return false;
/* FIXME: for some reason TC compat with 2/4/8 samples breaks some cts
- * tests - disable for now */
+ * tests - disable for now. On GFX10 D32_SFLOAT is affected as well.
+ */
if (pCreateInfo->samples >= 2 &&
- pCreateInfo->format == VK_FORMAT_D32_SFLOAT_S8_UINT)
+ (pCreateInfo->format == VK_FORMAT_D32_SFLOAT_S8_UINT ||
+ (pCreateInfo->format == VK_FORMAT_D32_SFLOAT &&
+ device->physical_device->rad_info.chip_class == GFX10)))
return false;
/* GFX9 supports both 32-bit and 16-bit depth surfaces, while GFX8 only
first_non_void = vk_format_get_first_non_void_channel(vk_format);
stride = desc->block.bits / 8;
- num_format = radv_translate_buffer_numformat(desc, first_non_void);
- data_format = radv_translate_buffer_dataformat(desc, first_non_void);
-
- assert(data_format != V_008F0C_BUF_DATA_FORMAT_INVALID);
- assert(num_format != ~0);
-
va += offset;
state[0] = va;
state[1] = S_008F04_BASE_ADDRESS_HI(va >> 32) |
state[3] = S_008F0C_DST_SEL_X(radv_map_swizzle(desc->swizzle[0])) |
S_008F0C_DST_SEL_Y(radv_map_swizzle(desc->swizzle[1])) |
S_008F0C_DST_SEL_Z(radv_map_swizzle(desc->swizzle[2])) |
- S_008F0C_DST_SEL_W(radv_map_swizzle(desc->swizzle[3])) |
- S_008F0C_NUM_FORMAT(num_format) |
- S_008F0C_DATA_FORMAT(data_format);
+ S_008F0C_DST_SEL_W(radv_map_swizzle(desc->swizzle[3]));
+
+ if (device->physical_device->rad_info.chip_class >= GFX10) {
+ const struct gfx10_format *fmt = &gfx10_format_table[vk_format];
+
+ /* OOB_SELECT chooses the out-of-bounds check:
+ * - 0: (index >= NUM_RECORDS) || (offset >= STRIDE)
+ * - 1: index >= NUM_RECORDS
+ * - 2: NUM_RECORDS == 0
+ * - 3: if SWIZZLE_ENABLE == 0: offset >= NUM_RECORDS
+ * else: swizzle_address >= NUM_RECORDS
+ */
+ state[3] |= S_008F0C_FORMAT(fmt->img_format) |
+ S_008F0C_OOB_SELECT(0) |
+ S_008F0C_RESOURCE_LEVEL(1);
+ } else {
+ num_format = radv_translate_buffer_numformat(desc, first_non_void);
+ data_format = radv_translate_buffer_dataformat(desc, first_non_void);
+
+ assert(data_format != V_008F0C_BUF_DATA_FORMAT_INVALID);
+ assert(num_format != ~0);
+
+ state[3] |= S_008F0C_NUM_FORMAT(num_format) |
+ S_008F0C_DATA_FORMAT(data_format);
+ }
}
static void
meta_va = gpu_address + image->dcc_offset;
if (chip_class <= GFX8)
meta_va += base_level_info->dcc_offset;
+
+ unsigned dcc_tile_swizzle = plane->surface.tile_swizzle << 8;
+ dcc_tile_swizzle &= plane->surface.dcc_alignment - 1;
+ meta_va |= dcc_tile_swizzle;
} else if (!is_storage_image &&
radv_image_is_tc_compat_htile(image)) {
meta_va = gpu_address + image->htile_offset;
if (meta_va) {
state[6] |= S_008F28_COMPRESSION_EN(1);
- state[7] = meta_va >> 8;
- state[7] |= plane->surface.tile_swizzle;
+ if (chip_class <= GFX9)
+ state[7] = meta_va >> 8;
}
}
- if (chip_class >= GFX9) {
+ if (chip_class >= GFX10) {
+ state[3] &= C_00A00C_SW_MODE;
+
+ if (is_stencil) {
+ state[3] |= S_00A00C_SW_MODE(plane->surface.u.gfx9.stencil.swizzle_mode);
+ } else {
+ state[3] |= S_00A00C_SW_MODE(plane->surface.u.gfx9.surf.swizzle_mode);
+ }
+
+ state[6] &= C_00A018_META_DATA_ADDRESS_LO &
+ C_00A018_META_PIPE_ALIGNED;
+
+ if (meta_va) {
+ struct gfx9_surf_meta_flags meta;
+
+ if (image->dcc_offset)
+ meta = plane->surface.u.gfx9.dcc;
+ else
+ meta = plane->surface.u.gfx9.htile;
+
+ state[6] |= S_00A018_META_PIPE_ALIGNED(meta.pipe_aligned) |
+ S_00A018_META_DATA_ADDRESS_LO(meta_va >> 8);
+ }
+
+ state[7] = meta_va >> 16;
+ } else if (chip_class == GFX9) {
state[3] &= C_008F1C_SW_MODE;
state[4] &= C_008F20_PITCH;
return bc_swizzle;
}
+static bool vi_alpha_is_on_msb(struct radv_device *device, VkFormat format)
+{
+ const struct vk_format_description *desc = vk_format_description(format);
+
+ if (device->physical_device->rad_info.chip_class >= GFX10 && desc->nr_channels == 1)
+ return desc->swizzle[3] == VK_SWIZZLE_X;
+
+ return radv_translate_colorswap(format, false) <= 1;
+}
/**
* Build the sampler view descriptor for a texture (GFX10).
*/
}
type = radv_tex_dim(image->type, view_type, image->info.array_size, image->info.samples,
- is_storage_image, device->physical_device->rad_info.chip_class >= GFX9);
+ is_storage_image, device->physical_device->rad_info.chip_class == GFX9);
if (type == V_008F1C_SQ_RSRC_IMG_1D_ARRAY) {
height = 1;
depth = image->info.array_size;
state[7] = 0;
if (radv_dcc_enabled(image, first_level)) {
- unsigned swap = radv_translate_colorswap(vk_format, FALSE);
-
state[6] |= S_00A018_MAX_UNCOMPRESSED_BLOCK_SIZE(V_028C78_MAX_BLOCK_SIZE_256B) |
S_00A018_MAX_COMPRESSED_BLOCK_SIZE(V_028C78_MAX_BLOCK_SIZE_128B) |
- S_00A018_ALPHA_IS_ON_MSB(swap <= 1);
+ S_00A018_ALPHA_IS_ON_MSB(vi_alpha_is_on_msb(device, vk_format));
}
/* Initialize the sampler view for FMASK. */
assert(image->plane_count == 1);
- va = gpu_address + image->offset + image->fmask.offset;
+ va = gpu_address + image->offset + image->fmask_offset;
switch (image->info.samples) {
case 2:
}
/* S8 with either Z16 or Z32 HTILE need a special format. */
- if (device->physical_device->rad_info.chip_class >= GFX9 &&
+ if (device->physical_device->rad_info.chip_class == GFX9 &&
vk_format == VK_FORMAT_S8_UINT &&
radv_image_is_tc_compat_htile(image)) {
if (image->vk_format == VK_FORMAT_D32_SFLOAT_S8_UINT)
data_format = V_008F14_IMG_DATA_FORMAT_S8_16;
}
type = radv_tex_dim(image->type, view_type, image->info.array_size, image->info.samples,
- is_storage_image, device->physical_device->rad_info.chip_class >= GFX9);
+ is_storage_image, device->physical_device->rad_info.chip_class == GFX9);
if (type == V_008F1C_SQ_RSRC_IMG_1D_ARRAY) {
height = 1;
depth = image->info.array_size;
state[6] = 0;
state[7] = 0;
- if (device->physical_device->rad_info.chip_class >= GFX9) {
+ if (device->physical_device->rad_info.chip_class == GFX9) {
unsigned bc_swizzle = gfx9_border_color_swizzle(swizzle);
/* Depth is the last accessible layer on Gfx9.
state[5] |= S_008F24_LAST_ARRAY(last_layer);
}
if (image->dcc_offset) {
- unsigned swap = radv_translate_colorswap(vk_format, FALSE);
-
- state[6] = S_008F28_ALPHA_IS_ON_MSB(swap <= 1);
+ state[6] = S_008F28_ALPHA_IS_ON_MSB(vi_alpha_is_on_msb(device, vk_format));
} else {
/* The last dword is unused by hw. The shader uses it to clear
* bits in the first dword of sampler state.
assert(image->plane_count == 1);
- va = gpu_address + image->offset + image->fmask.offset;
+ va = gpu_address + image->offset + image->fmask_offset;
- if (device->physical_device->rad_info.chip_class >= GFX9) {
+ if (device->physical_device->rad_info.chip_class == GFX9) {
fmask_format = V_008F14_IMG_DATA_FORMAT_FMASK;
switch (image->info.samples) {
case 2:
}
fmask_state[0] = va >> 8;
- fmask_state[0] |= image->fmask.tile_swizzle;
+ fmask_state[0] |= image->planes[0].surface.fmask_tile_swizzle;
fmask_state[1] = S_008F14_BASE_ADDRESS_HI(va >> 40) |
S_008F14_DATA_FORMAT(fmask_format) |
S_008F14_NUM_FORMAT(num_format);
fmask_state[6] = 0;
fmask_state[7] = 0;
- if (device->physical_device->rad_info.chip_class >= GFX9) {
+ if (device->physical_device->rad_info.chip_class == GFX9) {
fmask_state[3] |= S_008F1C_SW_MODE(image->planes[0].surface.u.gfx9.fmask.swizzle_mode);
fmask_state[4] |= S_008F20_DEPTH(last_layer) |
S_008F20_PITCH(image->planes[0].surface.u.gfx9.fmask.epitch);
S_008F24_META_RB_ALIGNED(image->planes[0].surface.u.gfx9.cmask.rb_aligned);
if (radv_image_is_tc_compat_cmask(image)) {
- va = gpu_address + image->offset + image->cmask.offset;
+ va = gpu_address + image->offset + image->cmask_offset;
fmask_state[5] |= S_008F24_META_DATA_ADDRESS(va >> 40);
fmask_state[6] |= S_008F28_COMPRESSION_EN(1);
fmask_state[7] |= va >> 8;
}
} else {
- fmask_state[3] |= S_008F1C_TILING_INDEX(image->fmask.tile_mode_index);
+ fmask_state[3] |= S_008F1C_TILING_INDEX(image->planes[0].surface.u.legacy.fmask.tiling_index);
fmask_state[4] |= S_008F20_DEPTH(depth - 1) |
- S_008F20_PITCH(image->fmask.pitch_in_pixels - 1);
+ S_008F20_PITCH(image->planes[0].surface.u.legacy.fmask.pitch_in_pixels - 1);
fmask_state[5] |= S_008F24_LAST_ARRAY(last_layer);
if (radv_image_is_tc_compat_cmask(image)) {
- va = gpu_address + image->offset + image->cmask.offset;
+ va = gpu_address + image->offset + image->cmask_offset;
fmask_state[6] |= S_008F28_COMPRESSION_EN(1);
fmask_state[7] |= va >> 8;
for (i = 0; i <= image->info.levels - 1; i++)
md->metadata[10+i] = image->planes[0].surface.u.legacy.level[i].offset >> 8;
md->size_metadata = (11 + image->info.levels - 1) * 4;
- }
+ } else
+ md->size_metadata = 10 * 4;
}
void
}
}
-/* The number of samples can be specified independently of the texture. */
-static void
-radv_image_get_fmask_info(struct radv_device *device,
- struct radv_image *image,
- unsigned nr_samples,
- struct radv_fmask_info *out)
-{
- if (device->physical_device->rad_info.chip_class >= GFX9) {
- out->alignment = image->planes[0].surface.fmask_alignment;
- out->size = image->planes[0].surface.fmask_size;
- out->tile_swizzle = image->planes[0].surface.fmask_tile_swizzle;
- return;
- }
-
- out->slice_tile_max = image->planes[0].surface.u.legacy.fmask.slice_tile_max;
- out->tile_mode_index = image->planes[0].surface.u.legacy.fmask.tiling_index;
- out->pitch_in_pixels = image->planes[0].surface.u.legacy.fmask.pitch_in_pixels;
- out->slice_size = image->planes[0].surface.u.legacy.fmask.slice_size;
- out->bank_height = image->planes[0].surface.u.legacy.fmask.bankh;
- out->tile_swizzle = image->planes[0].surface.fmask_tile_swizzle;
- out->alignment = image->planes[0].surface.fmask_alignment;
- out->size = image->planes[0].surface.fmask_size;
-
- assert(!out->tile_swizzle || !image->shareable);
-}
-
static void
radv_image_alloc_fmask(struct radv_device *device,
struct radv_image *image)
{
- radv_image_get_fmask_info(device, image, image->info.samples, &image->fmask);
+ unsigned fmask_alignment = image->planes[0].surface.fmask_alignment;
- image->fmask.offset = align64(image->size, image->fmask.alignment);
- image->size = image->fmask.offset + image->fmask.size;
- image->alignment = MAX2(image->alignment, image->fmask.alignment);
-}
-
-static void
-radv_image_get_cmask_info(struct radv_device *device,
- struct radv_image *image,
- struct radv_cmask_info *out)
-{
- assert(image->plane_count == 1);
-
- if (device->physical_device->rad_info.chip_class >= GFX9) {
- out->alignment = image->planes[0].surface.cmask_alignment;
- out->size = image->planes[0].surface.cmask_size;
- return;
- }
-
- out->slice_tile_max = image->planes[0].surface.u.legacy.cmask_slice_tile_max;
- out->alignment = image->planes[0].surface.cmask_alignment;
- out->slice_size = image->planes[0].surface.cmask_slice_size;
- out->size = image->planes[0].surface.cmask_size;
+ image->fmask_offset = align64(image->size, fmask_alignment);
+ image->size = image->fmask_offset + image->planes[0].surface.fmask_size;
+ image->alignment = MAX2(image->alignment, fmask_alignment);
}
static void
radv_image_alloc_cmask(struct radv_device *device,
struct radv_image *image)
{
+ unsigned cmask_alignment = image->planes[0].surface.cmask_alignment;
+ unsigned cmask_size = image->planes[0].surface.cmask_size;
uint32_t clear_value_size = 0;
- radv_image_get_cmask_info(device, image, &image->cmask);
- image->cmask.offset = align64(image->size, image->cmask.alignment);
+ if (!cmask_size)
+ return;
+
+ assert(cmask_alignment);
+
+ image->cmask_offset = align64(image->size, cmask_alignment);
/* + 8 for storing the clear values */
if (!image->clear_value_offset) {
- image->clear_value_offset = image->cmask.offset + image->cmask.size;
+ image->clear_value_offset = image->cmask_offset + cmask_size;
clear_value_size = 8;
}
- image->size = image->cmask.offset + image->cmask.size + clear_value_size;
- image->alignment = MAX2(image->alignment, image->cmask.alignment);
+ image->size = image->cmask_offset + cmask_size + clear_value_size;
+ image->alignment = MAX2(image->alignment, cmask_alignment);
}
static void
}
static void
-radv_image_alloc_htile(struct radv_image *image)
+radv_image_alloc_htile(struct radv_device *device, struct radv_image *image)
{
image->htile_offset = align64(image->size, image->planes[0].surface.htile_alignment);
/* + 8 for storing the clear values */
image->clear_value_offset = image->htile_offset + image->planes[0].surface.htile_size;
image->size = image->clear_value_offset + 8;
- if (radv_image_is_tc_compat_htile(image)) {
+ if (radv_image_is_tc_compat_htile(image) &&
+ device->physical_device->has_tc_compat_zrange_bug) {
/* Metadata for the TC-compatible HTILE hardware bug which
* have to be fixed by updating ZRANGE_PRECISION when doing
* fast depth clears to 0.0f.
if (radv_image_can_enable_htile(image) &&
!(device->instance->debug_flags & RADV_DEBUG_NO_HIZ)) {
image->tc_compatible_htile = image->planes[0].surface.flags & RADEON_SURF_TC_COMPATIBLE_HTILE;
- radv_image_alloc_htile(image);
+ radv_image_alloc_htile(device, image);
} else {
radv_image_disable_htile(image);
}
projects / mesa.git / blobdiff