mesa/src/intel/vulkan/anv_nir.h

102 lines
4 KiB
C
Raw Normal View History

/*
* Copyright © 2015 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#ifndef ANV_NIR_H
#define ANV_NIR_H
#include "nir/nir.h"
#include "anv_private.h"
#ifdef __cplusplus
extern "C" {
#endif
bool anv_check_for_primitive_replication(struct anv_device *device,
VkShaderStageFlags stages,
nir_shader **shaders,
uint32_t view_mask);
anv/gen12: Lower VK_KHR_multiview using Primitive Replication Identify if view_index is used only for position calculation, and use Primitive Replication to implement Multiview in Gen12. This feature allows storing per-view position information in a single execution of the shader, treating position as an array. The shader is transformed by adding a for-loop around it, that have an iteration per active view (in the view_mask). Stores to the position now store into the position array for the current index in the loop, and load_view_index() will return the view index corresponding to the current index in the loop. The feature is controlled by setting the environment variable ANV_PRIMITIVE_REPLICATION_MAX_VIEWS, which defaults to 2 if unset. For pipelines with view counts larger than that, the regular instancing will be used instead of Primitive Replication. To disable it completely set the variable to 0. v2: Don't assume position is set in vertex shader; remove only stores for position; don't apply optimizations since other passes will do; clone shader body without extract/reinsert; don't use last_block (potentially stale). (Jason) Fix view_index immediate to contain the view index, not its order. Check for maximum number of views supported. Add guard for gen12. v3: Clone the entire shader function and change it before reinsert; disable optimization when shader has memory writes. (Jason) Use a single environment variable with _DEBUG on the name. v4: Change to use new nir_deref_instr. When removing stores, look for mode nir_var_shader_out instead of the walking the list of outputs. Ensure unused derefs are removed in the non-position part of the shader. Remove dead control flow when identifying if can use or not primitive replication. v5: Consider all the active shaders (including fragment) when deciding that Primitive Replication can be used. Change environment variable to ANV_PRIMITIVE_REPLICATION. Squash the emission of 3DSTATE_PRIMITIVE_REPLICATION into this patch. Disable Prim Rep in blorp_exec_3d. v6: Use a loop around the shader, instead of manually unrolling, since the regular unroll pass will kick in. Document that we don't expect to see copy_deref or load_deref involving the position variable. Recover use_primitive_replication value when loading pipeline from the cache. Set VARYING_SLOT_LAYER to 0 in the shader. Earlier versions were relying on ForceZeroRTAIndexEnable but that might not be sufficient. Disable Prim Rep in cmd_buffer_so_memcpy. v7: Don't use Primitive Replication if position is not set, fallback to instancing; change environment variable to be ANV_PRIMITVE_REPLICATION_MAX_VIEWS and default it to 2 based on experiments. Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com> Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2313> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2313>
2018-03-27 10:10:34 -07:00
bool anv_nir_lower_multiview(nir_shader *shader, uint32_t view_mask,
bool use_primitive_replication);
bool anv_nir_lower_ycbcr_textures(nir_shader *shader,
anv: add dynamic buffer offsets support with independent sets With independent sets, we're not able to compute immediate values for the index at which to read anv_push_constants::dynamic_offsets to get the offset of a dynamic buffer. This is because the pipeline layout may not have all the descriptor set layouts when we compile the shader. To solve that issue, we insert a layer of indirection. This reworks the dynamic buffer offset storage with a 2D array in anv_cmd_pipeline_state : dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS] When the pipeline or the dynamic buffer offsets are updated, we flatten that array into the anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array. For shaders compiled with independent sets, the bottom 6 bits of element X in anv_push_constants::desc_sets[] is used to specify the base offsets into the anv_push_constants::dynamic_offsets[] for the set X. The computation in the shader is now something like : base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx] It was suggested by Faith to use a different push constant buffer with dynamic_offsets prepared for each stage when using independent sets instead, but it feels easier to understand this way. And there is some room for optimization if you are set X and that you know all the sets in the range [0, X], then you can still avoid the indirection. Separate push constant allocations per stage do have a CPU cost. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Emma Anholt <emma@anholt.net> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
2022-04-06 18:12:02 +03:00
const struct anv_pipeline_sets_layout *layout);
static inline nir_address_format
anv_nir_ssbo_addr_format(const struct anv_physical_device *pdevice,
bool robust_buffer_access)
{
if (robust_buffer_access)
return nir_address_format_64bit_bounded_global;
else
return nir_address_format_64bit_global_32bit_offset;
}
static inline nir_address_format
anv_nir_ubo_addr_format(const struct anv_physical_device *pdevice,
bool robust_buffer_access)
{
if (robust_buffer_access)
return nir_address_format_64bit_bounded_global;
else
return nir_address_format_64bit_global_32bit_offset;
}
bool anv_nir_lower_ubo_loads(nir_shader *shader);
void anv_nir_apply_pipeline_layout(nir_shader *shader,
const struct anv_physical_device *pdevice,
bool robust_buffer_access,
anv: add dynamic buffer offsets support with independent sets With independent sets, we're not able to compute immediate values for the index at which to read anv_push_constants::dynamic_offsets to get the offset of a dynamic buffer. This is because the pipeline layout may not have all the descriptor set layouts when we compile the shader. To solve that issue, we insert a layer of indirection. This reworks the dynamic buffer offset storage with a 2D array in anv_cmd_pipeline_state : dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS] When the pipeline or the dynamic buffer offsets are updated, we flatten that array into the anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array. For shaders compiled with independent sets, the bottom 6 bits of element X in anv_push_constants::desc_sets[] is used to specify the base offsets into the anv_push_constants::dynamic_offsets[] for the set X. The computation in the shader is now something like : base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx] It was suggested by Faith to use a different push constant buffer with dynamic_offsets prepared for each stage when using independent sets instead, but it feels easier to understand this way. And there is some room for optimization if you are set X and that you know all the sets in the range [0, X], then you can still avoid the indirection. Separate push constant allocations per stage do have a CPU cost. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Emma Anholt <emma@anholt.net> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
2022-04-06 18:12:02 +03:00
bool independent_sets,
const struct anv_pipeline_sets_layout *layout,
struct anv_pipeline_bind_map *map);
void anv_nir_compute_push_layout(nir_shader *nir,
const struct anv_physical_device *pdevice,
bool robust_buffer_access,
struct brw_stage_prog_data *prog_data,
struct anv_pipeline_bind_map *map,
void *mem_ctx);
void anv_nir_validate_push_layout(struct brw_stage_prog_data *prog_data,
struct anv_pipeline_bind_map *map);
bool anv_nir_add_base_work_group_id(nir_shader *shader);
uint32_t anv_nir_compute_used_push_descriptors(nir_shader *shader,
anv: add dynamic buffer offsets support with independent sets With independent sets, we're not able to compute immediate values for the index at which to read anv_push_constants::dynamic_offsets to get the offset of a dynamic buffer. This is because the pipeline layout may not have all the descriptor set layouts when we compile the shader. To solve that issue, we insert a layer of indirection. This reworks the dynamic buffer offset storage with a 2D array in anv_cmd_pipeline_state : dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS] When the pipeline or the dynamic buffer offsets are updated, we flatten that array into the anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array. For shaders compiled with independent sets, the bottom 6 bits of element X in anv_push_constants::desc_sets[] is used to specify the base offsets into the anv_push_constants::dynamic_offsets[] for the set X. The computation in the shader is now something like : base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx] It was suggested by Faith to use a different push constant buffer with dynamic_offsets prepared for each stage when using independent sets instead, but it feels easier to understand this way. And there is some room for optimization if you are set X and that you know all the sets in the range [0, X], then you can still avoid the indirection. Separate push constant allocations per stage do have a CPU cost. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Emma Anholt <emma@anholt.net> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
2022-04-06 18:12:02 +03:00
const struct anv_pipeline_sets_layout *layout);
bool anv_nir_loads_push_desc_buffer(nir_shader *nir,
anv: add dynamic buffer offsets support with independent sets With independent sets, we're not able to compute immediate values for the index at which to read anv_push_constants::dynamic_offsets to get the offset of a dynamic buffer. This is because the pipeline layout may not have all the descriptor set layouts when we compile the shader. To solve that issue, we insert a layer of indirection. This reworks the dynamic buffer offset storage with a 2D array in anv_cmd_pipeline_state : dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS] When the pipeline or the dynamic buffer offsets are updated, we flatten that array into the anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array. For shaders compiled with independent sets, the bottom 6 bits of element X in anv_push_constants::desc_sets[] is used to specify the base offsets into the anv_push_constants::dynamic_offsets[] for the set X. The computation in the shader is now something like : base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx] It was suggested by Faith to use a different push constant buffer with dynamic_offsets prepared for each stage when using independent sets instead, but it feels easier to understand this way. And there is some room for optimization if you are set X and that you know all the sets in the range [0, X], then you can still avoid the indirection. Separate push constant allocations per stage do have a CPU cost. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Emma Anholt <emma@anholt.net> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
2022-04-06 18:12:02 +03:00
const struct anv_pipeline_sets_layout *layout,
const struct anv_pipeline_bind_map *bind_map);
uint32_t anv_nir_push_desc_ubo_fully_promoted(nir_shader *nir,
anv: add dynamic buffer offsets support with independent sets With independent sets, we're not able to compute immediate values for the index at which to read anv_push_constants::dynamic_offsets to get the offset of a dynamic buffer. This is because the pipeline layout may not have all the descriptor set layouts when we compile the shader. To solve that issue, we insert a layer of indirection. This reworks the dynamic buffer offset storage with a 2D array in anv_cmd_pipeline_state : dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS] When the pipeline or the dynamic buffer offsets are updated, we flatten that array into the anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array. For shaders compiled with independent sets, the bottom 6 bits of element X in anv_push_constants::desc_sets[] is used to specify the base offsets into the anv_push_constants::dynamic_offsets[] for the set X. The computation in the shader is now something like : base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx] It was suggested by Faith to use a different push constant buffer with dynamic_offsets prepared for each stage when using independent sets instead, but it feels easier to understand this way. And there is some room for optimization if you are set X and that you know all the sets in the range [0, X], then you can still avoid the indirection. Separate push constant allocations per stage do have a CPU cost. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Emma Anholt <emma@anholt.net> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
2022-04-06 18:12:02 +03:00
const struct anv_pipeline_sets_layout *layout,
const struct anv_pipeline_bind_map *bind_map);
#ifdef __cplusplus
}
#endif
#endif /* ANV_NIR_H */