anv: Stop resolving CCS implicitly

With an earlier patch from this series, resolves are additionally
performed on layout transitions. Remove the now unnecessary implicit
resolves within render passes.

Signed-off-by: Nanley Chery <nanley.g.chery@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This commit is contained in:
Nanley Chery
2017-03-17 22:36:05 -07:00
committed by Jason Ekstrand
parent 5ba93e6f5a
commit 597ff919e7
3 changed files with 5 additions and 169 deletions

View File

@@ -1502,150 +1502,16 @@ anv_image_fast_clear(struct anv_cmd_buffer *cmd_buffer,
ANV_PIPE_RENDER_TARGET_CACHE_FLUSH_BIT | ANV_PIPE_CS_STALL_BIT;
}
static void
ccs_resolve_attachment(struct anv_cmd_buffer *cmd_buffer,
uint32_t att)
{
struct anv_framebuffer *fb = cmd_buffer->state.framebuffer;
struct anv_attachment_state *att_state =
&cmd_buffer->state.attachments[att];
if (att_state->aux_usage == ISL_AUX_USAGE_NONE ||
att_state->aux_usage == ISL_AUX_USAGE_MCS)
return; /* Nothing to resolve */
assert(att_state->aux_usage == ISL_AUX_USAGE_CCS_E ||
att_state->aux_usage == ISL_AUX_USAGE_CCS_D);
struct anv_render_pass *pass = cmd_buffer->state.pass;
const uint32_t subpass_idx = anv_get_subpass_id(&cmd_buffer->state);
/* Scan forward to see what all ways this attachment will be used.
* Ideally, we would like to resolve in the same subpass as the last write
* of a particular attachment. That way we only resolve once but it's
* still hot in the cache.
*/
bool found_draw = false;
enum anv_subpass_usage usage = 0;
for (uint32_t s = subpass_idx + 1; s < pass->subpass_count; s++) {
usage |= pass->attachments[att].subpass_usage[s];
if (usage & (ANV_SUBPASS_USAGE_DRAW | ANV_SUBPASS_USAGE_RESOLVE_DST)) {
/* We found another subpass that draws to this attachment. We'll
* wait to resolve until then.
*/
found_draw = true;
break;
}
}
struct anv_image_view *iview = fb->attachments[att];
const struct anv_image *image = iview->image;
assert(image->aspects == VK_IMAGE_ASPECT_COLOR_BIT);
enum blorp_fast_clear_op resolve_op = BLORP_FAST_CLEAR_OP_NONE;
if (!found_draw) {
/* This is the last subpass that writes to this attachment so we need to
* resolve here. Ideally, we would like to only resolve if the storeOp
* is set to VK_ATTACHMENT_STORE_OP_STORE. However, we need to ensure
* that the CCS bits are set to "resolved" because there may be copy or
* blit operations (which may ignore CCS) between now and the next time
* we render and we need to ensure that anything they write will be
* respected in the next render. Unfortunately, the hardware does not
* provide us with any sort of "invalidate" pass that sets the CCS to
* "resolved" without writing to the render target.
*/
if (iview->image->aux_usage != ISL_AUX_USAGE_CCS_E) {
/* The image destination surface doesn't support compression outside
* the render pass. We need a full resolve.
*/
resolve_op = BLORP_FAST_CLEAR_OP_RESOLVE_FULL;
} else if (att_state->fast_clear) {
/* We don't know what to do with clear colors outside the render
* pass. We need a partial resolve. Only transparent black is
* built into the surface state object and thus no resolve is
* required for this case.
*/
if (att_state->clear_value.color.uint32[0] ||
att_state->clear_value.color.uint32[1] ||
att_state->clear_value.color.uint32[2] ||
att_state->clear_value.color.uint32[3])
resolve_op = BLORP_FAST_CLEAR_OP_RESOLVE_PARTIAL;
} else {
/* The image "natively" supports all the compression we care about
* and we don't need to resolve at all. If this is the case, we also
* don't need to resolve for any of the input attachment cases below.
*/
}
} else if (usage & ANV_SUBPASS_USAGE_INPUT) {
/* Input attachments are clear-color aware so, at least on Sky Lake, we
* can frequently sample from them with no resolves at all.
*/
if (att_state->aux_usage != att_state->input_aux_usage) {
assert(att_state->input_aux_usage == ISL_AUX_USAGE_NONE);
resolve_op = BLORP_FAST_CLEAR_OP_RESOLVE_FULL;
} else if (!att_state->clear_color_is_zero_one) {
/* Sky Lake PRM, Vol. 2d, RENDER_SURFACE_STATE::Red Clear Color:
*
* "If Number of Multisamples is MULTISAMPLECOUNT_1 AND if this RT
* is fast cleared with non-0/1 clear value, this RT must be
* partially resolved (refer to Partial Resolve operation) before
* binding this surface to Sampler."
*/
resolve_op = BLORP_FAST_CLEAR_OP_RESOLVE_PARTIAL;
}
}
if (resolve_op == BLORP_FAST_CLEAR_OP_NONE)
return;
/* From the Sky Lake PRM Vol. 7, "Render Target Resolve":
*
* "When performing a render target resolve, PIPE_CONTROL with end of
* pipe sync must be delivered."
*
* This comment is a bit cryptic and doesn't really tell you what's going
* or what's really needed. It appears that fast clear ops are not
* properly synchronized with other drawing. We need to use a PIPE_CONTROL
* to ensure that the contents of the previous draw hit the render target
* before we resolve and then use a second PIPE_CONTROL after the resolve
* to ensure that it is completed before any additional drawing occurs.
*/
cmd_buffer->state.pending_pipe_bits |=
ANV_PIPE_RENDER_TARGET_CACHE_FLUSH_BIT | ANV_PIPE_CS_STALL_BIT;
const uint32_t aux_layers =
anv_image_aux_layers(image, iview->isl.base_level);
anv_ccs_resolve(cmd_buffer, att_state->color_rt_state, image,
iview->isl.base_level, MIN2(fb->layers, aux_layers),
resolve_op);
cmd_buffer->state.pending_pipe_bits |=
ANV_PIPE_RENDER_TARGET_CACHE_FLUSH_BIT | ANV_PIPE_CS_STALL_BIT;
/* Once we've done any sort of resolve, we're no longer fast-cleared */
att_state->fast_clear = false;
if (att_state->aux_usage == ISL_AUX_USAGE_CCS_D)
att_state->aux_usage = ISL_AUX_USAGE_NONE;
}
void
anv_cmd_buffer_resolve_subpass(struct anv_cmd_buffer *cmd_buffer)
{
struct anv_framebuffer *fb = cmd_buffer->state.framebuffer;
struct anv_subpass *subpass = cmd_buffer->state.subpass;
for (uint32_t i = 0; i < subpass->color_count; ++i) {
const uint32_t att = subpass->color_attachments[i].attachment;
if (att == VK_ATTACHMENT_UNUSED)
continue;
assert(att < cmd_buffer->state.pass->attachment_count);
ccs_resolve_attachment(cmd_buffer, att);
}
if (subpass->has_resolve) {
struct blorp_batch batch;
blorp_batch_init(&cmd_buffer->device->blorp, &batch, cmd_buffer, 0);
/* We are about to do some MSAA resolves. We need to flush so that the
* result of writes to the MSAA color attachments show up in the sampler
* when we blit to the single-sampled resolve target.
@@ -1687,9 +1553,6 @@ anv_cmd_buffer_resolve_subpass(struct anv_cmd_buffer *cmd_buffer)
assert(src_iview->aspect_mask == dst_iview->aspect_mask);
struct blorp_batch batch;
blorp_batch_init(&cmd_buffer->device->blorp, &batch, cmd_buffer, 0);
resolve_image(&batch, src_iview->image, src_aux_usage,
src_iview->isl.base_level,
src_iview->isl.base_array_layer,
@@ -1700,13 +1563,10 @@ anv_cmd_buffer_resolve_subpass(struct anv_cmd_buffer *cmd_buffer)
render_area.offset.x, render_area.offset.y,
render_area.offset.x, render_area.offset.y,
render_area.extent.width, render_area.extent.height);
blorp_batch_finish(&batch);
ccs_resolve_attachment(cmd_buffer, dst_att);
}
}
blorp_batch_finish(&batch);
}
}
void

View File

@@ -73,10 +73,6 @@ VkResult anv_CreateRenderPass(
}
anv_multialloc_add(&ma, &subpass_attachments, subpass_attachment_count);
enum anv_subpass_usage *subpass_usages;
anv_multialloc_add(&ma, &subpass_usages,
pCreateInfo->subpassCount * pCreateInfo->attachmentCount);
if (!anv_multialloc_alloc2(&ma, &device->alloc, pAllocator,
VK_SYSTEM_ALLOCATION_SCOPE_OBJECT))
return vk_error(VK_ERROR_OUT_OF_HOST_MEMORY);
@@ -102,8 +98,6 @@ VkResult anv_CreateRenderPass(
att->initial_layout = pCreateInfo->pAttachments[i].initialLayout;
att->final_layout = pCreateInfo->pAttachments[i].finalLayout;
att->first_subpass_layout = VK_IMAGE_LAYOUT_UNDEFINED;
att->subpass_usage = subpass_usages;
subpass_usages += pass->subpass_count;
}
bool has_color = false, has_depth = false, has_input = false;
@@ -127,7 +121,6 @@ VkResult anv_CreateRenderPass(
if (a != VK_ATTACHMENT_UNUSED) {
has_input = true;
pass->attachments[a].usage |= VK_IMAGE_USAGE_INPUT_ATTACHMENT_BIT;
pass->attachments[a].subpass_usage[i] |= ANV_SUBPASS_USAGE_INPUT;
pass->attachments[a].last_subpass_idx = i;
init_first_subpass_layout(&pass->attachments[a],
@@ -149,7 +142,6 @@ VkResult anv_CreateRenderPass(
if (a != VK_ATTACHMENT_UNUSED) {
has_color = true;
pass->attachments[a].usage |= VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT;
pass->attachments[a].subpass_usage[i] |= ANV_SUBPASS_USAGE_DRAW;
pass->attachments[a].last_subpass_idx = i;
init_first_subpass_layout(&pass->attachments[a],
@@ -172,11 +164,6 @@ VkResult anv_CreateRenderPass(
pass->attachments[color_att].usage |=
VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
pass->attachments[a].usage |= VK_IMAGE_USAGE_TRANSFER_DST_BIT;
pass->attachments[color_att].subpass_usage[i] |=
ANV_SUBPASS_USAGE_RESOLVE_SRC;
pass->attachments[a].subpass_usage[i] |=
ANV_SUBPASS_USAGE_RESOLVE_DST;
pass->attachments[a].last_subpass_idx = i;
init_first_subpass_layout(&pass->attachments[a],
@@ -193,7 +180,6 @@ VkResult anv_CreateRenderPass(
has_depth = true;
pass->attachments[a].usage |=
VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT;
pass->attachments[a].subpass_usage[i] |= ANV_SUBPASS_USAGE_DRAW;
pass->attachments[a].last_subpass_idx = i;
init_first_subpass_layout(&pass->attachments[a],

View File

@@ -2290,13 +2290,6 @@ anv_subpass_view_count(const struct anv_subpass *subpass)
return MAX2(1, _mesa_bitcount(subpass->view_mask));
}
enum anv_subpass_usage {
ANV_SUBPASS_USAGE_DRAW = (1 << 0),
ANV_SUBPASS_USAGE_INPUT = (1 << 1),
ANV_SUBPASS_USAGE_RESOLVE_SRC = (1 << 2),
ANV_SUBPASS_USAGE_RESOLVE_DST = (1 << 3),
};
struct anv_render_pass_attachment {
/* TODO: Consider using VkAttachmentDescription instead of storing each of
* its members individually.
@@ -2311,9 +2304,6 @@ struct anv_render_pass_attachment {
VkImageLayout final_layout;
VkImageLayout first_subpass_layout;
/* An array, indexed by subpass id, of how the attachment will be used. */
enum anv_subpass_usage * subpass_usage;
/* The subpass id in which the attachment will be used last. */
uint32_t last_subpass_idx;
};