NV04(push, NV50_3D(ZETA_ENABLE), 1);
PUSH_DATA (push, 0); PUSH_DATA (push, 0);
@ -404,6 +408,9 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,
BEGIN_NV04(push, NV50_3D(RT_ARRAY_MODE), 1); BEGIN_NV04(push, NV50_3D(RT_ARRAY_MODE), 1);
PUSH_DATA (push, 512); PUSH_DATA (push, 512);
BEGIN_NV04(push, NV50_3D(MULTISAMPLE_MODE), 1);
PUSH_DATA (push, mt->ms_mode);
BEGIN_NV04(push, NV50_3D(VIEWPORT_HORIZ(0)), 2); BEGIN_NV04(push, NV50_3D(VIEWPORT_HORIZ(0)), 2);
PUSH_DATA (push, (width << 16) | dstx); PUSH_DATA (push, (width << 16) | dstx);
PUSH_DATA (push, (height << 16) | dsty); PUSH_DATA (push, (height << 16) | dsty);
@ -417,6 +424,80 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,
nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR; nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR;
} }
void
nv50_clear_texture(struct pipe_context *pipe,
struct pipe_resource *res,
unsigned level,
const struct pipe_box *box,
const void *data)
{
struct pipe_surface tmpl = {{0}}, *sf;
tmpl.format = res->format;
tmpl.u.tex.first_layer = box->z;
tmpl.u.tex.last_layer = box->z + box->depth - 1;
tmpl.u.tex.level = level;
sf = pipe->create_surface(pipe, res, &tmpl);
if (!sf)
return;
if (util_format_is_depth_or_stencil(res->format)) {
float depth = 0;
uint8_t stencil = 0;
unsigned clear = 0;
const struct util_format_description *desc =
util_format_description(res->format);
if (util_format_has_depth(desc)) {
clear |= PIPE_CLEAR_DEPTH;
desc->unpack_z_float(&depth, 0, data, 0, 1, 1);
}
if (util_format_has_stencil(desc)) {
clear |= PIPE_CLEAR_STENCIL;
desc->unpack_s_8uint(&stencil, 0, data, 0, 1, 1);
}
pipe->clear_depth_stencil(pipe, sf, clear, depth, stencil,
box->x, box->y, box->width, box->height);
} else {
union pipe_color_union color;
switch (util_format_get_blocksizebits(res->format)) {
case 128:
sf->format = PIPE_FORMAT_R32G32B32A32_UINT;
memcpy(&color.ui, data, 128 / 8);
break;
case 64:
sf->format = PIPE_FORMAT_R32G32_UINT;
memcpy(&color.ui, data, 64 / 8);
memset(&color.ui[2], 0, 64 / 8);
break;
case 32:
sf->format = PIPE_FORMAT_R32_UINT;
memcpy(&color.ui, data, 32 / 8);
memset(&color.ui[1], 0, 96 / 8);
break;
case 16:
sf->format = PIPE_FORMAT_R16_UINT;
color.ui[0] = util_cpu_to_le32(
util_le16_to_cpu(*(unsigned short *)data));
memset(&color.ui[1], 0, 96 / 8);
break;
case 8:
sf->format = PIPE_FORMAT_R8_UINT;
color.ui[0] = util_cpu_to_le32(*(unsigned char *)data);
memset(&color.ui[1], 0, 96 / 8);
break;
default:
assert(!"Unknown texel element size");
return;
}
pipe->clear_render_target(pipe, sf, &color,
box->x, box->y, box->width, box->height);
}
pipe->surface_destroy(pipe, sf);
}
void void
nv50_clear(struct pipe_context *pipe, unsigned buffers, nv50_clear(struct pipe_context *pipe, unsigned buffers,
const union pipe_color_union *color, const union pipe_color_union *color,
@ -464,11 +545,9 @@ nv50_clear(struct pipe_context *pipe, unsigned buffers,
if (mode) { if (mode) {
int zs_layers = 0, color0_layers = 0; int zs_layers = 0, color0_layers = 0;
if (fb->cbufs[0] && (mode & 0x3c)) if (fb->cbufs[0] && (mode & 0x3c))
color0_layers = fb->cbufs[0]->u.tex.last_layer - color0_layers = nv50_surface(fb->cbufs[0])->depth;
fb->cbufs[0]->u.tex.first_layer + 1;
if (fb->zsbuf && (mode & ~0x3c)) if (fb->zsbuf && (mode & ~0x3c))
zs_layers = fb->zsbuf->u.tex.last_layer - zs_layers = nv50_surface(fb->zsbuf)->depth;
fb->zsbuf->u.tex.first_layer + 1;
for (j = 0; j < MIN2(zs_layers, color0_layers); j++) { for (j = 0; j < MIN2(zs_layers, color0_layers); j++) {
BEGIN_NV04(push, NV50_3D(CLEAR_BUFFERS), 1); BEGIN_NV04(push, NV50_3D(CLEAR_BUFFERS), 1);
@ -488,7 +567,7 @@ nv50_clear(struct pipe_context *pipe, unsigned buffers,
struct pipe_surface *sf = fb->cbufs[i]; struct pipe_surface *sf = fb->cbufs[i];
if (!sf || !(buffers & (PIPE_CLEAR_COLOR0 << i))) if (!sf || !(buffers & (PIPE_CLEAR_COLOR0 << i)))
continue; continue;
for (j = 0; j <= sf->u.tex.last_layer - sf->u.tex.first_layer; j++) { for (j = 0; j < nv50_surface(sf)->depth; j++) {
BEGIN_NV04(push, NV50_3D(CLEAR_BUFFERS), 1); BEGIN_NV04(push, NV50_3D(CLEAR_BUFFERS), 1);
PUSH_DATA (push, (i << 6) | 0x3c | PUSH_DATA (push, (i << 6) | 0x3c |
(j << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT)); (j << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT));
@ -585,6 +664,8 @@ nv50_clear_buffer(struct pipe_context *pipe,
PUSH_DATA (push, height); PUSH_DATA (push, height);
BEGIN_NV04(push, NV50_3D(ZETA_ENABLE), 1); BEGIN_NV04(push, NV50_3D(ZETA_ENABLE), 1);
PUSH_DATA (push, 0); PUSH_DATA (push, 0);
BEGIN_NV04(push, NV50_3D(MULTISAMPLE_MODE), 1);
PUSH_DATA (push, 0);
/* NOTE: only works with D3D clear flag (5097/0x143c bit 4) */ /* NOTE: only works with D3D clear flag (5097/0x143c bit 4) */
@ -1593,6 +1674,7 @@ nv50_init_surface_functions(struct nv50_context *nv50)
pipe->resource_copy_region = nv50_resource_copy_region; pipe->resource_copy_region = nv50_resource_copy_region;
pipe->blit = nv50_blit; pipe->blit = nv50_blit;
pipe->flush_resource = nv50_flush_resource; pipe->flush_resource = nv50_flush_resource;
pipe->clear_texture = nv50_clear_texture;
pipe->clear_render_target = nv50_clear_render_target; pipe->clear_render_target = nv50_clear_render_target;
pipe->clear_depth_stencil = nv50_clear_depth_stencil; pipe->clear_depth_stencil = nv50_clear_depth_stencil;
pipe->clear_buffer = nv50_clear_buffer; pipe->clear_buffer = nv50_clear_buffer;

View File

@ -182,6 +182,7 @@ nvc0_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
case PIPE_CAP_COPY_BETWEEN_COMPRESSED_AND_PLAIN_FORMATS: case PIPE_CAP_COPY_BETWEEN_COMPRESSED_AND_PLAIN_FORMATS:
case PIPE_CAP_FORCE_PERSAMPLE_INTERP: case PIPE_CAP_FORCE_PERSAMPLE_INTERP:
case PIPE_CAP_SHAREABLE_SHADERS: case PIPE_CAP_SHAREABLE_SHADERS:
case PIPE_CAP_CLEAR_TEXTURE:
return 1; return 1;
case PIPE_CAP_SEAMLESS_CUBE_MAP_PER_TEXTURE: case PIPE_CAP_SEAMLESS_CUBE_MAP_PER_TEXTURE:
return (class_3d >= NVE4_3D_CLASS) ? 1 : 0; return (class_3d >= NVE4_3D_CLASS) ? 1 : 0;
@ -204,7 +205,6 @@ nvc0_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
case PIPE_CAP_VERTEXID_NOBASE: case PIPE_CAP_VERTEXID_NOBASE:
case PIPE_CAP_RESOURCE_FROM_USER_MEMORY: case PIPE_CAP_RESOURCE_FROM_USER_MEMORY:
case PIPE_CAP_DEVICE_RESET_STATUS_QUERY: case PIPE_CAP_DEVICE_RESET_STATUS_QUERY:
case PIPE_CAP_CLEAR_TEXTURE:
return 0; return 0;
case PIPE_CAP_VENDOR_ID: case PIPE_CAP_VENDOR_ID:

View File

@ -319,6 +319,7 @@ nvc0_clear_render_target(struct pipe_context *pipe,
PUSH_DATA(push, dst->u.tex.first_layer + sf->depth); PUSH_DATA(push, dst->u.tex.first_layer + sf->depth);
PUSH_DATA(push, mt->layer_stride >> 2); PUSH_DATA(push, mt->layer_stride >> 2);
PUSH_DATA(push, dst->u.tex.first_layer); PUSH_DATA(push, dst->u.tex.first_layer);
IMMED_NVC0(push, NVC0_3D(MULTISAMPLE_MODE), mt->ms_mode);
} else { } else {
if (res->base.target == PIPE_BUFFER) { if (res->base.target == PIPE_BUFFER) {
PUSH_DATA(push, 262144); PUSH_DATA(push, 262144);
@ -334,6 +335,7 @@ nvc0_clear_render_target(struct pipe_context *pipe,
PUSH_DATA(push, 0); PUSH_DATA(push, 0);
IMMED_NVC0(push, NVC0_3D(ZETA_ENABLE), 0); IMMED_NVC0(push, NVC0_3D(ZETA_ENABLE), 0);
IMMED_NVC0(push, NVC0_3D(MULTISAMPLE_MODE), 0);
/* tiled textures don't have to be fenced, they're not mapped directly */ /* tiled textures don't have to be fenced, they're not mapped directly */
nvc0_resource_fence(res, NOUVEAU_BO_WR); nvc0_resource_fence(res, NOUVEAU_BO_WR);
@ -466,6 +468,7 @@ nvc0_clear_buffer(struct pipe_context *pipe,
PUSH_DATA (push, 0); PUSH_DATA (push, 0);
IMMED_NVC0(push, NVC0_3D(ZETA_ENABLE), 0); IMMED_NVC0(push, NVC0_3D(ZETA_ENABLE), 0);
IMMED_NVC0(push, NVC0_3D(MULTISAMPLE_MODE), 0);
IMMED_NVC0(push, NVC0_3D(CLEAR_BUFFERS), 0x3c); IMMED_NVC0(push, NVC0_3D(CLEAR_BUFFERS), 0x3c);
@ -540,6 +543,7 @@ nvc0_clear_depth_stencil(struct pipe_context *pipe,
PUSH_DATA (push, (unk << 16) | (dst->u.tex.first_layer + sf->depth)); PUSH_DATA (push, (unk << 16) | (dst->u.tex.first_layer + sf->depth));
BEGIN_NVC0(push, NVC0_3D(ZETA_BASE_LAYER), 1); BEGIN_NVC0(push, NVC0_3D(ZETA_BASE_LAYER), 1);
PUSH_DATA (push, dst->u.tex.first_layer); PUSH_DATA (push, dst->u.tex.first_layer);
IMMED_NVC0(push, NVC0_3D(MULTISAMPLE_MODE), mt->ms_mode);
BEGIN_NIC0(push, NVC0_3D(CLEAR_BUFFERS), sf->depth); BEGIN_NIC0(push, NVC0_3D(CLEAR_BUFFERS), sf->depth);
for (z = 0; z < sf->depth; ++z) { for (z = 0; z < sf->depth; ++z) {
@ -1541,5 +1545,6 @@ nvc0_init_surface_functions(struct nvc0_context *nvc0)
pipe->flush_resource = nvc0_flush_resource; pipe->flush_resource = nvc0_flush_resource;
pipe->clear_render_target = nvc0_clear_render_target; pipe->clear_render_target = nvc0_clear_render_target;
pipe->clear_depth_stencil = nvc0_clear_depth_stencil; pipe->clear_depth_stencil = nvc0_clear_depth_stencil;
pipe->clear_texture = nv50_clear_texture;
pipe->clear_buffer = nvc0_clear_buffer; pipe->clear_buffer = nvc0_clear_buffer;
} }