radv: move calculating vs out info regs into pipeline.
This moves some calculations of register values into the pipeline construction, it saves looking at outinfo in the cmd buffer emit. Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Signed-off-by: Dave Airlie <airlied@redhat.com>
This commit is contained in:
@@ -698,28 +698,15 @@ radv_emit_shaders_prefetch(struct radv_cmd_buffer *cmd_buffer,
|
||||
static void
|
||||
radv_emit_hw_vs(struct radv_cmd_buffer *cmd_buffer,
|
||||
struct radv_pipeline *pipeline,
|
||||
struct radv_shader_variant *shader,
|
||||
struct ac_vs_output_info *outinfo)
|
||||
struct radv_shader_variant *shader)
|
||||
{
|
||||
uint64_t va = radv_buffer_get_va(shader->bo) + shader->bo_offset;
|
||||
unsigned export_count;
|
||||
|
||||
export_count = MAX2(1, outinfo->param_exports);
|
||||
radeon_set_context_reg(cmd_buffer->cs, R_0286C4_SPI_VS_OUT_CONFIG,
|
||||
S_0286C4_VS_EXPORT_COUNT(export_count - 1));
|
||||
pipeline->graphics.vs.spi_vs_out_config);
|
||||
|
||||
radeon_set_context_reg(cmd_buffer->cs, R_02870C_SPI_SHADER_POS_FORMAT,
|
||||
S_02870C_POS0_EXPORT_FORMAT(V_02870C_SPI_SHADER_4COMP) |
|
||||
S_02870C_POS1_EXPORT_FORMAT(outinfo->pos_exports > 1 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE) |
|
||||
S_02870C_POS2_EXPORT_FORMAT(outinfo->pos_exports > 2 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE) |
|
||||
S_02870C_POS3_EXPORT_FORMAT(outinfo->pos_exports > 3 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE));
|
||||
|
||||
pipeline->graphics.vs.spi_shader_pos_format);
|
||||
|
||||
radeon_set_sh_reg_seq(cmd_buffer->cs, R_00B120_SPI_SHADER_PGM_LO_VS, 4);
|
||||
radeon_emit(cmd_buffer->cs, va >> 8);
|
||||
@@ -735,11 +722,11 @@ radv_emit_hw_vs(struct radv_cmd_buffer *cmd_buffer,
|
||||
|
||||
|
||||
radeon_set_context_reg(cmd_buffer->cs, R_02881C_PA_CL_VS_OUT_CNTL,
|
||||
pipeline->graphics.pa_cl_vs_out_cntl);
|
||||
pipeline->graphics.vs.pa_cl_vs_out_cntl);
|
||||
|
||||
if (cmd_buffer->device->physical_device->rad_info.chip_class <= VI)
|
||||
radeon_set_context_reg(cmd_buffer->cs, R_028AB4_VGT_REUSE_OFF,
|
||||
S_028AB4_REUSE_OFF(outinfo->writes_viewport_index));
|
||||
pipeline->graphics.vs.vgt_reuse_off);
|
||||
}
|
||||
|
||||
static void
|
||||
@@ -821,7 +808,7 @@ radv_emit_vertex_shader(struct radv_cmd_buffer *cmd_buffer,
|
||||
else if (vs->info.vs.as_es)
|
||||
radv_emit_hw_es(cmd_buffer, vs, &vs->info.vs.es_info);
|
||||
else
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, vs, &vs->info.vs.outinfo);
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, vs);
|
||||
}
|
||||
|
||||
|
||||
@@ -841,7 +828,7 @@ radv_emit_tess_shaders(struct radv_cmd_buffer *cmd_buffer,
|
||||
if (tes->info.tes.as_es)
|
||||
radv_emit_hw_es(cmd_buffer, tes, &tes->info.tes.es_info);
|
||||
else
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, tes, &tes->info.tes.outinfo);
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, tes);
|
||||
}
|
||||
|
||||
radv_emit_hw_hs(cmd_buffer, tcs);
|
||||
@@ -951,7 +938,7 @@ radv_emit_geometry_shader(struct radv_cmd_buffer *cmd_buffer,
|
||||
radeon_emit(cmd_buffer->cs, gs->rsrc2);
|
||||
}
|
||||
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, pipeline->gs_copy_shader, &pipeline->gs_copy_shader->info.vs.outinfo);
|
||||
radv_emit_hw_vs(cmd_buffer, pipeline, pipeline->gs_copy_shader);
|
||||
|
||||
struct ac_userdata_info *loc = radv_lookup_user_sgpr(cmd_buffer->state.pipeline, MESA_SHADER_GEOMETRY,
|
||||
AC_UD_GS_VS_RING_STRIDE_ENTRIES);
|
||||
|
@@ -1545,7 +1545,7 @@ static void calculate_vgt_gs_mode(struct radv_pipeline *pipeline)
|
||||
}
|
||||
}
|
||||
|
||||
static void calculate_pa_cl_vs_out_cntl(struct radv_pipeline *pipeline)
|
||||
static void calculate_vs_outinfo(struct radv_pipeline *pipeline)
|
||||
{
|
||||
struct ac_vs_output_info *outinfo = get_vs_output_info(pipeline);
|
||||
|
||||
@@ -1557,7 +1557,7 @@ static void calculate_pa_cl_vs_out_cntl(struct radv_pipeline *pipeline)
|
||||
bool misc_vec_ena = outinfo->writes_pointsize ||
|
||||
outinfo->writes_layer ||
|
||||
outinfo->writes_viewport_index;
|
||||
pipeline->graphics.pa_cl_vs_out_cntl =
|
||||
pipeline->graphics.vs.pa_cl_vs_out_cntl =
|
||||
S_02881C_USE_VTX_POINT_SIZE(outinfo->writes_pointsize) |
|
||||
S_02881C_USE_VTX_RENDER_TARGET_INDX(outinfo->writes_layer) |
|
||||
S_02881C_USE_VTX_VIEWPORT_INDX(outinfo->writes_viewport_index) |
|
||||
@@ -1568,6 +1568,21 @@ static void calculate_pa_cl_vs_out_cntl(struct radv_pipeline *pipeline)
|
||||
cull_dist_mask << 8 |
|
||||
clip_dist_mask;
|
||||
|
||||
pipeline->graphics.vs.spi_shader_pos_format =
|
||||
S_02870C_POS0_EXPORT_FORMAT(V_02870C_SPI_SHADER_4COMP) |
|
||||
S_02870C_POS1_EXPORT_FORMAT(outinfo->pos_exports > 1 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE) |
|
||||
S_02870C_POS2_EXPORT_FORMAT(outinfo->pos_exports > 2 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE) |
|
||||
S_02870C_POS3_EXPORT_FORMAT(outinfo->pos_exports > 3 ?
|
||||
V_02870C_SPI_SHADER_4COMP :
|
||||
V_02870C_SPI_SHADER_NONE);
|
||||
|
||||
pipeline->graphics.vs.spi_vs_out_config = S_0286C4_VS_EXPORT_COUNT(MAX2(1, outinfo->param_exports) - 1);
|
||||
/* only emitted on pre-VI */
|
||||
pipeline->graphics.vs.vgt_reuse_off = S_028AB4_REUSE_OFF(outinfo->writes_viewport_index);
|
||||
}
|
||||
|
||||
static uint32_t offset_to_ps_input(uint32_t offset, bool flat_shade)
|
||||
@@ -2093,7 +2108,7 @@ radv_pipeline_init(struct radv_pipeline *pipeline,
|
||||
V_028710_SPI_SHADER_ZERO;
|
||||
|
||||
calculate_vgt_gs_mode(pipeline);
|
||||
calculate_pa_cl_vs_out_cntl(pipeline);
|
||||
calculate_vs_outinfo(pipeline);
|
||||
calculate_ps_inputs(pipeline);
|
||||
|
||||
for (unsigned i = 0; i < MESA_SHADER_STAGES; i++) {
|
||||
|
@@ -1110,6 +1110,13 @@ struct radv_vertex_elements_info {
|
||||
uint32_t count;
|
||||
};
|
||||
|
||||
struct radv_vs_state {
|
||||
uint32_t pa_cl_vs_out_cntl;
|
||||
uint32_t spi_shader_pos_format;
|
||||
uint32_t spi_vs_out_config;
|
||||
uint32_t vgt_reuse_off;
|
||||
};
|
||||
|
||||
#define SI_GS_PER_ES 128
|
||||
|
||||
struct radv_pipeline {
|
||||
@@ -1137,6 +1144,7 @@ struct radv_pipeline {
|
||||
struct radv_multisample_state ms;
|
||||
struct radv_tessellation_state tess;
|
||||
struct radv_gs_state gs;
|
||||
struct radv_vs_state vs;
|
||||
uint32_t db_shader_control;
|
||||
uint32_t shader_z_format;
|
||||
unsigned prim;
|
||||
@@ -1150,7 +1158,6 @@ struct radv_pipeline {
|
||||
unsigned gsvs_ring_size;
|
||||
uint32_t ps_input_cntl[32];
|
||||
uint32_t ps_input_cntl_num;
|
||||
uint32_t pa_cl_vs_out_cntl;
|
||||
uint32_t vgt_shader_stages_en;
|
||||
uint32_t vtx_base_sgpr;
|
||||
uint32_t base_ia_multi_vgt_param;
|
||||
|
Reference in New Issue
Block a user