anv: Refactor pipeline l3 config setup

Now that we're using gen_l3_config.c, we no longer have one set of l3
config functions per gen and we can simplify a bit.  Also, we know that
only compute uses SLM so we don't need to look for it in all of the stages.

Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
This commit is contained in:
Jason Ekstrand
2016-08-22 16:56:48 -07:00
parent 6448c0e324
commit 42d03c204c
5 changed files with 25 additions and 67 deletions

View File

@@ -44,8 +44,6 @@ void genX(cmd_buffer_apply_pipe_flushes)(struct anv_cmd_buffer *cmd_buffer);
void genX(flush_pipeline_select_3d)(struct anv_cmd_buffer *cmd_buffer);
void genX(flush_pipeline_select_gpgpu)(struct anv_cmd_buffer *cmd_buffer);
void genX(setup_pipeline_l3_config)(struct anv_pipeline *pipeline);
void genX(cmd_buffer_config_l3)(struct anv_cmd_buffer *cmd_buffer,
const struct anv_pipeline *pipeline);

View File

@@ -28,6 +28,7 @@
#include <fcntl.h>
#include "util/mesa-sha1.h"
#include "common/gen_l3_config.h"
#include "anv_private.h"
#include "brw_nir.h"
#include "anv_nir.h"
@@ -802,29 +803,6 @@ anv_pipeline_compile_cs(struct anv_pipeline *pipeline,
return VK_SUCCESS;
}
void
anv_setup_pipeline_l3_config(struct anv_pipeline *pipeline)
{
const struct gen_device_info *devinfo = &pipeline->device->info;
switch (devinfo->gen) {
case 7:
if (devinfo->is_haswell)
gen75_setup_pipeline_l3_config(pipeline);
else
gen7_setup_pipeline_l3_config(pipeline);
break;
case 8:
gen8_setup_pipeline_l3_config(pipeline);
break;
case 9:
gen9_setup_pipeline_l3_config(pipeline);
break;
default:
unreachable("unsupported gen\n");
}
}
void
anv_compute_urb_partition(struct anv_pipeline *pipeline)
{
@@ -1151,6 +1129,26 @@ anv_pipeline_validate_create_info(const VkGraphicsPipelineCreateInfo *info)
}
}
/**
* Calculate the desired L3 partitioning based on the current state of the
* pipeline. For now this simply returns the conservative defaults calculated
* by get_default_l3_weights(), but we could probably do better by gathering
* more statistics from the pipeline state (e.g. guess of expected URB usage
* and bound surfaces), or by using feed-back from performance counters.
*/
void
anv_pipeline_setup_l3_config(struct anv_pipeline *pipeline, bool needs_slm)
{
const struct gen_device_info *devinfo = &pipeline->device->info;
const struct gen_l3_weights w =
gen_get_default_l3_weights(devinfo, pipeline->needs_data_cache, needs_slm);
pipeline->urb.l3_config = gen_get_l3_config(devinfo, w);
pipeline->urb.total_size =
gen_get_l3_config_urb_size(devinfo, pipeline->urb.l3_config);
}
VkResult
anv_pipeline_init(struct anv_pipeline *pipeline,
struct anv_device *device,
@@ -1243,7 +1241,7 @@ anv_pipeline_init(struct anv_pipeline *pipeline,
assert(extra->disable_vs);
}
anv_setup_pipeline_l3_config(pipeline);
anv_pipeline_setup_l3_config(pipeline, false);
anv_compute_urb_partition(pipeline);
const VkPipelineVertexInputStateCreateInfo *vi_info =

View File

@@ -1648,7 +1648,7 @@ void
anv_compute_urb_partition(struct anv_pipeline *pipeline);
void
anv_setup_pipeline_l3_config(struct anv_pipeline *pipeline);
anv_pipeline_setup_l3_config(struct anv_pipeline *pipeline, bool needs_slm);
/**
* Subsurface of an anv_image.

View File

@@ -27,33 +27,6 @@
#include "genxml/gen_macros.h"
#include "genxml/genX_pack.h"
/**
* Calculate the desired L3 partitioning based on the current state of the
* pipeline. For now this simply returns the conservative defaults calculated
* by get_default_l3_weights(), but we could probably do better by gathering
* more statistics from the pipeline state (e.g. guess of expected URB usage
* and bound surfaces), or by using feed-back from performance counters.
*/
static struct gen_l3_weights
get_pipeline_state_l3_weights(const struct anv_pipeline *pipeline)
{
bool needs_dc = false, needs_slm = false;
for (unsigned i = 0; i < MESA_SHADER_STAGES; i++) {
if (!anv_pipeline_has_stage(pipeline, i))
continue;
const struct brw_stage_prog_data *prog_data =
anv_shader_bin_get_prog_data(pipeline->shaders[i]);
needs_dc |= pipeline->needs_data_cache;
needs_slm |= prog_data->total_shared;
}
return gen_get_default_l3_weights(&pipeline->device->info,
needs_dc, needs_slm);
}
#define emit_lri(batch, reg, imm) \
anv_batch_emit(batch, GENX(MI_LOAD_REGISTER_IMM), lri) { \
lri.RegisterOffset = __anv_reg_num(reg); \
@@ -207,17 +180,6 @@ setup_l3_config(struct anv_cmd_buffer *cmd_buffer/*, struct brw_context *brw*/,
}
void
genX(setup_pipeline_l3_config)(struct anv_pipeline *pipeline)
{
const struct gen_l3_weights w = get_pipeline_state_l3_weights(pipeline);
const struct gen_device_info *devinfo = &pipeline->device->info;
pipeline->urb.l3_config = gen_get_l3_config(devinfo, w);
pipeline->urb.total_size =
gen_get_l3_config_urb_size(devinfo, pipeline->urb.l3_config);
}
void
genX(cmd_buffer_config_l3)(struct anv_cmd_buffer *cmd_buffer,
const struct anv_pipeline *pipeline)

View File

@@ -85,10 +85,10 @@ genX(compute_pipeline_create)(
pipeline->use_repclear = false;
anv_setup_pipeline_l3_config(pipeline);
const struct brw_cs_prog_data *cs_prog_data = get_cs_prog_data(pipeline);
anv_pipeline_setup_l3_config(pipeline, cs_prog_data->base.total_shared > 0);
uint32_t group_size = cs_prog_data->local_size[0] *
cs_prog_data->local_size[1] * cs_prog_data->local_size[2];
uint32_t remainder = group_size & (cs_prog_data->simd_size - 1);