radv: Implement VK_EXT_pipeline_creation_feedback.

Does what it says on the tin.

The per stage time is only an approximation due to linking and
the Vega merged stages.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
This commit is contained in:
Bas Nieuwenhuizen
2019-03-19 02:30:33 +01:00
parent 72e366b4c2
commit 5f5ac19f13
5 changed files with 107 additions and 9 deletions

View File

@@ -3647,7 +3647,7 @@ void radv_DestroyFence(
}
static uint64_t radv_get_current_time()
uint64_t radv_get_current_time(void)
{
struct timespec tv;
clock_gettime(CLOCK_MONOTONIC, &tv);

View File

@@ -112,6 +112,7 @@ EXTENSIONS = [
Extension('VK_EXT_memory_budget', 1, True),
Extension('VK_EXT_memory_priority', 1, True),
Extension('VK_EXT_pci_bus_info', 2, True),
Extension('VK_EXT_pipeline_creation_feedback', 1, True),
Extension('VK_EXT_sampler_filter_minmax', 1, 'device->rad_info.chip_class >= CIK'),
Extension('VK_EXT_scalar_block_layout', 1, 'device->rad_info.chip_class >= CIK'),
Extension('VK_EXT_shader_viewport_index_layer', 1, True),

View File

@@ -2033,13 +2033,53 @@ merge_tess_info(struct shader_info *tes_info,
tes_info->tess.point_mode |= tcs_info->tess.point_mode;
}
static
void radv_init_feedback(const VkPipelineCreationFeedbackCreateInfoEXT *ext)
{
if (!ext)
return;
if (ext->pPipelineCreationFeedback) {
ext->pPipelineCreationFeedback->flags = 0;
ext->pPipelineCreationFeedback->duration = 0;
}
for (unsigned i = 0; i < ext->pipelineStageCreationFeedbackCount; ++i) {
ext->pPipelineStageCreationFeedbacks[i].flags = 0;
ext->pPipelineStageCreationFeedbacks[i].duration = 0;
}
}
static
void radv_start_feedback(VkPipelineCreationFeedbackEXT *feedback)
{
if (!feedback)
return;
feedback->duration -= radv_get_current_time();
feedback ->flags = VK_PIPELINE_CREATION_FEEDBACK_VALID_BIT_EXT;
}
static
void radv_stop_feedback(VkPipelineCreationFeedbackEXT *feedback, bool cache_hit)
{
if (!feedback)
return;
feedback->duration += radv_get_current_time();
feedback ->flags = VK_PIPELINE_CREATION_FEEDBACK_VALID_BIT_EXT |
(cache_hit ? VK_PIPELINE_CREATION_FEEDBACK_APPLICATION_PIPELINE_CACHE_HIT_BIT_EXT : 0);
}
static
void radv_create_shaders(struct radv_pipeline *pipeline,
struct radv_device *device,
struct radv_pipeline_cache *cache,
const struct radv_pipeline_key *key,
const VkPipelineShaderStageCreateInfo **pStages,
const VkPipelineCreateFlags flags)
const VkPipelineCreateFlags flags,
VkPipelineCreationFeedbackEXT *pipeline_feedback,
VkPipelineCreationFeedbackEXT **stage_feedbacks)
{
struct radv_shader_module fs_m = {0};
struct radv_shader_module *modules[MESA_SHADER_STAGES] = { 0, };
@@ -2049,6 +2089,8 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
struct radv_shader_variant_key keys[MESA_SHADER_STAGES] = {{{{0}}}};
unsigned char hash[20], gs_copy_hash[20];
radv_start_feedback(pipeline_feedback);
for (unsigned i = 0; i < MESA_SHADER_STAGES; ++i) {
if (pStages[i]) {
modules[i] = radv_shader_module_from_handle(pStages[i]->module);
@@ -2065,14 +2107,18 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
memcpy(gs_copy_hash, hash, 20);
gs_copy_hash[0] ^= 1;
bool found_in_application_cache = true;
if (modules[MESA_SHADER_GEOMETRY]) {
struct radv_shader_variant *variants[MESA_SHADER_STAGES] = {0};
radv_create_shader_variants_from_pipeline_cache(device, cache, gs_copy_hash, variants);
radv_create_shader_variants_from_pipeline_cache(device, cache, gs_copy_hash, variants,
&found_in_application_cache);
pipeline->gs_copy_shader = variants[MESA_SHADER_GEOMETRY];
}
if (radv_create_shader_variants_from_pipeline_cache(device, cache, hash, pipeline->shaders) &&
if (radv_create_shader_variants_from_pipeline_cache(device, cache, hash, pipeline->shaders,
&found_in_application_cache) &&
(!modules[MESA_SHADER_GEOMETRY] || pipeline->gs_copy_shader)) {
radv_stop_feedback(pipeline_feedback, found_in_application_cache);
return;
}
@@ -2090,6 +2136,8 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
if (!modules[i])
continue;
radv_start_feedback(stage_feedbacks[i]);
nir[i] = radv_shader_compile_to_nir(device, modules[i],
stage ? stage->pName : "main", i,
stage ? stage->pSpecializationInfo : NULL,
@@ -2101,6 +2149,8 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
if (nir[i]->info.name) {
nir[i] = nir_shader_clone(NULL, nir[i]);
}
radv_stop_feedback(stage_feedbacks[i], false);
}
if (nir[MESA_SHADER_TESS_CTRL]) {
@@ -2124,10 +2174,14 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
if (nir[MESA_SHADER_FRAGMENT]) {
if (!pipeline->shaders[MESA_SHADER_FRAGMENT]) {
radv_start_feedback(stage_feedbacks[MESA_SHADER_FRAGMENT]);
pipeline->shaders[MESA_SHADER_FRAGMENT] =
radv_shader_variant_create(device, modules[MESA_SHADER_FRAGMENT], &nir[MESA_SHADER_FRAGMENT], 1,
pipeline->layout, keys + MESA_SHADER_FRAGMENT,
&codes[MESA_SHADER_FRAGMENT], &code_sizes[MESA_SHADER_FRAGMENT]);
radv_stop_feedback(stage_feedbacks[MESA_SHADER_FRAGMENT], false);
}
/* TODO: These are no longer used as keys we should refactor this */
@@ -2146,10 +2200,15 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
struct nir_shader *combined_nir[] = {nir[MESA_SHADER_VERTEX], nir[MESA_SHADER_TESS_CTRL]};
struct radv_shader_variant_key key = keys[MESA_SHADER_TESS_CTRL];
key.tcs.vs_key = keys[MESA_SHADER_VERTEX].vs;
radv_start_feedback(stage_feedbacks[MESA_SHADER_TESS_CTRL]);
pipeline->shaders[MESA_SHADER_TESS_CTRL] = radv_shader_variant_create(device, modules[MESA_SHADER_TESS_CTRL], combined_nir, 2,
pipeline->layout,
&key, &codes[MESA_SHADER_TESS_CTRL],
&code_sizes[MESA_SHADER_TESS_CTRL]);
radv_stop_feedback(stage_feedbacks[MESA_SHADER_TESS_CTRL], false);
}
modules[MESA_SHADER_VERTEX] = NULL;
keys[MESA_SHADER_TESS_EVAL].tes.num_patches = pipeline->shaders[MESA_SHADER_TESS_CTRL]->info.tcs.num_patches;
@@ -2160,10 +2219,15 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
gl_shader_stage pre_stage = modules[MESA_SHADER_TESS_EVAL] ? MESA_SHADER_TESS_EVAL : MESA_SHADER_VERTEX;
if (!pipeline->shaders[MESA_SHADER_GEOMETRY]) {
struct nir_shader *combined_nir[] = {nir[pre_stage], nir[MESA_SHADER_GEOMETRY]};
radv_start_feedback(stage_feedbacks[MESA_SHADER_GEOMETRY]);
pipeline->shaders[MESA_SHADER_GEOMETRY] = radv_shader_variant_create(device, modules[MESA_SHADER_GEOMETRY], combined_nir, 2,
pipeline->layout,
&keys[pre_stage] , &codes[MESA_SHADER_GEOMETRY],
&code_sizes[MESA_SHADER_GEOMETRY]);
radv_stop_feedback(stage_feedbacks[MESA_SHADER_GEOMETRY], false);
}
modules[pre_stage] = NULL;
}
@@ -2177,10 +2241,15 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
keys[MESA_SHADER_TESS_EVAL].tes.num_patches = pipeline->shaders[MESA_SHADER_TESS_CTRL]->info.tcs.num_patches;
keys[MESA_SHADER_TESS_EVAL].tes.tcs_num_outputs = util_last_bit64(pipeline->shaders[MESA_SHADER_TESS_CTRL]->info.info.tcs.outputs_written);
}
radv_start_feedback(stage_feedbacks[i]);
pipeline->shaders[i] = radv_shader_variant_create(device, modules[i], &nir[i], 1,
pipeline->layout,
keys + i, &codes[i],
&code_sizes[i]);
radv_stop_feedback(stage_feedbacks[i], false);
}
}
@@ -2230,6 +2299,8 @@ void radv_create_shaders(struct radv_pipeline *pipeline,
if (fs_m.nir)
ralloc_free(fs_m.nir);
radv_stop_feedback(pipeline_feedback, false);
}
static uint32_t
@@ -3591,14 +3662,23 @@ radv_pipeline_init(struct radv_pipeline *pipeline,
struct radv_blend_state blend = radv_pipeline_init_blend_state(pipeline, pCreateInfo, extra);
const VkPipelineCreationFeedbackCreateInfoEXT *creation_feedback =
vk_find_struct_const(pCreateInfo->pNext, PIPELINE_CREATION_FEEDBACK_CREATE_INFO_EXT);
radv_init_feedback(creation_feedback);
VkPipelineCreationFeedbackEXT *pipeline_feedback = creation_feedback ? creation_feedback->pPipelineCreationFeedback : NULL;
const VkPipelineShaderStageCreateInfo *pStages[MESA_SHADER_STAGES] = { 0, };
VkPipelineCreationFeedbackEXT *stage_feedbacks[MESA_SHADER_STAGES];
for (uint32_t i = 0; i < pCreateInfo->stageCount; i++) {
gl_shader_stage stage = ffs(pCreateInfo->pStages[i].stage) - 1;
pStages[stage] = &pCreateInfo->pStages[i];
if(creation_feedback)
stage_feedbacks[stage] = &creation_feedback->pPipelineStageCreationFeedbacks[i];
}
struct radv_pipeline_key key = radv_generate_graphics_pipeline_key(pipeline, pCreateInfo, &blend, has_view_index);
radv_create_shaders(pipeline, device, cache, &key, pStages, pCreateInfo->flags);
radv_create_shaders(pipeline, device, cache, &key, pStages, pCreateInfo->flags, pipeline_feedback, stage_feedbacks);
pipeline->graphics.spi_baryc_cntl = S_0286E0_FRONT_FACE_ALL_BITS(1);
radv_pipeline_init_multisample_state(pipeline, &blend, pCreateInfo);
@@ -3821,6 +3901,7 @@ static VkResult radv_compute_pipeline_create(
RADV_FROM_HANDLE(radv_device, device, _device);
RADV_FROM_HANDLE(radv_pipeline_cache, cache, _cache);
const VkPipelineShaderStageCreateInfo *pStages[MESA_SHADER_STAGES] = { 0, };
VkPipelineCreationFeedbackEXT *stage_feedbacks[MESA_SHADER_STAGES];
struct radv_pipeline *pipeline;
VkResult result;
@@ -3833,8 +3914,16 @@ static VkResult radv_compute_pipeline_create(
pipeline->layout = radv_pipeline_layout_from_handle(pCreateInfo->layout);
assert(pipeline->layout);
const VkPipelineCreationFeedbackCreateInfoEXT *creation_feedback =
vk_find_struct_const(pCreateInfo->pNext, PIPELINE_CREATION_FEEDBACK_CREATE_INFO_EXT);
radv_init_feedback(creation_feedback);
VkPipelineCreationFeedbackEXT *pipeline_feedback = creation_feedback ? creation_feedback->pPipelineCreationFeedback : NULL;
if (creation_feedback)
stage_feedbacks[MESA_SHADER_COMPUTE] = &creation_feedback->pPipelineStageCreationFeedbacks[0];
pStages[MESA_SHADER_COMPUTE] = &pCreateInfo->stage;
radv_create_shaders(pipeline, device, cache, &(struct radv_pipeline_key) {0}, pStages, pCreateInfo->flags);
radv_create_shaders(pipeline, device, cache, &(struct radv_pipeline_key) {0}, pStages, pCreateInfo->flags, pipeline_feedback, stage_feedbacks);
pipeline->user_data_0[MESA_SHADER_COMPUTE] = radv_pipeline_stage_to_user_data_0(pipeline, MESA_SHADER_COMPUTE, device->physical_device->rad_info.chip_class);
pipeline->need_indirect_descriptor_sets |= pipeline->shaders[MESA_SHADER_COMPUTE]->info.need_indirect_descriptor_sets;

View File

@@ -255,18 +255,23 @@ bool
radv_create_shader_variants_from_pipeline_cache(struct radv_device *device,
struct radv_pipeline_cache *cache,
const unsigned char *sha1,
struct radv_shader_variant **variants)
struct radv_shader_variant **variants,
bool *found_in_application_cache)
{
struct cache_entry *entry;
if (!cache)
if (!cache) {
cache = device->mem_cache;
*found_in_application_cache = false;
}
pthread_mutex_lock(&cache->mutex);
entry = radv_pipeline_cache_search_unlocked(cache, sha1);
if (!entry) {
*found_in_application_cache = false;
/* Don't cache when we want debug info, since this isn't
* present in the cache.
*/

View File

@@ -396,7 +396,8 @@ bool
radv_create_shader_variants_from_pipeline_cache(struct radv_device *device,
struct radv_pipeline_cache *cache,
const unsigned char *sha1,
struct radv_shader_variant **variants);
struct radv_shader_variant **variants,
bool *found_in_application_cache);
void
radv_pipeline_cache_insert_shaders(struct radv_device *device,
@@ -1961,6 +1962,8 @@ void radv_nir_shader_info_init(struct radv_shader_info *info);
struct radeon_winsys_sem;
uint64_t radv_get_current_time(void);
#define RADV_DEFINE_HANDLE_CASTS(__radv_type, __VkType) \
\
static inline struct __radv_type * \